activity
20212024
most citedBridging the Gap Between End-to-end and Non-End-to-end Multi-Object Tracking

11 citations · 26 across the 6 of their papers we have counts for

collaborators

6 papers

cs.CV20241 cited

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…

cs.CV20231 cited

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…

cs.CV202311 cited

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…

cs.CV202310 cited

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…

cs.CV20223 cited

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…

cs.CV2021

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…