Search Results for author:
Found 40 papers, 12 papers with code
Occlusion-Aware Siamese Network for Human Pose Estimation
To overcome the defects caused by the erasing operation, we perform feature reconstruction to recover the information destroyed by occlusion and details lost in cleaning procedure.
Decoupling GCN with DropGraph Module for Skeleton-Based Action Recognition
Nevertheless, how to efficiently model the spatial-temporal skeleton graph without introducing extra computation burden is a challenging problem for industrial deployment.
Towards Unified Multi-Modal Personalization: Large Vision-Language Models for Generative Recommendation and Beyond
Developing a universal model that can effectively harness heterogeneous resources and respond to a wide range of personalized needs has been a longstanding community aspiration.
Language Models As Semantic Indexers
Semantic identifier (ID) is an important concept in information retrieval that aims to preserve the semantics of objects such as documents and items inside their IDs.
Amazon-M2: A Multilingual Multi-locale Shopping Session Dataset for Recommendation and Text Generation
To test the potential of the dataset, we introduce three tasks in this work: (1) next-product recommendation, (2) next-product recommendation with domain shifts, and (3) next-product title generation.
Multilingual Knowledge Graph Completion with Self-Supervised Adaptive Graph Alignment
In this paper, we explore multilingual KG completion, which leverages limited seed alignment as a bridge, to embrace the collective knowledge from multiple languages.
Ranked #3 on
Knowledge Graph Completion
on DPB-5L (French)
QUEACO: Borrowing Treasures from Weakly-labeled Behavior Data for Query Attribute Value Extraction
We study the problem of query attribute value extraction, which aims to identify named entities from user queries as diverse surface form attribute values and afterward transform them into formally canonical forms.
OPT: Omni-Perception Pre-Trainer for Cross-Modal Understanding and Generation
In this paper, we propose an Omni-perception Pre-Trainer (OPT) for cross-modal understanding and generation, by jointly modeling visual, text and audio resources.
Ranked #1 on
Image Retrieval
on Localized Narratives
Improving Multiple Object Tracking With Single Object Tracking
Despite considerable similarities between multiple object tracking (MOT) and single object tracking (SOT) tasks, modern MOT methods have not benefited from the development of SOT ones to achieve satisfactory performance.
Graph-based Multilingual Product Retrieval in E-commerce Search
Nowadays, with many e-commerce platforms conducting global business, e-commerce search systems are required to handle product retrieval under multilingual scenarios.
AdaSGN: Adapting Joint Number and Model Size for Efficient Skeleton-Based Action Recognition
Existing methods for skeleton-based action recognition mainly focus on improving the recognition accuracy, whereas the efficiency of the model is rarely considered.
Fast Sequence Generation with Multi-Agent Reinforcement Learning
These models are autoregressive in that they generate each word by conditioning on previously generated words, which leads to heavy latency during inference.
High-Performance Discriminative Tracking With Transformers
End-to-end discriminative trackers improve the state of the art significantly, yet the improvement in robustness and efficiency is restricted by the conventional discriminative model, i. e., least-squares based regression.
HAIR: Hierarchical Visual-Semantic Relational Reasoning for Video Question Answering
Specifically, we present a novel graph memory mechanism to perform relational reasoning, and further develop two types of graph memory: a) visual graph memory that leverages visual information of video for relational reasoning; b) semantic graph memory that is specifically designed to explicitly leverage semantic knowledge contained in the classes and attributes of video objects, and perform relational reasoning in the semantic space.
Scene Segmentation with Dual Relation-aware Attention Network
We conduct extensive experiments to validate the effectiveness of our network and achieve new state-of-the-art segmentation performance on four challenging scene segmentation data sets, i. e., Cityscapes, ADE20K, PASCAL Context, and COCO Stuff data sets.
Ranked #8 on
Semantic Segmentation
on COCO-Stuff test
Decoupled Spatial-Temporal Attention Network for Skeleton-Based Action Recognition
Besides, from the data aspect, we introduce a skeletal data decoupling technique to emphasize the specific characteristics of space/time and different motion scales, resulting in a more comprehensive understanding of the human actions. To test the effectiveness of the proposed method, extensive experiments are conducted on four challenging datasets for skeleton-based gesture and action recognition, namely, SHREC, DHG, NTU-60 and NTU-120, where DSTA-Net achieves state-of-the-art performance on all of them.
Ranked #27 on
Skeleton Based Action Recognition
on NTU RGB+D
Non-Autoregressive Image Captioning with Counterfactuals-Critical Multi-Agent Learning
In this paper, we propose a Non-Autoregressive Image Captioning (NAIC) model with a novel training paradigm: Counterfactuals-critical Multi-Agent Learning (CMAL).
What and Where: Modeling Skeletons from Semantic and Spatial Perspectives for Action Recognition
The two perspectives are orthogonal and complementary to each other; and by fusing them in a unified framework, our method achieves a more comprehensive understanding of the skeleton data.
Normalized and Geometry-Aware Self-Attention Network for Image Captioning
First, we propose Normalized Self-Attention (NSA), a reparameterization of SA that brings the benefits of normalization inside SA.
Skeleton-Based Action Recognition with Multi-Stream Adaptive Graph Convolutional Networks
Second, the second-order information of the skeleton data, i. e., the length and orientation of the bones, is rarely investigated, which is naturally more informative and discriminative for the human action recognition.
Action Recognition via Pose-Based Graph Convolutional Networks with Intermediate Dense Supervision
Existing methods exploit the joint positions to extract the body-part features from the activation map of the convolutional networks to assist human action recognition.
Adaptive Context Network for Scene Parsing
Recent works attempt to improve scene parsing performance by exploring different levels of contexts, and typically train a well-designed convolutional network to exploit useful contexts across all pixels equally.
Ranked #72 on
Semantic Segmentation
on ADE20K val
Aligning Linguistic Words and Visual Semantic Units for Image Captioning
Image captioning attempts to generate a sentence composed of several linguistic words, which are used to describe objects, attributes, and interactions in an image, denoted as visual semantic units in this paper.
Non-Local Graph Convolutional Networks for Skeleton-Based Action Recognition
However, the topology of the graph is set by hand and fixed over all layers, which may be not optimal for the action recognition task and the hierarchical CNN structures.
Ranked #55 on
Skeleton Based Action Recognition
on NTU RGB+D
Learning Feature Embeddings for Discriminant Model based Tracking
After observing that the features used in most online discriminatively trained trackers are not optimal, in this paper, we propose a novel and effective architecture to learn optimal feature embeddings for online discriminative tracking.
Recurrent Calibration Network for Irregular Text Recognition
In this paper, we propose a novel Recurrent Calibration Network (RCN) for irregular scene text recognition.
Dual Attention Network for Scene Segmentation
Specifically, we append two types of attention modules on top of traditional dilated FCN, which model the semantic interdependencies in spatial and channel dimensions respectively.
Ranked #6 on
Semantic Segmentation
on Trans10K
Two-Stream Adaptive Graph Convolutional Networks for Skeleton-Based Action Recognition
In addition, the second-order information (the lengths and directions of bones) of the skeleton data, which is naturally more informative and discriminative for action recognition, is rarely investigated in existing methods.
Ranked #5 on
Skeleton Based Action Recognition
on UAV-Human
Recent Advances in Efficient Computation of Deep Convolutional Neural Networks
As for hardware implementation of deep neural networks, a batch of accelerators based on FPGA/ASIC have been proposed in recent years.
Decoding with Value Networks for Neural Machine Translation
Inspired by the success and methodology of AlphaGo, in this paper we propose using a prediction network to improve beam search, which takes the source sentence $x$, the currently available decoding output $y_1,\cdots, y_{t-1}$ and a candidate word $w$ at step $t$ as inputs and predicts the long-term value (e. g., BLEU score) of the partial target sentence if it is completed by the NMT model.
Egocentric Gesture Recognition Using Recurrent 3D Convolutional Neural Networks With Spatiotemporal Transformer Modules
Gesture is a natural interface in interacting with wearable devices such as VR/AR helmet and glasses.
Reading Scene Text with Attention Convolutional Sequence Modeling
Reading text in the wild is a challenging task in the field of computer vision.
CONE: Community Oriented Network Embedding
It is usually modeled as an unsupervised clustering problem on graphs, based on heuristic assumptions about community characteristics, such as edge density and node homogeneity.
Social and Information Networks Physics and Society
Stacked Deconvolutional Network for Semantic Segmentation
In SDN, multiple shallow deconvolutional networks, which are called as SDN units, are stacked one by one to integrate contextual information and guarantee the fine recovery of localization information.
Ranked #4 on
Semantic Segmentation
on PASCAL VOC 2012 test
CoupleNet: Coupling Global Structure with Local Parts for Object Detection
To fully explore the local and global properties, in this paper, we propose a novel fully convolutional network, named as CoupleNet, to couple the global structure with local parts for object detection.
Ranked #5 on
Object Detection
on PASCAL VOC 2007
Body Joint guided 3D Deep Convolutional Descriptors for Action Recognition
To make it end-to-end and do not rely on any sophisticated body joint detection algorithm, we further propose a two-stream bilinear model which can learn the guidance from the body joints and capture the spatio-temporal features simultaneously.
Relaxing From Vocabulary: Robust Weakly-Supervised Deep Learning for Vocabulary-Free Image Tagging
The development of deep learning has empowered machines with comparable capability of recognizing limited image categories to human beings.
Online Sketching Hashing
Recently, hashing based approximate nearest neighbor (ANN) search has attracted much attention.
Fast and Accurate Image Matching with Cascade Hashing for 3D Reconstruction
Image matching is one of the most challenging stages in 3D reconstruction, which usually occupies half of computational cost and inaccurate matching may lead to failure of reconstruction.
Weakly-Supervised Dual Clustering for Image Semantic Segmentation
In this paper, we propose a novel Weakly-Supervised Dual Clustering (WSDC) approach for image semantic segmentation with image-level labels, i. e., collaboratively performing image segmentation and tag alignment with those regions.
