activity
20162021
most citedFew-Shot Class-Incremental Learning

15 citations · 41 across the 9 of their papers we have counts for

collaborators

12 papers

cs.CV2021

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…

cs.CV20211 cited

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…

cs.CV2021

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…

cs.CV202015 cited

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…

cs.CV2019

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…

cs.CV2019

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…