collaborators
Showing cs.CVShow all

5 papers · 1 filter

cs.CV2024

Skim then Focus: Integrating Contextual and Fine-grained Views for Repetitive Action Counting

Zhengqi Zhao, Xiaohu Huang, Hao Zhou +6

The key to action counting is accurately locating each video's repetitive actions. Instead of estimating the probability of each frame belonging to an action directly, we propose a…

cs.CV20244 cited

FROSTER: Frozen CLIP Is A Strong Teacher for Open-Vocabulary Action Recognition

Xiaohu Huang, Hao Zhou, Kun Yao +1

In this paper, we introduce FROSTER, an effective framework for open-vocabulary action recognition. The CLIP model has achieved remarkable success in a range of image-based tasks,…

cs.CV20235 cited

HAP: Structure-Aware Masked Image Modeling for Human-Centric Perception

Junkun Yuan, Xinyu Zhang, Hao Zhou +12

Model pre-training is essential in human-centric perception. In this paper, we first introduce masked image modeling (MIM) as a pre-training approach for this task. Upon revisiting…

cs.CV20232 cited

Sign Language Translation with Iterative Prototype

Huijie Yao, Wengang Zhou, Hao Feng +3

This paper presents IP-SLT, a simple yet effective framework for sign language translation (SLT). Our IP-SLT adopts a recurrent structure and enhances the semantic representation (…

cs.CV20231 cited

Towards Diverse Temporal Grounding under Single Positive Labels

Hao Zhou, Chongyang Zhang, Yanjun Chen +1

Temporal grounding aims to retrieve moments of the described event within an untrimmed video by a language query. Typically, existing methods assume annotations are precise and uni…