activity
20212023
most citedFeature Erasing and Diffusion Network for Occluded Person Re-Identification

17 citations · 20 across the 7 of their papers we have counts for

collaborators

7 papers

cs.CV2023

Advancing Referring Expression Segmentation Beyond Single Image

Yixuan Wu, Zhao Zhang, Xie Chi +2

Referring Expression Segmentation (RES) is a widely explored multi-modal task, which endeavors to segment the pre-existing object within a single image with a given linguistic expr…

cs.CV20232 cited

CORA: Adapting CLIP for Open-Vocabulary Detection with Region Prompting and Anchor Pre-Matching

Xiaoshi Wu, Feng Zhu, Rui Zhao +1

Open-vocabulary detection (OVD) is an object detection task aiming at detecting objects from novel categories beyond the base categories on which the detector is trained. Recent OV…

cs.CV2023

HumanBench: Towards General Human-centric Perception with Projector Assisted Pretraining

Shixiang Tang, Cheng Chen, Qingsong Xie +9

Human-centric perceptions include a variety of vision tasks, which have widespread industrial applications, including surveillance, autonomous driving, and the metaverse. It is des…

cs.CV2023

Saliency Guided Contrastive Learning on Scene Images

Meilin Chen, Yizhou Wang, Shixiang Tang +6

Self-supervised learning holds promise in leveraging large numbers of unlabeled data. However, its success heavily relies on the highly-curated dataset, e.g., ImageNet, which still…

cs.IR20231 cited

DCMT: A Direct Entire-Space Causal Multi-Task Framework for Post-Click Conversion Estimation

Feng Zhu, Mingjie Zhong, Xinxing Yang +8

In recommendation scenarios, there are two long-standing challenges, i.e., selection bias and data sparsity, which lead to a significant drop in prediction accuracy for both Click-…

cs.CV2022

Instance As Identity: A Generic Online Paradigm for Video Instance Segmentation

Feng Zhu, Zongxin Yang, Xin Yu +2

Modeling temporal information for both detection and tracking in a unified framework has been proved a promising solution to video instance segmentation (VIS). However, how to effe…