Guardado en:
Detalles Bibliográficos
Autores principales: Chao, Lianying, Yin, Linfeng, Ren, Peiyu, Jiang, Yifan, Ren, Qiaoyu, Shan, Dingcheng, Pang, Jing-cheng, Wu, Sijie, Li, Xubin, Zhang, Kai, Chen, Xin
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:https://arxiv.org/abs/2601.14594
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917465939771392
author Chao, Lianying
Yin, Linfeng
Ren, Peiyu
Jiang, Yifan
Ren, Qiaoyu
Shan, Dingcheng
Pang, Jing-cheng
Wu, Sijie
Li, Xubin
Zhang, Kai
Chen, Xin
author_facet Chao, Lianying
Yin, Linfeng
Ren, Peiyu
Jiang, Yifan
Ren, Qiaoyu
Shan, Dingcheng
Pang, Jing-cheng
Wu, Sijie
Li, Xubin
Zhang, Kai
Chen, Xin
contents Video captioning models convert frames into visual tokens and generate descriptions with large language models (LLMs). Since encoding all frames is prohibitively expensive, uniform sampling is the default choice, but it enforces equal temporal coverage while ignoring the uneven events distribution. This motivates a Learnable Frame Selector (LFS) that selects temporally diverse and event-relevant frames. LFS explicitly models temporal importance to balance temporal diversity and event relevance, and employs a stratified strategy to ensure temporal coverage while avoiding clustering. Crucially, LFS leverages caption feedback from frozen video-LLMs to learn frame selection that directly optimizes downstream caption quality. Additionally, we identify the gap between existing benchmark and human's cognition. Thus, we introduce ICH-CC built from carefully designed questions by annotators that reflect human-consistent understanding of video. Experiments indicate that LFS consistently improves detailed video captioning across two representative community benchmarks and ICH-CC, achieving up to 2.0% gains on VDC and over 4% gains on ICH-CC. Moreover, we observe that enhanced captions with LFS leads to improved performance on video question answering. Overall, LFS provides an effective and easy-to-integrate solution for detailed video captioning.
format Preprint
id arxiv_https___arxiv_org_abs_2601_14594
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle LFS: Learnable Frame Selector for Event-Aware and Temporally Diverse Video Captioning
Chao, Lianying
Yin, Linfeng
Ren, Peiyu
Jiang, Yifan
Ren, Qiaoyu
Shan, Dingcheng
Pang, Jing-cheng
Wu, Sijie
Li, Xubin
Zhang, Kai
Chen, Xin
Computer Vision and Pattern Recognition
Video captioning models convert frames into visual tokens and generate descriptions with large language models (LLMs). Since encoding all frames is prohibitively expensive, uniform sampling is the default choice, but it enforces equal temporal coverage while ignoring the uneven events distribution. This motivates a Learnable Frame Selector (LFS) that selects temporally diverse and event-relevant frames. LFS explicitly models temporal importance to balance temporal diversity and event relevance, and employs a stratified strategy to ensure temporal coverage while avoiding clustering. Crucially, LFS leverages caption feedback from frozen video-LLMs to learn frame selection that directly optimizes downstream caption quality. Additionally, we identify the gap between existing benchmark and human's cognition. Thus, we introduce ICH-CC built from carefully designed questions by annotators that reflect human-consistent understanding of video. Experiments indicate that LFS consistently improves detailed video captioning across two representative community benchmarks and ICH-CC, achieving up to 2.0% gains on VDC and over 4% gains on ICH-CC. Moreover, we observe that enhanced captions with LFS leads to improved performance on video question answering. Overall, LFS provides an effective and easy-to-integrate solution for detailed video captioning.
title LFS: Learnable Frame Selector for Event-Aware and Temporally Diverse Video Captioning
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2601.14594