11 citations · 26 across the 6 of their papers we have counts for
6 papers
LaSagnA: Language-based Segmentation Assistant for Complex Queries
Cong Wei, Haoxian Tan, Yujie Zhong +2
Recent advancements have empowered Large Language Models for Vision (vLLMs) to generate detailed perceptual outcomes, including bounding boxes and masks. Nonetheless, there are two…
Temporal Action Localization with Enhanced Instant Discriminability
Dingfeng Shi, Qiong Cao, Yujie Zhong +4
Temporal action detection (TAD) aims to detect all action boundaries and their corresponding categories in an untrimmed video. The unclear boundaries of actions in videos often res…
Bridging the Gap Between End-to-end and Non-End-to-end Multi-Object Tracking
Feng Yan, Weixin Luo, Yujie Zhong +2
Existing end-to-end Multi-Object Tracking (e2e-MOT) methods have not surpassed non-end-to-end tracking-by-detection methods. One potential reason is its label assignment strategy d…
TriDet: Temporal Action Detection with Relative Boundary Modeling
Dingfeng Shi, Yujie Zhong, Qiong Cao +3
In this paper, we present a one-stage framework TriDet for temporal action detection. Existing methods often suffer from imprecise boundary predictions due to the ambiguous action…
ReAct: Temporal Action Detection with Relational Queries
Dingfeng Shi, Yujie Zhong, Qiong Cao +4
This work aims at advancing temporal action detection (TAD) using an encoder-decoder framework with action queries, similar to DETR, which has shown great success in object detecti…
InsCLR: Improving Instance Retrieval with Self-Supervision
Zelu Deng, Yujie Zhong, Sheng Guo +1
This work aims at improving instance retrieval with self-supervision. We find that fine-tuning using the recently developed self-supervised (SSL) learning methods, such as SimCLR a…