71 citations · 194 across the 13 of their papers we have counts for
14 papers
Online Continual Learning via Multiple Deep Metric Learning and Uncertainty-guided Episodic Memory Replay -- 3rd Place Solution for ICCV 2021 Workshop SSLAD Track 3A Continual Object Classification
Muhammad Rifki Kurniawan, Xing Wei, Yihong Gong
Online continual learning in the wild is a very difficult task in machine learning. Non-stationarity in online continual learning potentially brings about catastrophic forgetting i…
Direct Measure Matching for Crowd Counting
Hui Lin, Xiaopeng Hong, Zhiheng Ma +4
Traditional crowd counting approaches usually use Gaussian assumption to generate pseudo density ground truth, which suffers from problems like inaccurate estimation of the Gaussia…
Know Your Surroundings: Panoramic Multi-Object Tracking by Multimodality Collaboration
Yuhang He, Wentao Yu, Jie Han +3
In this paper, we focus on the multi-object tracking (MOT) problem of automatic driving and robot navigation. Most existing MOT methods track multiple objects using a singular RGB…
Few-Shot Class-Incremental Learning
Xiaoyu Tao, Xiaopeng Hong, Xinyuan Chang +3
The ability to incrementally learn new classes is crucial to the development of real-world artificial intelligence systems. In this paper, we focus on a challenging but practical f…
Beyond Universal Person Re-ID Attack
Wenjie Ding, Xing Wei, Rongrong Ji +3
Deep learning-based person re-identification (Re-ID) has made great progress and achieved high performance recently. In this paper, we make the first attempt to examine the vulnera…
Bayesian Loss for Crowd Count Estimation with Point Supervision
Zhiheng Ma, Xing Wei, Xiaopeng Hong +1
In crowd counting datasets, each person is annotated by a point, which is usually the center of the head. And the task is to estimate the total count in a crowd scene. Most of the…
Discriminative Feature Learning with Foreground Attention for Person Re-Identification
Sanping Zhou, Jinjun Wang, Deyu Meng +3
The performance of person re-identification (Re-ID) has been seriously effected by the large cross-view appearance variations caused by mutual occlusions and background clutters. H…
Deep Self-Paced Learning for Person Re-Identification
Sanping Zhou, Jinjun Wang, Deyu Meng +4
Person re-identification (Re-ID) usually suffers from noisy samples with background clutter and mutual occlusion, which makes it extremely difficult to distinguish different indivi…
Tracking Persons-of-Interest via Unsupervised Representation Adaptation
Shun Zhang, Jia-Bin Huang, Jongwoo Lim +4
Multi-face tracking in unconstrained videos is a challenging problem as faces of one person often appear drastically different in multiple shots due to significant variations in sc…
Large Margin Learning in Set to Set Similarity Comparison for Person Re-identification
Sanping Zhou, Jinjun Wang, Rui Shi +3
Person re-identification (Re-ID) aims at matching images of the same person across disjoint camera views, which is a challenging problem in multimedia analysis, multimedia editing…
Deep Feature Learning via Structured Graph Laplacian Embedding for Person Re-Identification
De Cheng, Yihong Gong, Zhihui Li +3
Learning the distance metric between pairs of examples is of great importance for visual recognition, especially for person re-identification (Re-Id). Recently, the contrastive and…
Single Image Super Resolution - When Model Adaptation Matters
Yudong Liang, Radu Timofte, Jinjun Wang +2
In the recent years impressive advances were made for single image super-resolution. Deep learning is behind a big part of this success. Deep(er) architecture design and external p…
Superpixel Hierarchy
Xing Wei, Qingxiong Yang, Yihong Gong +2
Superpixel segmentation is becoming ubiquitous in computer vision. In practice, an object can either be represented by a number of segments in finer levels of detail or included in…
Deep Multimodal Feature Analysis for Action Recognition in RGB+D Videos
Amir Shahroudy, Tian-Tsong Ng, Yihong Gong +1
Single modality action recognition on RGB or depth sequences has been extensively explored recently. It is generally accepted that each of these two modalities has different streng…