216 citations · 1.9k across the 97 of their papers we have counts for
19 papers · 1 filter
Contrastive Transformation for Self-supervised Correspondence Learning
Ning Wang, Wengang Zhou, Houqiang Li
In this paper, we focus on the self-supervised learning of visual correspondence using unlabeled videos in the wild. Our method simultaneously considers intra- and inter-video repr…
Voxel R-CNN: Towards High Performance Voxel-based 3D Object Detection
Jiajun Deng, Shaoshuai Shi, Peiwei Li +3
Recent advances on 3D object detection heavily rely on how the 3D data are represented, \emph{i.e.}, voxel-based or point-based representation. Many existing high performance 3D de…
Unsupervised Pre-training for Person Re-identification
Dengpan Fu, Dongdong Chen, Jianmin Bao +5
In this paper, we present a large scale unlabeled person re-identification (Re-ID) dataset "LUPerson" and make the first attempt of performing unsupervised pre-training for improvi…
Heterogeneous Contrastive Learning: Encoding Spatial Information for Compact Visual Representations
Xinyue Huo, Lingxi Xie, Longhui Wei +6
Contrastive learning has achieved great success in self-supervised visual representation learning, but existing approaches mostly ignored spatial information which is often crucial…
Can Semantic Labels Assist Self-Supervised Visual Representation Learning?
Longhui Wei, Lingxi Xie, Jianzhong He +5
Recently, contrastive learning has largely advanced the progress of unsupervised visual representation learning. Pre-trained on ImageNet, some self-supervised algorithms reported h…
Spatio-Temporal Inception Graph Convolutional Networks for Skeleton-Based Action Recognition
Zhen Huang, Xu Shen, Xinmei Tian +3
Skeleton-based human action recognition has attracted much attention with the prevalence of accessible depth sensors. Recently, graph convolutional networks (GCNs) have been widely…
Masked Contrastive Representation Learning for Reinforcement Learning
Jinhua Zhu, Yingce Xia, Lijun Wu +4
Improving sample efficiency is a key research problem in reinforcement learning (RL), and CURL, which uses contrastive learning to extract high-level features from raw pixels of in…
Boosting Continuous Sign Language Recognition via Cross Modality Augmentation
Junfu Pu, Wengang Zhou, Hezhen Hu +1
Continuous sign language recognition (SLR) deals with unaligned video-text pair and uses the word error rate (WER), i.e., edit distance, as the main evaluation metric. Since it is…
Improving Person Re-identification with Iterative Impression Aggregation
Dengpan Fu, Bo Xin, Jingdong Wang +4
Our impression about one person often updates after we see more aspects of him/her and this process keeps iterating given more meetings. We formulate such an intuition into the pro…
Vision Meets Wireless Positioning: Effective Person Re-identification with Recurrent Context Propagation
Yiheng Liu, Wengang Zhou, Mao Xi +2
Existing person re-identification methods rely on the visual sensor to capture the pedestrians. The image or video data from visual sensor inevitably suffers the occlusion and dram…
Global-local Enhancement Network for NMFs-aware Sign Language Recognition
Hezhen Hu, Wengang Zhou, Junfu Pu +1
Sign language recognition (SLR) is a challenging problem, involving complex manual features, i.e., hand gestures, and fine-grained non-manual features (NMFs), i.e., facial expressi…
Unsupervised Deep Representation Learning for Real-Time Tracking
Ning Wang, Wengang Zhou, Yibing Song +3
The advancement of visual tracking has continuously been brought by deep learning models. Typically, supervised learning is employed to train these models with expensive labeled da…
Single Shot Video Object Detector
Jiajun Deng, Yingwei Pan, Ting Yao +3
Single shot detectors that are potentially faster and simpler than two-stage detectors tend to be more applicable to object detection in videos. Nevertheless, the extension of such…
Efficient Integer-Arithmetic-Only Convolutional Neural Networks
Hengrui Zhao, Dong Liu, Houqiang Li
Integer-arithmetic-only networks have been demonstrated effective to reduce computational cost and to ensure cross-platform consistency. However, previous works usually report a de…
Cascaded Regression Tracking: Towards Online Hard Distractor Discrimination
Ning Wang, Wengang Zhou, Qi Tian +1
Visual tracking can be easily disturbed by similar surrounding objects. Such objects as hard distractors, even though being the minority among negative samples, increase the risk o…
M-LVC: Multiple Frames Prediction for Learned Video Compression
Jianping Lin, Dong Liu, Houqiang Li +1
We propose an end-to-end learned video compression scheme for low-latency scenarios. Previous methods are limited in using the previous one frame as reference. Our method introduce…
Long Short-Term Relation Networks for Video Action Detection
Dong Li, Ting Yao, Zhaofan Qiu +2
It has been well recognized that modeling human-object or object-object relations would be helpful for detection task. Nevertheless, the problem is not trivial especially when expl…
Spatial-Temporal Multi-Cue Network for Continuous Sign Language Recognition
Hao Zhou, Wengang Zhou, Yun Zhou +1
Despite the recent success of deep learning in continuous sign language recognition (CSLR), deep models typically focus on the most discriminative features, ignoring other potentia…
Soft Hindsight Experience Replay
Qiwei He, Liansheng Zhuang, Houqiang Li
Efficient learning in the environment with sparse rewards is one of the most important challenges in Deep Reinforcement Learning (DRL). In continuous DRL environments such as robot…