Search Results for author: Liang Wang

Found 306 papers, 111 papers with code

DCT-Centered Temporal Relation Extraction

no code implementations COLING 2022 Liang Wang, Peifeng Li, Sheng Xu

Most previous work on temporal relation extraction only focused on extracting the temporal relations among events or suffered from the issue of different expressions of events, timexes and Document Creation Time (DCT).

Multi-Task Learning Relation +2

Prediction and Recovery for Adaptive Low-Resolution Person Re-Identification

no code implementations ECCV 2020 Ke Han, Yan Huang, Zerui Chen, Liang Wang, Tieniu Tan

In this paper, we propose a novel Prediction, Recovery and Identification (PRI) model for LR re-id, which adaptively recovers missing details by predicting a preferable scale factor based on the image content.

Person Re-Identification Super-Resolution

Towards Part-aware Monocular 3D Human Pose Estimation: An Architecture Search Approach

no code implementations ECCV 2020 Zerui Chen, Yan Huang, Hongyuan Yu, Bin Xue, Ke Han, Yiru Guo, Liang Wang

With roughly the same computational complexity as previous models, our approach achieves state-of-the-art results on both the single-person and multi-person 3D pose estimation benchmarks.

3D Pose Estimation Monocular 3D Human Pose Estimation

Out-of-distribution Rumor Detection via Test-Time Adaptation

no code implementations26 Mar 2024 Xiang Tao, Mingqing Zhang, Qiang Liu, Shu Wu, Liang Wang

This method models the propagation of news in the form of a propagation graph, and builds propagation graph test-time adaptation framework, enhancing the model's adaptability and robustness when facing OOD problems.

Test-time Adaptation

Antigen-Specific Antibody Design via Direct Energy-based Preference Optimization

no code implementations25 Mar 2024 Xiangxin Zhou, Dongyu Xue, Ruizhe Chen, Zaixiang Zheng, Liang Wang, Quanquan Gu

Antibody design, a crucial task with significant implications across various disciplines such as therapeutics and biology, presents considerable challenges due to its intricate nature.

Total Energy

KEBench: A Benchmark on Knowledge Editing for Large Vision-Language Models

no code implementations12 Mar 2024 Han Huang, Haitian Zhong, Qiang Liu, Shu Wu, Liang Wang, Tieniu Tan

We conducted experiments of different editing methods on five LVLMs, and thoroughly analyze how these methods impact the models.

knowledge editing

Debiasing Multimodal Large Language Models

1 code implementation8 Mar 2024 Yi-Fan Zhang, Weichen Yu, Qingsong Wen, Xue Wang, Zhang Zhang, Liang Wang, Rong Jin, Tieniu Tan

In the realms of computer vision and natural language processing, Large Vision-Language Models (LVLMs) have become indispensable tools, proficient in generating textual descriptions based on visual inputs.

Fairness Question Answering

PromptIQA: Boosting the Performance and Generalization for No-Reference Image Quality Assessment via Prompts

no code implementations8 Mar 2024 Zewen Chen, Haina Qin, Juan Wang, Chunfeng Yuan, Bing Li, Weiming Hu, Liang Wang

On the other hand, PromptIQA is trained on a mixed dataset with two proposed data augmentation strategies to learn diverse requirements, thus enabling it to effectively adapt to new requirements.

Data Augmentation No-Reference Image Quality Assessment

DecompOpt: Controllable and Decomposed Diffusion Models for Structure-based Molecular Optimization

no code implementations7 Mar 2024 Xiangxin Zhou, Xiwei Cheng, Yuwei Yang, Yu Bao, Liang Wang, Quanquan Gu

DecompOpt presents a new generation paradigm which combines optimization with conditional diffusion models to achieve desired properties while adhering to the molecular grammar.

Drug Discovery

Bridging Text and Molecule: A Survey on Multimodal Frameworks for Molecule

no code implementations7 Mar 2024 Yi Xiao, Xiangxin Zhou, Qiang Liu, Liang Wang

In this paper, we present the first systematic survey on multimodal frameworks for molecules research.

Drug Discovery

Stabilizing Policy Gradients for Stochastic Differential Equations via Consistency with Perturbation Process

no code implementations7 Mar 2024 Xiangxin Zhou, Liang Wang, Yichi Zhou

Nevertheless, when applying policy gradients to SDEs, since the policy gradient is estimated on a finite set of trajectories, it can be ill-defined, and the policy behavior in data-scarce regions may be uncontrolled.

Policy Gradient Methods

Evolving to the Future: Unseen Event Adaptive Fake News Detection on Social Media

no code implementations29 Feb 2024 Jiajun Zhang, ZHIXUN LI, Qiang Liu, Shu Wu, Liang Wang

With the rapid development of social media, the wide dissemination of fake news on social media is increasingly threatening both individuals and society.

Contrastive Learning Fake News Detection

BlendSQL: A Scalable Dialect for Unifying Hybrid Question Answering in Relational Algebra

1 code implementation27 Feb 2024 Parker Glenn, Parag Pravin Dakle, Liang Wang, Preethi Raghavan

Many existing end-to-end systems for hybrid question answering tasks can often be boiled down to a "prompt-and-pray" paradigm, where the user has limited control and insight into the intermediate reasoning steps used to achieve the final result.

Question Answering

Heterogeneous Graph Reasoning for Fact Checking over Texts and Tables

1 code implementation20 Feb 2024 Haisong Gong, Weizhi Xu, Shu Wu, Qiang Liu, Liang Wang

To address this, we propose a novel word-level Heterogeneous-graph-based model for Fact Checking over unstructured and structured information, namely HeterFC.

Fact Checking Language Modelling +1

Text-Guided Molecule Generation with Diffusion Language Model

1 code implementation20 Feb 2024 Haisong Gong, Qiang Liu, Shu Wu, Liang Wang

In this work, we propose the Text-Guided Molecule Generation with Diffusion Language Model (TGM-DLM), a novel approach that leverages diffusion models to address the limitations of autoregressive methods.

Language Modelling Text-based de novo Molecule Generation +1

Logical Closed Loop: Uncovering Object Hallucinations in Large Vision-Language Models

1 code implementation18 Feb 2024 Junfei Wu, Qiang Liu, Ding Wang, Jinghao Zhang, Shu Wu, Liang Wang, Tieniu Tan

In this work, we adopt the intuition that the LVLM tends to respond logically consistently for existent objects but inconsistently for hallucinated objects.

Hallucination Object

Stealthy Attack on Large Language Model based Recommendation

no code implementations18 Feb 2024 Jinghao Zhang, YuTing Liu, Qiang Liu, Shu Wu, Guibing Guo, Liang Wang

Recently, the powerful large language models (LLMs) have been instrumental in propelling the progress of recommender systems (RS).

Language Modelling Large Language Model +1

Generative Representational Instruction Tuning

2 code implementations15 Feb 2024 Niklas Muennighoff, Hongjin Su, Liang Wang, Nan Yang, Furu Wei, Tao Yu, Amanpreet Singh, Douwe Kiela

Notably, we find that GRIT matches training on only generative or embedding data, thus we can unify both at no performance loss.

Language Modelling Large Language Model +1

Variational Continual Test-Time Adaptation

no code implementations13 Feb 2024 Fan Lyu, Kaile Du, Yuyang Li, Hanyu Zhao, Zhang Zhang, Guangcan Liu, Liang Wang

At the source stage, we transform a pre-trained deterministic model into a Bayesian Neural Network (BNN) via a variational warm-up strategy, injecting uncertainties into the model.

Test-time Adaptation Variational Inference

Rethinking Graph Masked Autoencoders through Alignment and Uniformity

1 code implementation11 Feb 2024 Xiang Tao, Qiang Liu, Shu Wu, Liang Wang

Based on our theoretical analysis, we further identify the limitations of the GraphMAE from the perspectives of alignment and uniformity, which have been considered as two key properties of high-quality representations in GCL.

Contrastive Learning Self-Supervised Learning

Multilingual E5 Text Embeddings: A Technical Report

1 code implementation8 Feb 2024 Liang Wang, Nan Yang, Xiaolong Huang, Linjun Yang, Rangan Majumder, Furu Wei

This technical report presents the training methodology and evaluation results of the open-source multilingual E5 text embedding models, released in mid-2023.

Can Large Language Models Detect Rumors on Social Media?

no code implementations6 Feb 2024 Qiang Liu, Xiang Tao, Junfei Wu, Shu Wu, Liang Wang

In this work, we investigate to use Large Language Models (LLMs) for rumor detection on social media.

Enhancing Human Experience in Human-Agent Collaboration: A Human-Centered Modeling Approach Based on Positive Human Gain

no code implementations28 Jan 2024 Yiming Gao, Feiyu Liu, Liang Wang, Zhenjie Lian, Dehua Zheng, Weixuan Wang, Wenjin Yang, Siqin Li, Xianliang Wang, Wenhui Chen, Jing Dai, Qiang Fu, Wei Yang, Lanxiao Huang, Wei Liu

We expect that agents should learn to enhance the extent to which humans achieve these goals while maintaining agents' original abilities (e. g., winning games).

Knowledge Guided Entity-aware Video Captioning and A Basketball Benchmark

no code implementations25 Jan 2024 Zeyu Xi, Ge Shi, Xuefen Li, Junchi Yan, Zun Li, Lifang Wu, Zilin Liu, Liang Wang

We develop a knowledge guided entity-aware video captioning network (KEANet) based on a candidate player list in encoder-decoder form for basketball live text broadcast.

Video Captioning

Has Your Pretrained Model Improved? A Multi-head Posterior Based Approach

no code implementations2 Jan 2024 Prince Aboagye, Yan Zheng, Junpeng Wang, Uday Singh Saini, Xin Dai, Michael Yeh, Yujie Fan, Zhongfang Zhuang, Shubham Jain, Liang Wang, Wei zhang

The emergence of pre-trained models has significantly impacted Natural Language Processing (NLP) and Computer Vision to relational datasets.

Elastic Multi-Gradient Descent for Parallel Continual Learning

no code implementations2 Jan 2024 Fan Lyu, Wei Feng, Yuepan Li, Qing Sun, Fanhua Shang, Liang Wan, Liang Wang

The goal of Continual Learning (CL) is to continuously learn from new data streams and accomplish the corresponding tasks.

Continual Learning

Improving Text Embeddings with Large Language Models

1 code implementation31 Dec 2023 Liang Wang, Nan Yang, Xiaolong Huang, Linjun Yang, Rangan Majumder, Furu Wei

In this paper, we introduce a novel and simple method for obtaining high-quality text embeddings using only synthetic data and less than 1k training steps.

Assaying on the Robustness of Zero-Shot Machine-Generated Text Detectors

1 code implementation20 Dec 2023 Yi-Fan Zhang, Zhang Zhang, Liang Wang, Tieniu Tan, Rong Jin

In an effort to address these issues, we delve into the realm of zero-shot machine-generated text detection.

Binary Classification Text Detection +1

Scene 3-D Reconstruction System in Scattering Medium

no code implementations14 Dec 2023 Zhuoyifan Zhang, Lu Zhang, Liang Wang, Haoming Wu

The research on neural radiance fields for new view synthesis has experienced explosive growth with the development of new models and extensions.

3D Reconstruction Pose Estimation

Model-free Test Time Adaptation for Out-Of-Distribution Detection

no code implementations28 Nov 2023 Yifan Zhang, Xue Wang, Tian Zhou, Kun Yuan, Zhang Zhang, Liang Wang, Rong Jin, Tieniu Tan

We demonstrate the effectiveness of \abbr through comprehensive experiments on multiple OOD detection benchmarks, extensive empirical studies show that \abbr significantly improves the performance of OOD detection over state-of-the-art methods.

Decision Making Out-of-Distribution Detection +2

Learning Decentralized Traffic Signal Controllers with Multi-Agent Graph Reinforcement Learning

no code implementations7 Nov 2023 Yao Zhang, Zhiwen Yu, Jun Zhang, Liang Wang, Tom H. Luan, Bin Guo, Chau Yuen

Nevertheless, existing MARL algorithms ignore effective information aggregation which is fundamental for improving the learning capacity of decentralized agents.

Graph Learning Multi-agent Reinforcement Learning +1

Temporal Treasure Hunt: Content-based Time Series Retrieval System for Discovering Insights

no code implementations5 Nov 2023 Chin-Chia Michael Yeh, Huiyuan Chen, Xin Dai, Yan Zheng, Yujie Fan, Vivian Lai, Junpeng Wang, Audrey Der, Zhongfang Zhuang, Liang Wang, Wei zhang

To facilitate this investigation, we introduce a CTSR benchmark dataset that comprises time series data from a variety of domains, such as motion, power demand, and traffic.

Retrieval Time Series +1

Time Series Synthesis Using the Matrix Profile for Anonymization

no code implementations5 Nov 2023 Audrey Der, Chin-Chia Michael Yeh, Yan Zheng, Junpeng Wang, Huiyuan Chen, Zhongfang Zhuang, Liang Wang, Wei zhang, Eamonn Keogh

As a result, unmodified data mining tools can obtain near-identical performance on the synthesized time series as on the original time series.

Time Series

Ego-Network Transformer for Subsequence Classification in Time Series Data

no code implementations5 Nov 2023 Chin-Chia Michael Yeh, Huiyuan Chen, Yujie Fan, Xin Dai, Yan Zheng, Vivian Lai, Junpeng Wang, Zhongfang Zhuang, Liang Wang, Wei zhang, Eamonn Keogh

The ego-networks of all subsequences collectively form a time series subsequence graph, and we introduce an algorithm to efficiently construct this graph.

Time Series Time Series Classification

Visual Analytics for Efficient Image Exploration and User-Guided Image Captioning

no code implementations2 Nov 2023 Yiran Li, Junpeng Wang, Prince Aboagye, Michael Yeh, Yan Zheng, Liang Wang, Wei zhang, Kwan-Liu Ma

On the one hand, by visually examining the captions automatically generated from language-image models for an image dataset, we gain deeper insights into the semantic underpinnings of the visual contents, unearthing data biases that may be entrenched within the dataset.

Efficient Exploration Image Captioning

Combating Bilateral Edge Noise for Robust Link Prediction

1 code implementation NeurIPS 2023 Zhanke Zhou, Jiangchao Yao, Jiaxu Liu, Xiawei Guo, Quanming Yao, Li He, Liang Wang, Bo Zheng, Bo Han

To address this dilemma, we propose an information-theory-guided principle, Robust Graph Information Bottleneck (RGIB), to extract reliable supervision signals and avoid representation collapse.

Denoising Link Prediction +1

Large Search Model: Redefining Search Stack in the Era of LLMs

no code implementations23 Oct 2023 Liang Wang, Nan Yang, Xiaolong Huang, Linjun Yang, Rangan Majumder, Furu Wei

Modern search engines are built on a stack of different components, including query understanding, retrieval, multi-stage ranking, and question answering, among others.

Language Modelling Large Language Model +3

EX-FEVER: A Dataset for Multi-hop Explainable Fact Verification

1 code implementation15 Oct 2023 Huanhuan Ma, Weizhi Xu, Yifan Wei, Liuji Chen, Qiang Liu, Shu Wu, Liang Wang

Each instance is accompanied by a veracity label and an explanation that outlines the reasoning path supporting the veracity classification.

Claim Verification Explanation Generation +3

Fine-Tuning LLaMA for Multi-Stage Text Retrieval

1 code implementation12 Oct 2023 Xueguang Ma, Liang Wang, Nan Yang, Furu Wei, Jimmy Lin

Our findings demonstrate that the effectiveness of large language models indeed surpasses that of smaller models.

Passage Retrieval Retrieval +1

An Efficient Content-based Time Series Retrieval System

no code implementations5 Oct 2023 Chin-Chia Michael Yeh, Huiyuan Chen, Xin Dai, Yan Zheng, Junpeng Wang, Vivian Lai, Yujie Fan, Audrey Der, Zhongfang Zhuang, Liang Wang, Wei zhang, Jeff M. Phillips

A Content-based Time Series Retrieval (CTSR) system is an information retrieval system for users to interact with time series emerged from multiple domains, such as finance, healthcare, and manufacturing.

Information Retrieval Retrieval +1

Toward a Foundation Model for Time Series Data

no code implementations5 Oct 2023 Chin-Chia Michael Yeh, Xin Dai, Huiyuan Chen, Yan Zheng, Yujie Fan, Audrey Der, Vivian Lai, Zhongfang Zhuang, Junpeng Wang, Liang Wang, Wei zhang

A foundation model is a machine learning model trained on a large and diverse set of data, typically using self-supervised learning-based pre-training techniques, that can be adapted to various downstream tasks.

Self-Supervised Learning Time Series

OneNet: Enhancing Time Series Forecasting Models under Concept Drift by Online Ensembling

1 code implementation NeurIPS 2023 Yi-Fan Zhang, Qingsong Wen, Xue Wang, Weiqi Chen, Liang Sun, Zhang Zhang, Liang Wang, Rong Jin, Tieniu Tan

Online updating of time series forecasting models aims to address the concept drifting problem by efficiently updating forecasting models based on streaming data.

Time Series Time Series Forecasting

PoSE: Efficient Context Window Extension of LLMs via Positional Skip-wise Training

1 code implementation19 Sep 2023 Dawei Zhu, Nan Yang, Liang Wang, YiFan Song, Wenhao Wu, Furu Wei, Sujian Li

To decouple train length from target length for efficient context window extension, we propose Positional Skip-wisE (PoSE) training that smartly simulates long inputs using a fixed context window.

Position

Multi-Semantic Fusion Model for Generalized Zero-Shot Skeleton-Based Action Recognition

1 code implementation18 Sep 2023 Ming-Zhe Li, Zhen Jia, Zhang Zhang, Zhanyu Ma, Liang Wang

In order to solve this dilemma, we propose a multi-semantic fusion (MSF) model for improving the performance of GZSSAR, where two kinds of class-level textual descriptions (i. e., action descriptions and motion descriptions), are collected as auxiliary semantic information to enhance the learning efficacy of generalizable skeleton features.

Action Recognition Generalized Zero Shot skeletal action recognition +1

CvFormer: Cross-view transFormers with Pre-training for fMRI Analysis of Human Brain

no code implementations14 Sep 2023 Xiangzhu Meng, Qiang Liu, Shu Wu, Liang Wang

In recent years, functional magnetic resonance imaging (fMRI) has been widely utilized to diagnose neurological disease, by exploiting the region of interest (RoI) nodes as well as their connectivities in human brain.

Contrastive Learning

TiBGL: Template-induced Brain Graph Learning for Functional Neuroimaging Analysis

no code implementations14 Sep 2023 Xiangzhu Meng, Wei Wei, Qiang Liu, Shu Wu, Liang Wang

Motivated by the related medical findings on functional connectivites, TiBGL proposes template-induced brain graph learning to extract template brain graphs for all groups.

Graph Learning

Illumination Distillation Framework for Nighttime Person Re-Identification and A New Benchmark

1 code implementation31 Aug 2023 Andong Lu, Zhang Zhang, Yan Huang, Yifan Zhang, Chenglong Li, Jin Tang, Liang Wang

The illumination enhancement branch first estimates an enhanced image from the nighttime image using a nonlinear curve mapping method and then extracts the enhanced features.

Person Re-Identification

Pose-Graph Attentional Graph Neural Network for Lidar Place Recognition

1 code implementation31 Aug 2023 Milad Ramezani, Liang Wang, Joshua Knights, Zhibin Li, Pauline Pounds, Peyman Moghadam

This paper proposes a pose-graph attentional graph neural network, called P-GAT, which compares (key)nodes between sequential and non-sequential sub-graphs for place recognition tasks as opposed to a common frame-to-frame retrieval problem formulation currently implemented in SOTA place recognition methods.

Domain Adaptation Retrieval

Collaborative Route Planning of UAVs, Workers and Cars for Crowdsensing in Disaster Response

no code implementations21 Aug 2023 Lei Han, Chunyu Tu, Zhiwen Yu, Zhiyong Yu, Weihua Shan, Liang Wang, Bin Guo

In this paper, we explicitly address the route planning for a group of agents, including UAVs, workers, and cars, with the goal of maximizing the task completion rate.

Decision Making Disaster Response

EdgeMA: Model Adaptation System for Real-Time Video Analytics on Edge Devices

no code implementations17 Aug 2023 Liang Wang, Nan Zhang, Xiaoyang Qu, Jianzong Wang, Jiguang Wan, Guokuan Li, Kaiyu Hu, Guilin Jiang, Jing Xiao

In this paper, we introduce EdgeMA, a practical and efficient video analytics system designed to adapt models to shifts in real-world video streams over time, addressing the data drift problem.

End-to-end Alternating Optimization for Real-World Blind Super Resolution

2 code implementations17 Aug 2023 Zhengxiong Luo, Yan Huang, Shang Li, Liang Wang, Tieniu Tan

To address this issue, instead of considering these two problems independently, we adopt an alternating optimization algorithm, which can estimate the degradation and restore the SR image in a single model.

Blind Super-Resolution Super-Resolution

PPI-NET: End-to-End Parametric Primitive Inference

no code implementations3 Aug 2023 Liang Wang, Xiaogang Wang

In engineering applications, line, circle, arc, and point are collectively referred to as primitives, and they play a crucial role in path planning, simulation analysis, and manufacturing.

EmbeddingTree: Hierarchical Exploration of Entity Features in Embedding

no code implementations2 Aug 2023 Yan Zheng, Junpeng Wang, Chin-Chia Michael Yeh, Yujie Fan, Huiyuan Chen, Liang Wang, Wei zhang

The tool helps users discover nuance features of data entities, perform feature denoising/injecting in embedding training, and generate embeddings for unseen entities.

Denoising

Learning to Retrieve In-Context Examples for Large Language Models

2 code implementations14 Jul 2023 Liang Wang, Nan Yang, Furu Wei

Our framework initially trains a reward model based on LLM feedback to evaluate the quality of candidate examples, followed by knowledge distillation to train a bi-encoder based dense retriever.

In-Context Learning Knowledge Distillation

Shoggoth: Towards Efficient Edge-Cloud Collaborative Real-Time Video Inference via Adaptive Online Learning

no code implementations27 Jun 2023 Liang Wang, Kai Lu, Nan Zhang, Xiaoyang Qu, Jianzong Wang, Jiguang Wan, Guokuan Li, Jing Xiao

This paper proposes Shoggoth, an efficient edge-cloud collaborative architecture, for boosting inference performance on real-time video of changing scenes.

Knowledge Distillation

Learning to Rank in Generative Retrieval

2 code implementations27 Jun 2023 Yongqi Li, Nan Yang, Liang Wang, Furu Wei, Wenjie Li

However, only learning to generate is insufficient for generative retrieval.

Learning-To-Rank Passage Ranking +3

Mining Stable Preferences: Adaptive Modality Decorrelation for Multimedia Recommendation

no code implementations25 Jun 2023 Jinghao Zhang, Qiang Liu, Shu Wu, Liang Wang

Even worse, the strong statistical correlation might mislead models to learn the spurious preference towards inconsequential modalities.

Multimedia recommendation

Efficient Token-Guided Image-Text Retrieval with Consistent Multimodal Contrastive Training

1 code implementation15 Jun 2023 Chong Liu, Yuqi Zhang, Hongsong Wang, Weihua Chen, Fan Wang, Yan Huang, Yi-Dong Shen, Liang Wang

Most previous works either simply learn coarse-grained representations of the overall image and text, or elaborately establish the correspondence between image regions or pixels and text words.

Representation Learning Retrieval +1

Adversarial Constrained Bidding via Minimax Regret Optimization with Causality-Aware Reinforcement Learning

no code implementations12 Jun 2023 Haozhe Wang, Chao Du, Panyan Fang, Li He, Liang Wang, Bo Zheng

In this regard, we explore the problem of constrained bidding in adversarial bidding environments, which assumes no knowledge about the adversarial factors.

Meta-Learning reinforcement-learning

Exploring Model Dynamics for Accumulative Poisoning Discovery

1 code implementation6 Jun 2023 Jianing Zhu, Xiawei Guo, Jiangchao Yao, Chao Du, Li He, Shuo Yuan, Tongliang Liu, Liang Wang, Bo Han

In this paper, we dive into the perspective of model dynamics and propose a novel information measure, namely, Memorization Discrepancy, to explore the defense via the model-level information.

Memorization

PDT: Pretrained Dual Transformers for Time-aware Bipartite Graphs

no code implementations2 Jun 2023 Xin Dai, Yujie Fan, Zhongfang Zhuang, Shubham Jain, Chin-Chia Michael Yeh, Junpeng Wang, Liang Wang, Yan Zheng, Prince Osei Aboagye, Wei zhang

Pre-training on large models is prevalent and emerging with the ever-growing user-generated content in many machine learning application categories.

Contrastive Learning

Multiview Identifiers Enhanced Generative Retrieval

1 code implementation26 May 2023 Yongqi Li, Nan Yang, Liang Wang, Furu Wei, Wenjie Li

Instead of simply matching a query to pre-existing passages, generative retrieval generates identifier strings of passages as the retrieval target.

Retrieval

On Structural Expressive Power of Graph Transformers

no code implementations23 May 2023 Wenhao Zhu, Tianyu Wen, Guojie Song, Liang Wang, Bo Zheng

Graph Transformer has recently received wide attention in the research community with its outstanding performance, yet its structural expressive power has not been well analyzed.

FedAds: A Benchmark for Privacy-Preserving CVR Estimation with Vertical Federated Learning

no code implementations15 May 2023 Penghui Wei, Hongjian Dou, Shaoguo Liu, Rongjun Tang, Li Liu, Liang Wang, Bo Zheng

We introduce FedAds, the first benchmark for CVR estimation with vFL, to facilitate standardized and systematical evaluations for vFL algorithms.

Privacy Preserving Vertical Federated Learning

Hierarchical Transformer for Scalable Graph Learning

no code implementations4 May 2023 Wenhao Zhu, Tianyu Wen, Guojie Song, Xiaojun Ma, Liang Wang

Graph Transformer is gaining increasing attention in the field of machine learning and has demonstrated state-of-the-art performance on benchmarks for graph representation learning.

Graph Learning Graph Representation Learning

AdaNPC: Exploring Non-Parametric Classifier for Test-Time Adaptation

1 code implementation25 Apr 2023 Yi-Fan Zhang, Xue Wang, Kexin Jin, Kun Yuan, Zhang Zhang, Liang Wang, Rong Jin, Tieniu Tan

In particular, when the adaptation target is a series of domains, the adaptation accuracy of AdaNPC is 50% higher than advanced TTA methods.

Domain Generalization Test-time Adaptation

Out-of-distribution Evidence-aware Fake News Detection via Dual Adversarial Debiasing

no code implementations25 Apr 2023 Qiang Liu, Junfei Wu, Shu Wu, Liang Wang

Then, DAL reversely optimizes news-aspect and evidence-aspect debiasing discriminators to mitigate the impact of news and evidence content biases.

Fake News Detection

Towards Effective and Interpretable Human-Agent Collaboration in MOBA Games: A Communication Perspective

no code implementations23 Apr 2023 Yiming Gao, Feiyu Liu, Liang Wang, Zhenjie Lian, Weixuan Wang, Siqin Li, Xianliang Wang, Xianhan Zeng, Rundong Wang, Jiawei Wang, Qiang Fu, Wei Yang, Lanxiao Huang, Wei Liu

MOBA games, e. g., Dota2 and Honor of Kings, have been actively used as the testbed for the recent AI research on games, and various AI systems have been developed at the human level so far.

Deep Stable Multi-Interest Learning for Out-of-distribution Sequential Recommendation

no code implementations12 Apr 2023 Qiang Liu, Zhaocheng Liu, Zhenxi Zhu, Shu Wu, Liang Wang

However, none of existing multi-interest recommendation models consider the Out-Of-Distribution (OOD) generalization problem, in which interest distribution may change.

Sequential Recommendation

ETPNav: Evolving Topological Planning for Vision-Language Navigation in Continuous Environments

1 code implementation6 Apr 2023 Dong An, Hanqing Wang, Wenguan Wang, Zun Wang, Yan Huang, Keji He, Liang Wang

To develop a robust VLN-CE agent, we propose a new navigation framework, ETPNav, which focuses on two critical skills: 1) the capability to abstract environments and generate long-range navigation plans, and 2) the ability of obstacle-avoiding control in continuous environments.

Autonomous Navigation Navigate +1

How Does Attention Work in Vision Transformers? A Visual Analytics Attempt

no code implementations24 Mar 2023 Yiran Li, Junpeng Wang, Xin Dai, Liang Wang, Chin-Chia Michael Yeh, Yan Zheng, Wei zhang, Kwan-Liu Ma

Multi-head self-attentions are then applied to the sequence to learn the attention between patches.

Semantic Prompt for Few-Shot Image Recognition

1 code implementation CVPR 2023 Wentao Chen, Chenyang Si, Zhang Zhang, Liang Wang, Zilei Wang, Tieniu Tan

Instead of the naive exploitation of semantic information for remedying classifiers, we explore leveraging semantic information as prompts to tune the visual feature extraction network adaptively.

Few-Shot Learning

VideoFusion: Decomposed Diffusion Models for High-Quality Video Generation

1 code implementation CVPR 2023 Zhengxiong Luo, Dayou Chen, Yingya Zhang, Yan Huang, Liang Wang, Yujun Shen, Deli Zhao, Jingren Zhou, Tieniu Tan

A diffusion probabilistic model (DPM), which constructs a forward diffusion process by gradually adding noise to data points and learns the reverse denoising process to generate new samples, has been shown to handle complex data distribution.

Code Generation Denoising +4

Query2doc: Query Expansion with Large Language Models

no code implementations14 Mar 2023 Liang Wang, Nan Yang, Furu Wei

This paper introduces a simple yet effective query expansion approach, denoted as query2doc, to improve both sparse and dense retrieval systems.

Memorization Retrieval

3D Shape Temporal Aggregation for Video-Based Clothing-Change Person Re-Identication

1 code implementation Asian Conference on Computer Vision 2023 Ke Han, Shaogang Gong, Yan Huang, Liang Wang, Tieniu Tan

However, existing Re-ID methods usually generate 3D body shapes without considering identity modeling, which severely weakens the discriminability of 3D human shapes.

3D Shape Generation Person Re-Identification

Knowledge Augmented Relation Inference for Group Activity Recognition

no code implementations28 Feb 2023 Xianglong Lang, Zhuming Wang, Zun Li, Meng Tian, Ge Shi, Lifang Wu, Liang Wang

Specifically, the framework consists of a Visual Representation Module to extract individual appearance features, a Knowledge Augmented Semantic Relation Module explore semantic representations of individual actions, and a Knowledge-Semantic-Visual Interaction Module aims to integrate visual and semantic information by the knowledge.

Group Activity Recognition Relation

Securing IoT Communication using Physical Sensor Data -- Graph Layer Security with Federated Multi-Agent Deep Reinforcement Learning

no code implementations24 Feb 2023 Liang Wang, Zhuangkun Wei, Weisi Guo

This paper presents a Federated multi-agent Deep reinforcement learning-assisted Distributed Key generation scheme (FD2K), which fully exploits the common features of physical dynamics to establish secret key between legitimate users.

Federated Learning

Sketch Less Face Image Retrieval: A New Challenge

1 code implementation11 Feb 2023 Dawei Dai, Yutang Li, Liang Wang, Shiyu Fu, Shuyin Xia, Guoyin Wang

In this study, we proposed a new task named sketch less face image retrieval (SLFIR), in which the retrieval was carried out at each stroke and aim to retrieve the target face photo using a partial sketch with as few strokes as possible (see Fig. 1).

Face Image Retrieval Retrieval

RLTP: Reinforcement Learning to Pace for Delayed Impression Modeling in Preloaded Ads

no code implementations6 Feb 2023 Penghui Wei, Yongqiang Chen, Shaoguo Liu, Liang Wang, Bo Zheng

In a whole delivery period, advertisers usually desire a certain impression count for the ads, and they also expect that the delivery performance is as good as possible (e. g., obtaining high click-through rate).

reinforcement-learning Reinforcement Learning (RL)

Hybrid Contrastive Constraints for Multi-Scenario Ad Ranking

no code implementations6 Feb 2023 Shanlei Mu, Penghui Wei, Wayne Xin Zhao, Shaoguo Liu, Liang Wang, Bo Zheng

In this paper, we propose a Hybrid Contrastive Constrained approach (HC^2) for multi-scenario ad ranking.

Contrastive Learning

Breathing cluster in complex neuron-astrocyte networks

no code implementations26 Jan 2023 Ya Wang, Liang Wang, Huawei Fan, Jun Ma, Hui Cao, Xingang Wang

It is revealed that the contents of the cluster are determined by the network symmetry and the breathing activities are due to the interplay between the neural network and the astrocyte.

Edge Preserving Implicit Surface Representation of Point Clouds

no code implementations12 Jan 2023 Xiaogang Wang, Yuhang Cheng, Liang Wang, Jiangbo Lu, Kai Xu, GuoQiang Xiao

Among them, the differential Laplican regularizer can effectively alleviate the implicit surface unsmoothness caused by the point cloud quality deteriorates; Meanwhile, in order to reduce the excessive smoothing at the edge regions of implicit suface, we proposed a dynamic edge extract strategy for sampling near the sharp edge of point cloud, which can effectively avoid the Laplacian regularizer from smoothing all regions.

3D Reconstruction Surface Reconstruction

Clothing-Change Feature Augmentation for Person Re-Identification

no code implementations CVPR 2023 Ke Han, Shaogang Gong, Yan Huang, Liang Wang, Tieniu Tan

Specifically, to formulate meaningful clothing variations in the feature space, our method first estimates a clothing-change normal distribution with intra-ID cross-clothing variances.

Person Re-Identification

Human Image Generation: A Comprehensive Survey

no code implementations17 Dec 2022 Zhen Jia, Zhang Zhang, Liang Wang, Tieniu Tan

Image and video synthesis has become a blooming topic in computer vision and machine learning communities along with the developments of deep generative models, due to its great academic and application value.

Data Augmentation Image Generation +2

BEVBert: Multimodal Map Pre-training for Language-guided Navigation

1 code implementation ICCV 2023 Dong An, Yuankai Qi, Yangguang Li, Yan Huang, Liang Wang, Tieniu Tan, Jing Shao

Concretely, we build a local metric map to explicitly aggregate incomplete observations and remove duplicates, while modeling navigation dependency in a global topological map.

Vision and Language Navigation Visual Navigation

Quantized Wasserstein Procrustes Alignment of Word Embedding Spaces

no code implementations AMTA 2022 Prince O Aboagye, Yan Zheng, Michael Yeh, Junpeng Wang, Zhongfang Zhuang, Huiyuan Chen, Liang Wang, Wei zhang, Jeff Phillips

Optimal Transport (OT) provides a useful geometric framework to estimate the permutation matrix under unsupervised cross-lingual word embedding (CLWE) models that pose the alignment task as a Wasserstein-Procrustes problem.

Bilingual Lexicon Induction Quantization

Teach-DETR: Better Training DETR with Teachers

1 code implementation22 Nov 2022 Linjiang Huang, Kaixin Lu, Guanglu Song, Liang Wang, Si Liu, Yu Liu, Hongsheng Li

In this paper, we present a novel training scheme, namely Teach-DETR, to learn better DETR-based detectors from versatile teacher detectors.

Correlative Preference Transfer with Hierarchical Hypergraph Network for Multi-Domain Recommendation

no code implementations21 Nov 2022 Zixuan Xu, Penghui Wei, Shaoguo Liu, Weimin Zhang, Liang Wang, Bo Zheng

Conventional graph neural network based methods usually deal with each domain separately, or train a shared model to serve all domains.

Marketing Recommendation Systems

Data-driven modeling of Landau damping by physics-informed neural networks

no code implementations2 Nov 2022 Yilan Qin, Jiayu Ma, Mingle Jiang, Chuanfei Dong, Haiyang Fu, Liang Wang, Wenjie Cheng, YaQiu Jin

The multi-moment fluid model is trained with a small fraction of sparsely sampled data from kinetic simulations of Landau damping, using the physics-informed neural network (PINN) and the gradient-enhanced physics-informed neural network (gPINN).

Generalized Inter-class Loss for Gait Recognition

no code implementations13 Oct 2022 Weichen Yu, Hongyuan Yu, Yan Huang, Liang Wang

The proposed method can be generalized to different gait recognition networks and achieves significant improvements.

Gait Recognition

Regularized Graph Structure Learning with Semantic Knowledge for Multi-variates Time-Series Forecasting

1 code implementation12 Oct 2022 Hongyuan Yu, Ting Li, Weichen Yu, Jianguo Li, Yan Huang, Liang Wang, Alex Liu

In this paper, we propose Regularized Graph Structure Learning (RGSL) model to incorporate both explicit prior structure and implicit structure together, and learn the forecasting deep networks along with the graph structure.

Graph Generation Graph structure learning +2

Adversarial Contrastive Learning for Evidence-aware Fake News Detection with Graph Neural Networks

1 code implementation11 Oct 2022 Junfei Wu, Weizhi Xu, Qiang Liu, Shu Wu, Liang Wang

Comprehensive experiments have demonstrated the superiority of GETRAL over the state-of-the-arts and validated the efficacy of semantic mining with graph structure and contrastive learning.

Contrastive Learning Fake News Detection +2

Multi-level Adversarial Spatio-temporal Learning for Footstep Pressure based FoG Detection

no code implementations22 Sep 2022 Kun Hu, Shaohui Mei, Wei Wang, Kaylena A. Ehgoetz Martens, Liang Wang, Simon J. G. Lewis, David D. Feng, Zhiyong Wang

The proposed scheme also sheds light on improving subject-level clinical studies from other scenarios as it can be integrated with many existing deep architectures.

Data-driven, multi-moment fluid modeling of Landau damping

no code implementations10 Sep 2022 Wenjie Cheng, Haiyang Fu, Liang Wang, Chuanfei Dong, YaQiu Jin, Mingle Jiang, Jiayu Ma, Yilan Qin, Kexin Liu

The data-driven fluid modeling of PDEs for complex physical systems may be applied to improve fluid closure and reduce the computational cost of multi-scale modeling of global systems.

In-situ animal behavior classification using knowledge distillation and fixed-point quantization

no code implementations9 Sep 2022 Reza Arablouei, Liang Wang, Caitlin Phillips, Lachlan Currie, Jordan Yates, Greg Bishop-hurley

The evaluation results using two real-world animal behavior classification datasets show that the classification accuracy of the student GRU-MLP models improves appreciably through KD, approaching that of the teacher ResNet model.

Classification Knowledge Distillation +4

Modeling Adaptive Fine-grained Task Relatedness for Joint CTR-CVR Estimation

no code implementations29 Aug 2022 Zihan Lin, Xuanhua Yang, Xiaoyu Peng, Wayne Xin Zhao, Shaoguo Liu, Liang Wang, Bo Zheng

For this purpose, we build a relatedness prediction network, so that it can predict the contrast strength for inter-task representations of an instance.

Contrastive Learning Multi-Task Learning +2

Domain-Specific Risk Minimization for Out-of-Distribution Generalization

1 code implementation18 Aug 2022 Yi-Fan Zhang, Jindong Wang, Jian Liang, Zhang Zhang, Baosheng Yu, Liang Wang, DaCheng Tao, Xing Xie

Our bound motivates two strategies to reduce the gap: the first one is ensembling multiple classifiers to enrich the hypothesis space, then we propose effective gap estimation methods for guiding the selection of a better hypothesis for the target.

Domain Generalization Out-of-Distribution Generalization

Embedding Compression with Hashing for Efficient Representation Learning in Large-Scale Graph

no code implementations11 Aug 2022 Chin-Chia Michael Yeh, Mengting Gu, Yan Zheng, Huiyuan Chen, Javid Ebrahimi, Zhongfang Zhuang, Junpeng Wang, Liang Wang, Wei zhang

Graph neural networks (GNNs) are deep learning models designed specifically for graph data, and they typically rely on node features as the input to the first layer.

Representation Learning

Learning Diverse Document Representations with Deep Query Interactions for Dense Retrieval

1 code implementation8 Aug 2022 Zehan Li, Nan Yang, Liang Wang, Furu Wei

In this paper, we propose a new dense retrieval model which learns diverse document representations with deep query interactions.

Retrieval

Cross-Domain Cross-Set Few-Shot Learning via Learning Compact and Aligned Representations

1 code implementation16 Jul 2022 Wentao Chen, Zhang Zhang, Wei Wang, Liang Wang, Zilei Wang, Tieniu Tan

Different from previous cross-domain FSL work (CD-FSL) that considers the domain shift between base and novel classes, the new problem, termed cross-domain cross-set FSL (CDSC-FSL), requires few-shot learners not only to adapt to the new domain, but also to be consistent between different domains within each novel class.

Few-Shot Learning

Joint Super-Resolution and Inverse Tone-Mapping: A Feature Decomposition Aggregation Network and A New Benchmark

1 code implementation7 Jul 2022 Gang Xu, Yu-chen Yang, Liang Wang, Xian-Tong Zhen, Jun Xu

Joint Super-Resolution and Inverse Tone-Mapping (joint SR-ITM) aims to increase the resolution and dynamic range of low-resolution and standard dynamic range images.

inverse tone mapping Inverse-Tone-Mapping +2

SimLM: Pre-training with Representation Bottleneck for Dense Passage Retrieval

1 code implementation6 Jul 2022 Liang Wang, Nan Yang, Xiaolong Huang, Binxing Jiao, Linjun Yang, Daxin Jiang, Rangan Majumder, Furu Wei

It employs a simple bottleneck architecture that learns to compress the passage information into a dense vector through self-supervised pre-training.

Language Modelling Passage Retrieval +1

A Comprehensive Survey on Deep Gait Recognition: Algorithms, Datasets and Challenges

1 code implementation28 Jun 2022 Chuanfu Shen, Shiqi Yu, Jilong Wang, George Q. Huang, Liang Wang

We provide a comprehensive survey on recent literature using deep learning and a discussion on the privacy and security of gait biometrics.

Gait Recognition Representation Learning

1st Place Solutions for RxR-Habitat Vision-and-Language Navigation Competition (CVPR 2022)

1 code implementation23 Jun 2022 Dong An, Zun Wang, Yangguang Li, Yi Wang, Yicong Hong, Yan Huang, Liang Wang, Jing Shao

Our model consists of three modules: the candidate waypoints predictor (CWP), the history enhanced planner and the tryout controller.

Data Augmentation Vision and Language Navigation

RF-Next: Efficient Receptive Field Search for Convolutional Neural Networks

2 code implementations14 Jun 2022 ShangHua Gao, Zhong-Yu Li, Qi Han, Ming-Ming Cheng, Liang Wang

Our search scheme exploits both global search to find the coarse combinations and local search to get the refined receptive field combinations further.

Action Segmentation Instance Segmentation +5

Towards Personalized Bundle Creative Generation with Contrastive Non-Autoregressive Decoding

no code implementations30 May 2022 Penghui Wei, Shaoguo Liu, Xuanhua Yang, Liang Wang, Bo Zheng

Current bundle generation studies focus on generating a combination of items to improve user experience.

CREATER: CTR-driven Advertising Text Generation with Controlled Pre-Training and Contrastive Fine-Tuning

no code implementations NAACL (ACL) 2022 Penghui Wei, Xuanhua Yang, Shaoguo Liu, Liang Wang, Bo Zheng

This paper focuses on automatically generating the text of an ad, and the goal is that the generated text can capture user interest for achieving higher click-through rate (CTR).

Contrastive Learning Text Generation

Cross-Modality High-Frequency Transformer for MR Image Super-Resolution

no code implementations29 Mar 2022 Chaowei Fang, Dingwen Zhang, Liang Wang, Yulun Zhang, Lechao Cheng, Junwei Han

Improving the resolution of magnetic resonance (MR) image data is critical to computer-aided diagnosis and brain function analysis.

Image Super-Resolution Vocal Bursts Intensity Prediction

AMCAD: Adaptive Mixed-Curvature Representation based Advertisement Retrieval System

no code implementations28 Mar 2022 Zhirong Xu, Shiyang Wen, Junshan Wang, Guojun Liu, Liang Wang, Zhi Yang, Lei Ding, Yan Zhang, Di Zhang, Jian Xu, Bo Zheng

Moreover, to deploy AMCAD in Taobao, one of the largest ecommerce platforms with hundreds of million users, we design an efficient two-layer online retrieval framework for the task of graph based advertisement retrieval.

Graph Embedding Information Retrieval +1

Distributed data analytics

no code implementations26 Mar 2022 Richard Mortier, Hamed Haddadi, Sandra Servia, Liang Wang

A contrasting approach, distributed data analytics, where code and models for training and inference are distributed to the places where data is collected, has been boosted by two recent, ongoing developments: increased processing power and memory capacity available in user devices at the edge of the network, such as smartphones and home assistants; and increased sensitivity to the highly intrusive nature of many of these devices and services and the attendant demands for improved privacy.

Cloud Computing Fraud Detection +2

ZOOMER: Boosting Retrieval on Web-scale Graphs by Regions of Interest

1 code implementation20 Mar 2022 Yuezihan Jiang, Yu Cheng, Hanyu Zhao, Wentao Zhang, Xupeng Miao, Yu He, Liang Wang, Zhi Yang, Bin Cui

We introduce ZOOMER, a system deployed at Taobao, the largest e-commerce platform in China, for training and serving GNN-based recommendations over web-scale graphs.

Retrieval

Meta-Weight Graph Neural Network: Push the Limits Beyond Global Homophily

no code implementations19 Mar 2022 Xiaojun Ma, Qin Chen, Yuanyi Ren, Guojie Song, Liang Wang

These experiments show the excellent expressive power of MWGNN in dealing with graph data with various distributions.

DRTAM: Dual Rank-1 Tensor Attention Module

no code implementations11 Mar 2022 Hanxing Chi, Baihong Lin, Jun Hu, Liang Wang

Recently, attention mechanisms have been extensively investigated in computer vision, but few of them show excellent performance on both large and mobile networks.

Learning the Degradation Distribution for Blind Image Super-Resolution

1 code implementation CVPR 2022 Zhengxiong Luo, Yan Huang, Shang Li, Liang Wang, Tieniu Tan

Compared with previous deterministic degradation models, PDM could model more diverse degradations and generate HR-LR pairs that may better cover the various degradations of test images, and thus prevent the SR model from over-fitting to specific ones.

Image Super-Resolution

Weakly Supervised Temporal Action Localization via Representative Snippet Knowledge Propagation

1 code implementation CVPR 2022 Linjiang Huang, Liang Wang, Hongsheng Li

Our method seeks to mine the representative snippets in each video for propagating information between video snippets to generate better pseudo labels.

Pseudo Label Weakly-supervised Temporal Action Localization +1

Generalizable Person Re-Identification via Self-Supervised Batch Norm Test-Time Adaption

no code implementations1 Mar 2022 Ke Han, Chenyang Si, Yan Huang, Liang Wang, Tieniu Tan

In this paper, we investigate the generalization problem of person re-identification (re-id), whose major challenge is the distribution shift on an unseen domain.

Generalizable Person Re-identification

Deeply Explain CNN via Hierarchical Decomposition

no code implementations23 Jan 2022 Ming-Ming Cheng, Peng-Tao Jiang, Ling-Hao Han, Liang Wang, Philip Torr

The proposed framework can generate a deep hierarchy of strongly associated supporting evidence for the network decision, which provides insight into the decision-making process.

Decision Making

UKD: Debiasing Conversion Rate Estimation via Uncertainty-regularized Knowledge Distillation

no code implementations20 Jan 2022 Zixuan Xu, Penghui Wei, Weimin Zhang, Shaoguo Liu, Liang Wang, Bo Zheng

Then a student model is trained on both clicked and unclicked ads with knowledge distillation, performing uncertainty modeling to alleviate the inherent noise in pseudo-labels.

Knowledge Distillation Selection bias

Learning-From-Disagreement: A Model Comparison and Visual Analytics Framework

no code implementations19 Jan 2022 Junpeng Wang, Liang Wang, Yan Zheng, Chin-Chia Michael Yeh, Shubham Jain, Wei zhang

With these metrics, one can easily identify meta-features with the most complementary behaviors in two classifiers, and use them to better ensemble the classifiers.

Binary Classification

Evidence-aware Fake News Detection with Graph Neural Networks

1 code implementation18 Jan 2022 Weizhi Xu, Junfei Wu, Qiang Liu, Shu Wu, Liang Wang

In this paper, we focus on the evidence-based fake news detection, where several evidences are utilized to probe the veracity of news (i. e., a claim).

Fake News Detection Graph structure learning

Incremental Cross-view Mutual Distillation for Self-supervised Medical CT Synthesis

no code implementations CVPR 2022 Chaowei Fang, Liang Wang, Dingwen Zhang, Jun Xu, Yixuan Yuan, Junwei Han

Under this circumstance, the models learned from different views can distill valuable knowledge to guide the learning processes of each other.

Self-Supervised Learning

Knowledge Graph Embedding in E-commerce Applications: Attentive Reasoning, Explanations, and Transferable Rules

no code implementations16 Dec 2021 Wen Zhang, Shumin Deng, Mingyang Chen, Liang Wang, Qiang Chen, Feiyu Xiong, Xiangwen Liu, Huajun Chen

We first identity three important desiderata for e-commerce KG systems: 1) attentive reasoning, reasoning over a few target relations of more concerns instead of all; 2) explanation, providing explanations for a prediction to help both users and business operators understand why the prediction is made; 3) transferable rules, generating reusable rules to accelerate the deployment of a KG to new systems.

Entity Embeddings Graph Attention +4

Animal Behavior Classification via Accelerometry Data and Recurrent Neural Networks

no code implementations24 Nov 2021 Liang Wang, Reza Arablouei, Flavio A. P. Alvarenga, Greg J. Bishop-Hurley

We study the classification of animal behavior using accelerometry data through various recurrent neural network (RNN) models.

Classification Time Series +2

Animal behavior classification via deep learning on embedded systems

no code implementations24 Nov 2021 Reza Arablouei, Liang Wang, Lachlan Currie, Jordan Yates, Flavio A. P. Alvarenga, Greg J. Bishop-Hurley

We develop an end-to-end deep-neural-network-based algorithm for classifying animal behavior using accelerometry data on the embedded system of an artificial intelligence of things (AIoT) device installed in a wearable collar tag.

Classification TAG +3

Contrast-reconstruction Representation Learning for Self-supervised Skeleton-based Action Recognition

no code implementations22 Nov 2021 Peng Wang, Jun Wen, Chenyang Si, Yuntao Qian, Liang Wang

Finally, in the Information Fuser, we explore varied strategies to combine the Sequence Reconstructor and Contrastive Motion Learner, and propose to capture postures and motions simultaneously via a knowledge-distillation based fusion strategy that transfers the motion learning from the Contrastive Motion Learner to the Sequence Reconstructor.

Action Recognition Contrastive Learning +4

FakeTransformer: Exposing Face Forgery From Spatial-Temporal Representation Modeled By Facial Pixel Variations

no code implementations15 Nov 2021 Yuyang Sun, Zhiyong Zhang, Changzhen Qiu, Liang Wang, Zekai Wang

With the rapid development of generation model, AI-based face manipulation technology, which called DeepFakes, has become more and more realistic.

DeepFake Detection Face Swapping

AI in Human-computer Gaming: Techniques, Challenges and Opportunities

no code implementations15 Nov 2021 Qiyue Yin, Jun Yang, Kaiqi Huang, Meijing Zhao, Wancheng Ni, Bin Liang, Yan Huang, Shu Wu, Liang Wang

Through this survey, we 1) compare the main difficulties among different kinds of games and the corresponding techniques utilized for achieving professional human level AIs; 2) summarize the mainstream frameworks and techniques that can be properly relied on for developing AIs for complex human-computer gaming; 3) raise the challenges or drawbacks of current techniques in the successful AIs; and 4) try to point out future trends in human-computer gaming AIs.

Decision Making

Latent Structure Mining with Contrastive Modality Fusion for Multimedia Recommendation

1 code implementation1 Nov 2021 Jinghao Zhang, Yanqiao Zhu, Qiang Liu, Mengqi Zhang, Shu Wu, Liang Wang

Although having access to multiple modalities might allow us to capture rich information, we argue that the simple coarse-grained fusion by linear combination or concatenation in previous work is insufficient to fully understand content information and item relationships. To this end, we propose a latent structure MIning with ContRastive mOdality fusion method (MICRO for brevity).

Collaborative Filtering Multimedia recommendation

Learning Diverse Policies in MOBA Games via Macro-Goals

no code implementations NeurIPS 2021 Yiming Gao, Bei Shi, Xueying Du, Liang Wang, Guangwei Chen, Zhenjie Lian, Fuhao Qiu, Guoan Han, Weixuan Wang, Deheng Ye, Qiang Fu, Wei Yang, Lanxiao Huang

Recently, many researchers have made successful progress in building the AI systems for MOBA-game-playing with deep reinforcement learning, such as on Dota 2 and Honor of Kings.

Dota 2

Relation-aware Heterogeneous Graph for User Profiling

1 code implementation14 Oct 2021 Qilong Yan, Yufeng Zhang, Qiang Liu, Shu Wu, Liang Wang

User profiling has long been an important problem that investigates user interests in many real applications.

Node Classification Relation

Deviance Matrix Factorization

no code implementations12 Oct 2021 Liang Wang, Luis Carvalho

We investigate a general matrix factorization for deviance-based data losses, extending the ubiquitous singular value decomposition beyond squared error loss.

Face Recognition

Generalizable Person Re-identification Without Demographics

no code implementations29 Sep 2021 Yifan Zhang, Feng Li, Zhang Zhang, Liang Wang, DaCheng Tao, Tieniu Tan

However, the convex condition of KL DRO may not hold for overparameterized neural networks, such that applying KL DRO often fails to generalize under distribution shifts in real scenarios.

Generalizable Person Re-identification

Embedding Compression with Hashing for Efficient Representation Learning in Graph

no code implementations29 Sep 2021 Chin-Chia Michael Yeh, Mengting Gu, Yan Zheng, Huiyuan Chen, Javid Ebrahimi, Zhongfang Zhuang, Junpeng Wang, Liang Wang, Wei zhang

When applying such type of networks on graph without node feature, one can extract simple graph-based node features (e. g., number of degrees) or learn the input node representation (i. e., embeddings) when training the network.

Representation Learning

Deep Reinforcement Learning-Based Long-Range Autonomous Valet Parking for Smart Cities

no code implementations23 Sep 2021 Muhammad Khalid, Liang Wang, Kezhi Wang, Cunhua Pan, Nauman Aslam, Yue Cao

In this paper, to reduce the congestion rate at the city center and increase the quality of experience (QoE) of each user, the framework of long-range autonomous valet parking (LAVP) is presented, where an Autonomous Vehicle (AV) is deployed in the city, which can pick up, drop off users at their required spots, and then drive to the car park out of city center autonomously.

reinforcement-learning Reinforcement Learning (RL)

Online Multi-horizon Transaction Metric Estimation with Multi-modal Learning in Payment Networks

no code implementations21 Sep 2021 Chin-Chia Michael Yeh, Zhongfang Zhuang, Junpeng Wang, Yan Zheng, Javid Ebrahimi, Ryan Mercer, Liang Wang, Wei zhang

In this work, we study the problem of multivariate time series prediction for estimating transaction metrics associated with entities in the payment transaction database.

Time Series Time Series Prediction

Aligning Cross-lingual Sentence Representations with Dual Momentum Contrast

no code implementations EMNLP 2021 Liang Wang, Wei Zhao, Jingming Liu

In this paper, we propose to align sentence representations from different languages into a unified embedding space, where semantic similarities (both cross-lingual and monolingual) can be computed with a simple dot product.

Semantic Textual Similarity Sentence +1

Deep Contrastive Multiview Network Embedding

no code implementations16 Aug 2021 Mengqi Zhang, Yanqiao Zhu, Qiang Liu, Shu Wu, Liang Wang

In our work, different views can be obtained based on the various relations among nodes.

Attribute Contrastive Learning +2

Foreground-Action Consistency Network for Weakly Supervised Temporal Action Localization

1 code implementation ICCV 2021 Linjiang Huang, Liang Wang, Hongsheng Li

In this paper, we present a framework named FAC-Net based on the I3D backbone, on which three branches are appended, named class-wise foreground classification branch, class-agnostic attention branch and multiple instance learning branch.

Multiple Instance Learning Video Understanding +2

Fully Hyperbolic Graph Convolution Network for Recommendation

no code implementations10 Aug 2021 Liping Wang, Fenyu Hu, Shu Wu, Liang Wang

These methods embed users and items in Euclidean space, and perform graph convolution on user-item interaction graphs.

Grain: Improving Data Efficiency of Graph Neural Networks via Diversified Influence Maximization

1 code implementation31 Jul 2021 Wentao Zhang, Zhi Yang, Yexin Wang, Yu Shen, Yang Li, Liang Wang, Bin Cui

Data selection methods, such as active learning and core-set selection, are useful tools for improving the data efficiency of deep learning models on large-scale datasets.

Active Learning Knowledge Graphs

ROD: Reception-aware Online Distillation for Sparse Graphs

1 code implementation25 Jul 2021 Wentao Zhang, Yuezihan Jiang, Yang Li, Zeang Sheng, Yu Shen, Xupeng Miao, Liang Wang, Zhi Yang, Bin Cui

Unfortunately, many real-world networks are sparse in terms of both edges and labels, leading to sub-optimal performance of GNNs.

Clustering Graph Learning +5

Criticality in Reservoir Computer of Coupled Phase Oscillators

no code implementations23 Jul 2021 Liang Wang, Huawei Fan, Jinghua Xiao, Yueheng Lan, Xingang Wang

Additionally, it is found that despite the synchronization degree of the original network, once properly trained, the reservoir network is always developed to the same critical state, exemplifying the "attractor" nature of this state in machine learning.

BIG-bench Machine Learning

Adaptive Dilated Convolution For Human Pose Estimation

no code implementations22 Jul 2021 Zhengxiong Luo, Zhicheng Wang, Yan Huang, Liang Wang, Tieniu Tan, Erjin Zhou

It can generate and fuse multi-scale features of the same spatial sizes by setting different dilation rates for different channels.

Pose Estimation

Anomaly Detection in Dynamic Graphs via Transformer

1 code implementation18 Jun 2021 Yixin Liu, Shirui Pan, Yu Guang Wang, Fei Xiong, Liang Wang, Qingfeng Chen, Vincent CS Lee

Detecting anomalies for dynamic graphs has drawn increasing attention due to their wide applications in social networks, e-commerce, and cybersecurity.

Anomaly Detection

CMF: Cascaded Multi-model Fusion for Referring Image Segmentation

1 code implementation16 Jun 2021 Jianhua Yang, Yan Huang, Zhanyu Ma, Liang Wang

To solve this problem, we propose a simple yet effective Cascaded Multi-modal Fusion (CMF) module, which stacks multiple atrous convolutional layers in parallel and further introduces a cascaded branch to fuse visual and linguistic features.

Image Segmentation Segmentation +1

Representation and Correlation Enhanced Encoder-Decoder Framework for Scene Text Recognition

1 code implementation13 Jun 2021 Mengmeng Cui, Wei Wang, Jinjin Zhang, Liang Wang

However, for the current state-of-the-art(SOTA) methods, there is room for improvement in terms of the efficient usage of local visual and global context information of the input text image, as well as the robust correlation between the scene processing module(encoder) and the text processing module(decoder).

Scene Text Recognition

Normalization of Language Embeddings for Cross-Lingual Alignment

1 code implementation NeurIPS 2021 Prince Osei Aboagye, Jeff Phillips, Yan Zheng, Chin-Chia Michael Yeh, Junpeng Wang, Wei zhang, Liang Wang, Hao Yang

Learning a good transfer function to map the word vectors from two languages into a shared cross-lingual word vector space plays a crucial role in cross-lingual NLP.

Translation

End-to-end Alternating Optimization for Blind Super Resolution

1 code implementation14 May 2021 Zhengxiong Luo, Yan Huang, Shang Li, Liang Wang, Tieniu Tan

More importantly, \textit{Restorer} is trained with the kernel estimated by \textit{Estimator}, instead of the ground-truth kernel, thus \textit{Restorer} could be more tolerant to the estimation error of \textit{Estimator}.

Blind Super-Resolution Super-Resolution

FDAN: Flow-guided Deformable Alignment Network for Video Super-Resolution

no code implementations12 May 2021 Jiayi Lin, Yan Huang, Liang Wang

Recently, deformable alignment has drawn extensive attention in VSR community for its remarkable performance, which can adaptively align neighboring frames with the reference one.

Optical Flow Estimation Video Super-Resolution

Learning Hamiltonian dynamics by reservoir computer

no code implementations24 Apr 2021 Han Zhang, Huawei Fan, Liang Wang, Xingang Wang

Reconstructing the KAM dynamics diagram of Hamiltonian system from the time series of a limited number of parameters is an outstanding question in nonlinear science, especially when the Hamiltonian governing the system dynamics are unknown.

Time Series Time Series Analysis

Temporal Modulation Network for Controllable Space-Time Video Super-Resolution

1 code implementation CVPR 2021 Gang Xu, Jun Xu, Zhen Li, Liang Wang, Xing Sun, Ming-Ming Cheng

To well exploit the temporal information, we propose a Locally-temporal Feature Comparison (LFC) module, along with the Bi-directional Deformable ConvLSTM, to extract short-term and long-term motion cues in videos.

Space-time Video Super-resolution Video Super-Resolution

Mining Latent Structures for Multimedia Recommendation

1 code implementation19 Apr 2021 Jinghao Zhang, Yanqiao Zhu, Qiang Liu, Shu Wu, Shuhui Wang, Liang Wang

To be specific, in the proposed LATTICE model, we devise a novel modality-aware structure learning layer, which learns item-item structures for each modality and aggregates multiple modalities to obtain latent item graphs.

Collaborative Filtering Multimedia recommendation +1

Dynamic Graph Neural Networks for Sequential Recommendation

1 code implementation15 Apr 2021 Mengqi Zhang, Shu Wu, Xueli Yu, Qiang Liu, Liang Wang

We propose a new method named Dynamic Graph Neural Network for Sequential Recommendation (DGSR), which connects different user sequences through a dynamic graph structure, exploring the interactive behavior of users and items with time and order information.

Graph Attention Link Prediction +1

DyGCN: Dynamic Graph Embedding with Graph Convolutional Network

no code implementations7 Apr 2021 Zeyu Cui, Zekun Li, Shu Wu, XiaoYu Zhang, Qiang Liu, Liang Wang, Mengmeng Ai

We naturally generalizes the embedding propagation scheme of GCN to dynamic setting in an efficient manner, which is to propagate the change along the graph to update node embeddings.

Dynamic graph embedding

Incremental Generative Occlusion Adversarial Suppression Network for Person ReID

1 code implementation IEEE Transactions on Image Processing 2021 Cairong Zhao, Xinbi Lv, Shuguang Dou, Shanshan Zhang, Jun Wu, Liang Wang

The adversarial suppression branch, embedded with two occlusion suppression module, minimizes the generated occlusion’s response and strengthens attentive feature representation on human non-occluded body regions.

Data Augmentation Person Re-Identification

Graph Classification by Mixture of Diverse Experts

no code implementations29 Mar 2021 Fenyu Hu, Liping Wang, Shu Wu, Liang Wang, Tieniu Tan

Graph classification is a challenging research problem in many applications across a broad range of domains.

General Classification Graph Classification

GraphDIVE: Graph Classification by Mixture of Diverse Experts

1 code implementation journal 2021 Fenyu Hu, Liping Wang, Qiang Liu, Shu Wu, Liang Wang, Tieniu Tan

Graph classification is a challenging research problem in many applications across a broad range of domains.

Graph Classification

Graph-based Hierarchical Relevance Matching Signals for Ad-hoc Retrieval

1 code implementation22 Feb 2021 Xueli Yu, Weizhi Xu, Zeyu Cui, Shu Wu, Liang Wang

In addition, due to the complexity and scale of the document collections, it is considerable to explore the different grain-sized hierarchical matching signals at a more general level.

Retrieval

A Graph-based Relevance Matching Model for Ad-hoc Retrieval

1 code implementation28 Jan 2021 Yufeng Zhang, Jinghao Zhang, Zeyu Cui, Shu Wu, Liang Wang

To retrieve more relevant, appropriate and useful documents given a query, finding clues about that query through the text is crucial.

Retrieval

Focal and Efficient IOU Loss for Accurate Bounding Box Regression

no code implementations20 Jan 2021 Yi-Fan Zhang, Weiqiang Ren, Zhang Zhang, Zhen Jia, Liang Wang, Tieniu Tan

(ii) Most of the loss functions ignore the imbalance problem in BBR that the large number of anchor boxes which have small overlaps with the target boxes contribute most to the optimization of BBR.

object-detection Object Detection +2

Dynamic Graph Collaborative Filtering

1 code implementation8 Jan 2021 Xiaohan Li, Mengqi Zhang, Shu Wu, Zheng Liu, Liang Wang, Philip S. Yu

Here we propose Dynamic Graph Collaborative Filtering (DGCF), a novel framework leveraging dynamic graphs to capture collaborative and sequential relations of both items and users at the same time.

Collaborative Filtering Recommendation Systems

Global2Local: Efficient Structure Search for Video Action Segmentation

2 code implementations CVPR 2021 Shang-Hua Gao, Qi Han, Zhong-Yu Li, Pai Peng, Liang Wang, Ming-Ming Cheng

Our search scheme exploits both global search to find the coarse combinations and local search to get the refined receptive field combination patterns further.

Action Segmentation Segmentation

Efficient Human Pose Estimation by Learning Deeply Aggregated Representations

no code implementations13 Dec 2020 Zhengxiong Luo, Zhicheng Wang, Yuanhao Cai, GuanAn Wang, Yan Huang, Liang Wang, Erjin Zhou, Tieniu Tan, Jian Sun

Instead, we focus on exploiting multi-scale information from layers with different receptive-field sizes and then making full of use this information by improving the fusion method.

Pose Estimation

Receptivity and stability of hypersonic leading-edge sweep flows around a blunt body

no code implementations3 Dec 2020 Youcheng Xi, Jie Ren, Liang Wang, Song Fu

We establish an adjoint-based bi-orthogonal eigenfunction system to address the receptivity problem of such flows to any external forces and boundary perturbations.

Fluid Dynamics

Learning distributed sentence vectors with bi-directional 3D convolutions

no code implementations COLING 2020 Bin Liu, Liang Wang, Guosheng Yin

Similar to the Bi-LSTM, these n-gram detectors learn both forward and backward distributional semantic knowledge from the sentence tensor.

Sentence Sentence Embedding +1

Towards Playing Full MOBA Games with Deep Reinforcement Learning

no code implementations NeurIPS 2020 Deheng Ye, Guibin Chen, Wen Zhang, Sheng Chen, Bo Yuan, Bo Liu, Jia Chen, Zhao Liu, Fuhao Qiu, Hongsheng Yu, Yinyuting Yin, Bei Shi, Liang Wang, Tengfei Shi, Qiang Fu, Wei Yang, Lanxiao Huang, Wei Liu

However, existing work falls short in handling the raw game complexity caused by the explosion of agent combinations, i. e., lineups, when expanding the hero pool in case that OpenAI's Dota AI limits the play to a pool of only 17 heroes.

Dota 2 reinforcement-learning +1

Supervised Learning Achieves Human-Level Performance in MOBA Games: A Case Study of Honor of Kings

no code implementations25 Nov 2020 Deheng Ye, Guibin Chen, Peilin Zhao, Fuhao Qiu, Bo Yuan, Wen Zhang, Sheng Chen, Mingfei Sun, Xiaoqian Li, Siqin Li, Jing Liang, Zhenjie Lian, Bei Shi, Liang Wang, Tengfei Shi, Qiang Fu, Wei Yang, Lanxiao Huang

Unlike prior attempts, we integrate the macro-strategy and the micromanagement of MOBA-game-playing into neural networks in a supervised and end-to-end manner.

Cannot find the paper you are looking for? You can Submit a new open access paper.