1.6k citations · 3.7k across the 93 of their papers we have counts for
19 papers · 1 filter
Exploiting Sample Uncertainty for Domain Adaptive Person Re-Identification
Kecheng Zheng, Cuiling Lan, Wenjun Zeng +2
Many unsupervised domain adaptive (UDA) person re-identification (ReID) approaches combine clustering-based pseudo-label prediction with feature fine-tuning. However, because of do…
Re-identification = Retrieval + Verification: Back to Essence and Forward with a New Metric
Zheng Wang, Xin Yuan, Toshihiko Yamasaki +3
Re-identification (re-ID) is currently investigated as a closed-world image retrieval task, and evaluated by retrieval based metrics. The algorithms return ranking lists to users,…
An Empirical Study of the Collapsing Problem in Semi-Supervised 2D Human Pose Estimation
Rongchang Xie, Chunyu Wang, Wenjun Zeng +1
Semi-supervised learning aims to boost the accuracy of a model by exploring unlabeled images. The state-of-the-art methods are consistency-based which learn about unlabeled images…
AdaFuse: Adaptive Multiview Fusion for Accurate Human Pose Estimation in the Wild
Zhe Zhang, Chunyu Wang, Weichao Qiu +2
Occlusion is probably the biggest challenge for human pose estimation in the wild. Typical solutions often rely on intrusive sensors such as IMUs to detect occluded joints. To make…
Uncertainty-Aware Few-Shot Image Classification
Zhizheng Zhang, Cuiling Lan, Wenjun Zeng +2
Few-shot image classification learns to recognize new categories from limited labelled data. Metric learning based approaches have been widely investigated, where a query sample is…
Online Speaker Diarization with Relation Network
Xiang Li, Yucheng Zhao, Chong Luo +1
In this paper, we propose an online speaker diarization system based on Relation Network, named RenoSD. Unlike conventional diariztion systems which consist of several independentl…
Global Distance-distributions Separation for Unsupervised Person Re-identification
Xin Jin, Cuiling Lan, Wenjun Zeng +1
Supervised person re-identification (ReID) often has poor scalability and usability in real-world deployments due to domain gaps and the lack of annotations for the target domain d…
Feature Alignment and Restoration for Domain Generalization and Adaptation
Xin Jin, Cuiling Lan, Wenjun Zeng +1
For domain generalization (DG) and unsupervised domain adaptation (UDA), cross domain feature alignment has been widely explored to pull the feature distributions of different doma…
Beyond Triplet Loss: Meta Prototypical N-tuple Loss for Person Re-identification
Zhizheng Zhang, Cuiling Lan, Wenjun Zeng +2
Person Re-identification (ReID) aims at matching a person of interest across images. In convolutional neural network (CNN) based approaches, loss design plays a vital role in pulli…
Style Normalization and Restitution for Generalizable Person Re-identification
Xin Jin, Cuiling Lan, Wenjun Zeng +2
Existing fully-supervised person re-identification (ReID) methods usually suffer from poor generalization capability caused by domain gaps. The key to solving this problem lies in…
Spatiotemporal Fusion in 3D CNNs: A Probabilistic View
Yizhou Zhou, Xiaoyan Sun, Chong Luo +2
Despite the success in still image recognition, deep neural networks for spatiotemporal signal tasks (such as human action recognition in videos) still suffers from low efficacy an…
Fusing Wearable IMUs with Multi-View Images for Human Pose Estimation: A Geometric Approach
Zhe Zhang, Chunyu Wang, Wenhu Qin +1
We propose to estimate 3D human pose from multi-view images and a few IMUs attached at person's limbs. It operates by firstly detecting 2D poses from the two signals, and then lift…
Tracking by Instance Detection: A Meta-Learning Approach
Guangting Wang, Chong Luo, Xiaoyan Sun +2
We consider the tracking problem as a special type of object detection problem, which we call instance detection. With proper initialization, a detector can be quickly converted in…
VoxelPose: Towards Multi-Camera 3D Human Pose Estimation in Wild Environment
Hanyue Tu, Chunyu Wang, Wenjun Zeng
We present an approach to estimate 3D poses of multiple people from multiple camera views. In contrast to the previous efforts which require to establish cross-view correspondence…
FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking
Yifu Zhang, Chunyu Wang, Xinggang Wang +2
Multi-object tracking (MOT) is an important problem in computer vision which has a wide range of applications. Formulating MOT as multi-task learning of object detection and re-ID…
Multi-Granularity Reference-Aided Attentive Feature Aggregation for Video-based Person Re-identification
Zhizheng Zhang, Cuiling Lan, Wenjun Zeng +1
Video-based person re-identification (reID) aims at matching the same person across video clips. It is a challenging task due to the existence of redundancy among frames, newly rev…
STC-Flow: Spatio-temporal Context-aware Optical Flow Estimation
Xiaolin Song, Yuyang Zhao, Jingyu Yang
In this paper, we propose a spatio-temporal contextual network, STC-Flow, for optical flow estimation. Unlike previous optical flow estimation approaches with local pyramid feature…
Uncertainty-Aware Multi-Shot Knowledge Distillation for Image-Based Object Re-Identification
Xin Jin, Cuiling Lan, Wenjun Zeng +1
Object re-identification (re-id) aims to identify a specific object across times or camera views, with the person re-id and vehicle re-id as the most widely studied applications. R…
FPCR-Net: Feature Pyramidal Correlation and Residual Reconstruction for Optical Flow Estimation
Xiaolin Song, Yuyang Zhao, Jingyu Yang +2
Optical flow estimation is an important yet challenging problem in the field of video analytics. The features of different semantics levels/layers of a convolutional neural network…