5 citations · 9 across the 6 of their papers we have counts for
5 papers · 1 filter
PruneVid: Visual Token Pruning for Efficient Video Large Language Models
Xiaohu Huang, Hao Zhou, Kai Han
In this paper, we introduce PruneVid, a visual token pruning method designed to enhance the efficiency of multi-modal video understanding. Large Language Models (LLMs) have shown p…
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…
StrucTexTv3: An Efficient Vision-Language Model for Text-rich Image Perception, Comprehension, and Beyond
Pengyuan Lyu, Yulin Li, Hao Zhou +8
Text-rich images have significant and extensive value, deeply integrated into various aspects of human life. Notably, both visual cues and linguistic symbols in text-rich images pl…
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,…
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…