no code implementations • AACL (iwdp) 2020 • Yue Hu, Jiahao Qin, Zemeiqi Chen, Jingshi Zhou, Xiaojun Zhang
This paper focuses on the performance of encoder decoder attention mechanism in word sense disambiguation task with different text length, trying to find out the influence of context marker on attention mechanism in word sense disambiguation task.
no code implementations • CCL 2020 • Yue Hu, Guangyou Zhou
知识库问答依靠知识库推断答案需大量带标注信息的问答对, 但构建大规模且精准的数据集不仅代价昂贵, 还受领域等因素限制。为缓解数据标注问题, 面向知识库的问题生成任务引起了研究者关注, 该任务是利用知识库三元组自动生成问题。现有方法仅由一个三元组生成的问题简短且缺乏多样性。为生成信息量丰富且多样化的问题, 本文采用Graph Transformer和BERT两个编码层来加强三元组多粒度语义表征以获取背景信息。在SimpleQuestions上的实验结果证明了该方法有效性。
no code implementations • WMT (EMNLP) 2020 • Xiangpeng Wei, Ping Guo, Yunpeng Li, Xingsheng Zhang, Luxi Xing, Yue Hu
In this paper we introduce the systems IIE submitted for the WMT20 shared task on German-French news translation.
1 code implementation • 10 May 2024 • Ting Liu, Xuyang Liu, Siteng Huang, Honggang Chen, Quanjun Yin, Long Qin, Donglin Wang, Yue Hu
Specifically, we propose \textbf{DARA}, a novel PETL method comprising \underline{\textbf{D}}omain-aware \underline{\textbf{A}}dapters (DA Adapters) and \underline{\textbf{R}}elation-aware \underline{\textbf{A}}dapters (RA Adapters) for VG.
1 code implementation • 8 May 2024 • Yue Hu, Juntong Peng, Sifei Liu, Junhao Ge, Si Liu, Siheng Chen
It inherently results in a fundamental trade-off between perception ability and communication cost.
1 code implementation • 23 Apr 2024 • Yue Hu, Bin Huang
The protein language model can help us extract structural information from sequences.
no code implementations • 15 Apr 2024 • Genjia Liu, Yue Hu, Chenxin Xu, Weibo Mao, Junhao Ge, Zhengxiang Huang, Yifan Lu, Yinda Xu, Junkai Xia, Yafei Wang, Siheng Chen
This effort necessitates two key foundations: a platform capable of generating data to facilitate the training and testing of V2X-AD, and a comprehensive system that integrates full driving-related functionalities with mechanisms for information sharing.
no code implementations • 18 Mar 2024 • Guohang Zhuang, Yue Hu, Tianxing Yan, JiaZhan Gao
Currently, most food recognition relies on deep learning for category classification.
1 code implementation • 25 Jan 2024 • Yifan Lu, Yue Hu, Yiqi Zhong, Dequan Wang, Yanfeng Wang, Siheng Chen
In this paper, we introduce a new open heterogeneous problem: how to accommodate continually emerging new heterogeneous agent types into collaborative perception, while ensuring high perception performance and low integration cost?
no code implementations • 23 Jan 2024 • Yue Hu, Xianghe Pang, Xiaoqi Qin, Yonina C. Eldar, Siheng Chen, Ping Zhang, Wenjun Zhang
Following this strategy, we first formulate a mathematical optimization framework for the perception-communication trade-off and then propose PragComm, a multi-agent collaborative perception system with two key components: i) single-agent detection and tracking and ii) pragmatic collaboration.
no code implementations • 13 Dec 2023 • Jinta Weng, Jiarui Zhang, Yue Hu, Daidong Fa, Xiaofeng Xuand, Heyan Huang
In interaction with large language models, embedding more task-related information into prompts will make it easier to stimulate knowledge embedded in large language models.
no code implementations • 29 Nov 2023 • Ting Liu, Yue Hu, Wansen Wu, Youkai Wang, Kai Xu, Quanjun Yin
Then we introduce soft visual prompts in the input space of the visual encoder in a pretrained model.
1 code implementation • 10 Nov 2023 • Yuanmin Tang, Jing Yu, Keke Gai, Xiangyan Qu, Yue Hu, Gang Xiong, Qi Wu
Our extensive experiments on various datasets indicate that the proposed watermarking approach is effective and safe for verifying the copyright of VLPs for multi-modal EaaS and robust against model extraction attacks.
no code implementations • 29 Oct 2023 • Yongxiu Xu, Heyan Huang, Yue Hu
Named Entity Recognition (NER) remains challenging due to the complex entities, like nested, overlapping, and discontinuous entities.
no code implementations • 9 Oct 2023 • Peng Li, Yuping Ji, Yue Hu
To fill this gap, we propose a novel MRF reconstruction framework based on manifold structured data priors.
1 code implementation • 28 Sep 2023 • Yuanmin Tang, Jing Yu, Keke Gai, Jiamin Zhuang, Gang Xiong, Yue Hu, Qi Wu
Different from Composed Image Retrieval task that requires expensive labels for training task-specific models, Zero-Shot Composed Image Retrieval (ZS-CIR) involves diverse tasks with a broad range of visual content manipulation intent that could be related to domain, scene, object, and attribute.
1 code implementation • 28 Sep 2023 • Yuanmin Tang, Jing Yu, Keke Gai, Yujing Wang, Yue Hu, Gang Xiong, Qi Wu
Conventional research mainly studies from the view of modeling the implicit correlations between images and texts for query-ads matching, ignoring the alignment of detailed product information and resulting in suboptimal search performance. In this work, we propose a simple alignment network for explicitly mapping fine-grained visual parts in ads images to the corresponding text, which leverages the co-occurrence structure consistency between vision and language spaces without requiring expensive labeled training data.
Ranked #1 on Image-text matching on CommercialAdsDataset
no code implementations • 15 Sep 2023 • Yue Hu, Gourav Datta, Kira Beerel, Peter Beerel
This implies that ML pipelines might not need explicit correction for RS for many object detection applications, but mitigating RS effects in ISP-less ML pipelines that target fine-grained location of the objects may need additional research.
no code implementations • 7 Sep 2023 • Ting Liu, Yue Hu, Wansen Wu, Youkai Wang, Kai Xu, Quanjun Yin
In the indoor-aware stage, we apply an efficient tuning paradigm to learn deep visual prompts from an indoor dataset, in order to augment pretrained models with inductive biases towards indoor environments.
1 code implementation • 27 Aug 2023 • Jiamin Zhuang, Jing Yu, Yang Ding, Xiangyan Qu, Yue Hu
Image-text retrieval requires the system to bridge the heterogenous gap between vision and language for accurate retrieval while keeping the network lightweight-enough for efficient retrieval.
1 code implementation • 6 Aug 2023 • Yue Hu, Xinan Ye, Yifei Liu, Souvik Kundu, Gourav Datta, Srikar Mutnuri, Namo Asavisanu, Nora Ayanian, Konstantinos Psounis, Peter Beerel
This paper presents "FireFly", a synthetic dataset for ember detection created using Unreal Engine 4 (UE4), designed to overcome the current lack of ember-specific training resources.
1 code implementation • 19 Jul 2023 • Yinghao Zhang, Xiaodi Li, Weihang Li, Yue Hu
In particular, we put forward a novel deep unrolling shrinkage network (DUS-Net) by unrolling the alternating direction method of multipliers (ADMM) for optimizing the transformed $l_1$ norm dynamic MR reconstruction model.
1 code implementation • 23 Apr 2023 • Yue Hu, Yuhang Zhang, Yanbing Wang, Daniel Work
In this work, we consider the problem of detecting a variety of socially abnormal driving behaviors, i. e., behaviors that do not conform to the behavior of other nearby drivers.
1 code implementation • CVPR 2023 • Chi Xie, Fangao Zeng, Yue Hu, Shuang Liang, Yichen Wei
Unlike most previous HOI methods that focus on learning better human-object features, we propose a novel and complementary approach called category query learning.
Ranked #8 on Human-Object Interaction Detection on HICO-DET
1 code implementation • CVPR 2023 • Yue Hu, Yifan Lu, Runsheng Xu, Weidi Xie, Siheng Chen, Yanfeng Wang
Camera-only 3D detection provides an economical solution with a simple configuration for localizing objects in 3D space compared to LiDAR-based detection systems.
no code implementations • 24 Feb 2023 • Guanghao Li, Li Shen, Yan Sun, Yue Hu, Han Hu, DaCheng Tao
Federated learning (FL) enables multiple clients to train a machine learning model collaboratively without exchanging their local data.
no code implementations • 8 Nov 2022 • Jinta Weng, Yifan Deng, d Donghao Li, Hao You, Yue Hu, Heyan Huang
The prompt has become an effective linguistic tool for utilizing pre-trained language models.
no code implementations • 1 Nov 2022 • Wei Peng, Ziyuan Qin, Yue Hu, Yuqiang Xie, Yunpeng Li
The core module in FADO consists of a dual-level feedback strategy selector and a double control reader.
no code implementations • 29 Oct 2022 • Jinta Weng, Yue Hu, Jing Qiu, Heyan Huan
The effectiveness of prompt learning has been demonstrated in different pre-trained language models.
no code implementations • 18 Oct 2022 • Yangheng Zhao, Jun Wang, Xiaolong Li, Yue Hu, Ce Zhang, Yanfeng Wang, Siheng Chen
Instead of learning a single prototype for each class, in this paper, we propose to use an adaptive number of prototypes to dynamically describe the different point patterns within a semantic class.
Ranked #17 on 3D Semantic Segmentation on SemanticKITTI
no code implementations • COLING 2022 • Yuqiang Xie, Yue Hu, Yunpeng Li, Guanqun Bi, Luxi Xing, Wei Peng
Inspired by psychology theories, we introduce global psychological state chains, which include the needs and emotions of the protagonists, to help a story generation system create more controllable and well-planned stories.
2 code implementations • 26 Sep 2022 • Yue Hu, Shaoheng Fang, Zixing Lei, Yiqi Zhong, Siheng Chen
Where2comm has two distinct advantages: i) it considers pragmatic compression and uses less communication to achieve higher perception performance by focusing on perceptually critical areas; and ii) it can handle varying communication bandwidth by dynamically adjusting spatial areas involved in communication.
Ranked #1 on Monocular 3D Object Detection on CoPerception-UAVs
no code implementations • 21 Sep 2022 • Yilin Liu, Liqiang Lin, Yue Hu, Ke Xie, Chi-Wing Fu, Hao Zhang, Hui Huang
To reconstruct a new urban scene, we first build the 3D scene proxy, then rely on the predicted reconstruction quality and uncertainty measures by our network, based off of the proxy geometry, to guide the drone path planning.
1 code implementation • COLING 2022 • Yuqiang Xie, Yue Hu, Wei Peng, Guanqun Bi, Luxi Xing
Motivations, emotions, and actions are inter-related essential factors in human activities.
1 code implementation • 8 Sep 2022 • Yinghao Zhang, Yue Hu
By generalizing the FFT into an arbitrary unitary transformation of the transformed t-SVD and proposing the transformed tensor nuclear norm (TTNN), we introduce a flexible model based on TTNN with the ability to exploit the tensor low-rank prior of a transformed domain in a larger transformation space and elaborately design an iterative optimization algorithm based on the alternating direction method of multipliers (ADMM), which is further unrolled into a model-based deep unrolling reconstruction network to learn the transformed tensor low-rank prior (T$^2$LR-Net).
no code implementations • 27 Aug 2022 • Ziyang Wang, Huoyu Liu, Wei Wei, Yue Hu, Xian-Ling Mao, Shaojian He, Rui Fang, Dangyang Chen
Different from the previous contrastive learning-based methods for SR, MCLSR learns the representations of users and items through a cross-view contrastive learning paradigm from four specific views at two different levels (i. e., interest- and feature-level).
no code implementations • 8 Aug 2022 • Yue Hu, Shaoheng Fang, Weidi Xie, Siheng Chen
To fill the gap, this work proposes a dual-view detection system named DVDET to achieve aerial monocular object detection in both the 2D image space and the 3D physical space.
1 code implementation • 8 Aug 2022 • Yue Hu, Siheng Chen, Xu Chen, Ya zhang, Xiao Gu
Visual relationship detection aims to detect the interactions between objects in an image; however, this task suffers from combinatorial explosion due to the variety of objects and interactions.
1 code implementation • 18 Jul 2022 • Zixing Lei, Shunli Ren, Yue Hu, Wenjun Zhang, Siheng Chen
Collaborative perception has recently shown great potential to improve perception capabilities over single-agent perception.
1 code implementation • 24 Jun 2022 • Wei Peng, Yue Hu, Luxi Xing, Yuqiang Xie, Yajing Sun
Specifically, CFO-Net designs a feedback memory module, including strategy pool and feedback pool, to obtain emotion-aware strategy representation.
no code implementations • 21 Jun 2022 • Guanghao Li, Yue Hu, Miao Zhang, Ji Liu, Quanjun Yin, Yong Peng, Dejing Dou
As the efficiency of training in the ring topology prefers devices with homogeneous resources, the classification based on the computing capacity mitigates the impact of straggler effects.
no code implementations • 2 Jun 2022 • Yinghao Zhang, Peng Li, Yue Hu
While low-rank matrix prior has been exploited in dynamic MR image reconstruction and has obtained satisfying performance, tensor low-rank models have recently emerged as powerful alternative representations for three-dimensional dynamic MR datasets.
1 code implementation • 2 Jun 2022 • Yinghao Zhang, Yue Hu
Recently, a new tensor nuclear norm based on t-SVD has been proposed and applied to tensor completion.
1 code implementation • 7 May 2022 • Wei Peng, Yue Hu, Yuqiang Xie, Luxi Xing, Yajing Sun
In this paper, we propose a novel cognitive framework of individual interaction.
1 code implementation • 27 Apr 2022 • Wei Peng, Yue Hu, Luxi Xing, Yuqiang Xie, Yajing Sun, Yunpeng Li
Emotional support conversation aims at reducing the emotional distress of the help-seeker, which is a new and challenging task.
no code implementations • 19 Apr 2022 • Wencong Xu, Yandong Li, Bingshu Chen, Yue Hu, Jianxu Li, Zijing Zeng
The experimental results show that the PD direction-finding error is 3. 39{\deg}, which can meet the need for Partial discharge DOA estimation using inspection robots in substations.
2 code implementations • ACL 2022 • Xiangpeng Wei, Heng Yu, Yue Hu, Rongxiang Weng, Weihua Luo, Jun Xie, Rong Jin
Although data augmentation is widely used to enrich the training data, conventional methods with discrete manipulations fail to generate diverse and faithful training samples.
1 code implementation • CVPR 2022 • Yang Ding, Jing Yu, Bang Liu, Yue Hu, Mingxin Cui, Qi Wu
Knowledge-based visual question answering requires the ability of associating external knowledge for open-ended cross-modal scene understanding.
1 code implementation • 18 Feb 2022 • Yuqiang Xie, Yue Hu, Luxi Xing, Yunpeng Li, Wei Peng, Ping Guo
To address these two issues, we propose a novel Contrastive Learning framework for Story Ending Generation (CLSEG), which has two steps: multi-aspect sampling and story-specific contrastive learning.
no code implementations • 14 Feb 2022 • Wei Peng, Yue Hu, Luxi Xing, Yuqiang Xie, Xingsheng Zhang, Yajing Sun
Intention, emotion and action are important elements in human activities.
1 code implementation • 1 Sep 2021 • Yue Hu, Ao Qu, Yanbing Wang, Dan Work
Measuring the built and natural environment at a fine-grained scale is now possible with low-cost urban environmental sensor networks.
no code implementations • 16 Jul 2021 • Yajing Sun, Yue Hu, Luxi Xing, Yuqiang Xie, Xiangpeng Wei
End-to-End intelligent neural dialogue systems suffer from the problems of generating inconsistent and repetitive responses.
2 code implementations • 9 Jul 2021 • Liqiang Lin, Yilin Liu, Yue Hu, Xingguang Yan, Ke Xie, Hui Huang
We present UrbanScene3D, a large-scale data platform for research of urban scene perception and reconstruction.
no code implementations • 4 Jul 2021 • Luxi Xing, Yue Hu, Jing Yu, Yuqiang Xie, Wei Peng
It is prevalent to utilize external knowledge to help machine answer questions that need background commonsense, which faces a problem that unlimited knowledge will transmit noisy and misleading information.
1 code implementation • CVPR 2021 • Cheng Zou, Bohan Wang, Yue Hu, Junqi Liu, Qian Wu, Yu Zhao, Boxun Li, Chenguang Zhang, Chi Zhang, Yichen Wei, Jian Sun
We propose HOI Transformer to tackle human object interaction (HOI) detection in an end-to-end manner.
Ranked #30 on Human-Object Interaction Detection on HICO-DET (using extra training data)
no code implementations • 8 Mar 2021 • Wei Peng, Yue Hu, Jing Yu, Luxi Xing, Yuqiang Xie, Zihao Zhu, Yajing Sun
Most of the existing systems design a simple classifier to determine answerability implicitly without explicitly modeling mutual interaction and relation between the question and passage, leading to the poor performance for determining the unanswerable questions.
no code implementations • SEMEVAL 2021 • Yuqiang Xie, Luxi Xing, Wei Peng, Yue Hu
This paper introduces our systems for all three subtasks of SemEval-2021 Task 4: Reading Comprehension of Abstract Meaning.
no code implementations • 11 Feb 2021 • Yue Hu, A. Lazarian, Snezana Stanimirovic
We suggest that the Serpens G3-G6 south clump is undergoing a gravitational collapse.
Astrophysics of Galaxies
no code implementations • 10 Feb 2021 • Siyao Xu, Yue Hu
The interstellar turbulence is magnetized and thus anisotropic.
Astrophysics of Galaxies
1 code implementation • 25 Dec 2020 • Yue Hu, Ao Qu, Dan Work
Event detection has been an important task in transportation, whose task is to detect points in time when large events disrupts a large portion of the urban traffic network.
no code implementations • 11 Dec 2020 • Yue Hu, Siyao Xu, A. Lazarian
We demonstrate that the anisotropic structure functions of turbulent velocities can be used to estimate both the orientation and strength of magnetic fields.
Astrophysics of Galaxies
no code implementations • COLING 2020 • Wei Peng, Yue Hu, Luxi Xing, Yuqiang Xie, Jing Yu, Yajing Sun, Xiangpeng Wei
We propose a novel Bi-directional Cognitive Knowledge Framework (BCKF) for reading comprehension from the perspective of complementary learning systems theory.
3 code implementations • 11 Nov 2020 • Shuai Zhang, Huoyu Liu, Aston Zhang, Yue Hu, Ce Zhang, Yumeng Li, Tanchao Zhu, Shaojian He, Wenwu Ou
Furthermore, we present two variants of hypercuboids to enhance the capability in capturing the diversities of user interests.
no code implementations • 20 Oct 2020 • Wei Peng, Yue Hu, Luxi Xing, Yuqiang Xie, Jing Yu, Yajing Sun, Xiangpeng Wei
We propose a novel Bi-directional Cognitive Knowledge Framework (BCKF) for reading comprehension from the perspective of complementary learning systems theory.
no code implementations • EMNLP 2020 • Xiangpeng Wei, Heng Yu, Yue Hu, Rongxiang Weng, Luxi Xing, Weihua Luo
As a sequence-to-sequence generation task, neural machine translation (NMT) naturally contains intrinsic uncertainty, where a single sentence in one language has multiple valid counterparts in the other.
1 code implementation • 16 Sep 2020 • Jing Yu, Yuan Chai, Yujing Wang, Yue Hu, Qi Wu
We first build a cognitive structure CogTree to organize the relationships based on the prediction of a biased SGG model.
Ranked #2 on Scene Graph Generation on Visual Genome (mean Recall @20 metric)
no code implementations • 31 Aug 2020 • Jing Yu, Zihao Zhu, Yujing Wang, Weifeng Zhang, Yue Hu, Jianlong Tan
Finally, we perform graph neural networks to infer the global-optimal answer by jointly considering all the concepts.
no code implementations • 2 Aug 2020 • Yue Hu, A. Lazarian, Shmuel Bialy
In this work, we consider the effect of turbulence on the HI and H2 transition and explore the possibility of tracing the magnetic field direction in photodissociation regions using the Gradient Technique.
Astrophysics of Galaxies
no code implementations • ICLR 2021 • Xiangpeng Wei, Rongxiang Weng, Yue Hu, Luxi Xing, Heng Yu, Weihua Luo
Recent studies have demonstrated the overwhelming advantage of cross-lingual pre-trained models (PTMs), such as multilingual BERT and XLM, on cross-lingual NLP tasks.
Contrastive Learning Cross-Lingual Natural Language Inference +4
4 code implementations • 7 Jul 2020 • Xiaoze Jiang, Jing Yu, Yajing Sun, Zengchang Qin, Zihao Zhu, Yue Hu, Qi Wu
The ability of generating detailed and non-repetitive responses is crucial for the agent to achieve human-like conversation.
no code implementations • SEMEVAL 2020 • Luxi Xing, Yuqiang Xie, Yue Hu, Wei Peng
This paper introduces our systems for the first two subtasks of SemEval Task4: Commonsense Validation and Explanation.
no code implementations • 16 Jun 2020 • Zihao Zhu, Jing Yu, Yujing Wang, Yajing Sun, Yue Hu, Qi Wu
In this paper, we depict an image by a multi-modal heterogeneous graph, which contains multiple layers of information corresponding to the visual, semantic and factual features.
1 code implementation • ACL 2020 • Xiangpeng Wei, Heng Yu, Yue Hu, Yue Zhang, Rongxiang Weng, Weihua Luo
Recent evidence reveals that Neural Machine Translation (NMT) models with deeper neural networks can be more effective but are difficult to train.
1 code implementation • CVPR 2020 • Yue Hu, Siheng Chen, Ya zhang, Xiao Gu
Motion prediction is essential and challenging for autonomous vehicles and social robots.
1 code implementation • 17 Nov 2019 • Xiaoze Jiang, Jing Yu, Zengchang Qin, Yingying Zhuang, Xingxing Zhang, Yue Hu, Qi Wu
More importantly, we can tell which modality (visual or semantic) has more contribution in answering the current question by visualizing the gate values.
Ranked #6 on Visual Dialog on VisDial v0.9 val
no code implementations • CONLL 2019 • Xiangpeng Wei, Yue Hu, Luxi Xing, Li Gao
In this paper, we alleviate the local optimality of back-translation by learning a policy (takes the form of an encoder-decoder and is defined by its parameters) with future rewarding under the reinforcement learning framework, which aims to optimize the global word predictions for unsupervised neural machine translation.
no code implementations • 27 Aug 2019 • Yue Hu, Dan Work
In this article, we develop a method to detect extreme events in large traffic datasets, and to impute missing data during regular conditions.
no code implementations • 27 May 2019 • Zhen Li, Shiyun Xiong, Charles Sievers, Yue Hu, Zheyong Fan, Ning Wei, Hua Bao, Shunda Chen, Davide Donadio, Tapio Ala-Nissila
Conventionally, the thermal conductivity of a finite system is calculated as the ratio between the heat flux and the temperature gradient extracted from the linear part of the temperature profile away from the local thermostats.
Mesoscale and Nanoscale Physics Statistical Mechanics Computational Physics
1 code implementation • 22 Apr 2019 • Yang Gao, Hong Yang, Peng Zhang, Chuan Zhou, Yue Hu
On node classification tasks, GraphNAS can design a novel network architecture that rivals the best human-invented architecture in terms of test set accuracy.
Ranked #13 on Node Classification on PPI
no code implementations • 23 Dec 2018 • Zhuoqian Yang, Zengchang Qin, Jing Yu, Yue Hu
Upon the constructed graph, we propose a Scene Graph Convolutional Network (SceneGCN) to jointly reason the object properties and relational semantics for the correct answer.
no code implementations • 5 Nov 2018 • Junjie Zeng, Long Qin, Yue Hu, Cong Hu, Quanjun Yin
The first advantage of the proposed method is that SSG can solve the limitations of sparse reward and local minima trap for RL agents; thus, LSPI can be used to generate paths in complex environments.
1 code implementation • 31 Oct 2018 • Jing Yu, Chenghao Yang, Zengchang Qin, Zhuoqian Yang, Yue Hu, Yanbing Liu
A joint neural model is proposed to learn feature representation individually in each modality.
Multimedia
1 code implementation • 6 Sep 2018 • Giulio Romualdi, Stefano Dafarra, Yue Hu, Daniele Pucci
More precisely, we present and compare several DCM based implementations of a three layer control architecture.
Robotics
no code implementations • 8 Jul 2015 • Yue Hu, Xiaojun Wan
Third, we apply the extraction method and the classification model to a paper dataset in the computer science field and conduct a further analysis of the future works.