Long video understanding requires models to identify and reason over sparse, temporally distributed evidence within limited frame budgets. Existing keyframe selection methods typically retrieve query-relevant frames from a densely sampled candidate set before inference. However, global image-text matching incurs unnece...
Yi-Song Hu, Jun-Bo Wang, Yu-Ke Li et al.· 0 citations
Current large video-language models (LVLMs) still face challenges when dealing with long videos, mainly because frames are often processed independently, making it difficult to capture temporal dependencies across events. Although retrieval-augmented approaches have been introduced to provide additional context, most o...
Yu-Hao Qin, Jun-Bo Wang, Yu-Ke Li et al.· 0 citations
This work proposes TDVR, a training-free reasoning framework that disambiguates the input text and infers accurate viewpoints for zero-shot 3D visual grounding, and outperforms the existing state-of-the-art methods in addressing ambiguous query text and deficient viewpoints.
Qingxi Du, Jun-Bo Wang, Yu-Ke Li et al.· 0 citations
This work proposes a novel zero-shot video captioning framework (WSV) consisting of two training stages, which first generates corresponding synthetic video latent representations via a pretrained text-to-video generation model, and designs a polisher capable of bridging the gap between real and synthetic video distrib...
Liangyu Fu, Jun-Bo Wang, Yu-Ke Li et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.