VideoCLIP-XL: Advancing Long Description Understanding for Video CLIP Models

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Wang, Jiapeng, Wang, Chengyu, Huang, Kunzhe, Huang, Jun, Jin, Lianwen
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866910633089302528
author Wang, Jiapeng
Wang, Chengyu
Huang, Kunzhe
Huang, Jun
Jin, Lianwen
author_facet Wang, Jiapeng
Wang, Chengyu
Huang, Kunzhe
Huang, Jun
Jin, Lianwen
contents Contrastive Language-Image Pre-training (CLIP) has been widely studied and applied in numerous applications. However, the emphasis on brief summary texts during pre-training prevents CLIP from understanding long descriptions. This issue is particularly acute regarding videos given that videos often contain abundant detailed contents. In this paper, we propose the VideoCLIP-XL (eXtra Length) model, which aims to unleash the long-description understanding capability of video CLIP models. Firstly, we establish an automatic data collection system and gather a large-scale VILD pre-training dataset with VIdeo and Long-Description pairs. Then, we propose Text-similarity-guided Primary Component Matching (TPCM) to better learn the distribution of feature space while expanding the long description capability. We also introduce two new tasks namely Detail-aware Description Ranking (DDR) and Hallucination-aware Description Ranking (HDR) for further understanding improvement. Finally, we construct a Long Video Description Ranking (LVDR) benchmark for evaluating the long-description capability more comprehensively. Extensive experimental results on widely-used text-video retrieval benchmarks with both short and long descriptions and our LVDR benchmark can fully demonstrate the effectiveness of our method.
format Preprint
id arxiv_https___arxiv_org_abs_2410_00741
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle VideoCLIP-XL: Advancing Long Description Understanding for Video CLIP Models
Wang, Jiapeng
Wang, Chengyu
Huang, Kunzhe
Huang, Jun
Jin, Lianwen
Computation and Language
Computer Vision and Pattern Recognition
Multimedia
Contrastive Language-Image Pre-training (CLIP) has been widely studied and applied in numerous applications. However, the emphasis on brief summary texts during pre-training prevents CLIP from understanding long descriptions. This issue is particularly acute regarding videos given that videos often contain abundant detailed contents. In this paper, we propose the VideoCLIP-XL (eXtra Length) model, which aims to unleash the long-description understanding capability of video CLIP models. Firstly, we establish an automatic data collection system and gather a large-scale VILD pre-training dataset with VIdeo and Long-Description pairs. Then, we propose Text-similarity-guided Primary Component Matching (TPCM) to better learn the distribution of feature space while expanding the long description capability. We also introduce two new tasks namely Detail-aware Description Ranking (DDR) and Hallucination-aware Description Ranking (HDR) for further understanding improvement. Finally, we construct a Long Video Description Ranking (LVDR) benchmark for evaluating the long-description capability more comprehensively. Extensive experimental results on widely-used text-video retrieval benchmarks with both short and long descriptions and our LVDR benchmark can fully demonstrate the effectiveness of our method.
title VideoCLIP-XL: Advancing Long Description Understanding for Video CLIP Models
topic Computation and Language
Computer Vision and Pattern Recognition
Multimedia
url https://arxiv.org/abs/2410.00741