Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

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

About

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.

Jiapeng Wang, Chengyu Wang, Kunzhe Huang, Jun Huang, Lianwen Jin• 2024

Related benchmarks

TaskDatasetResultRank
Text-to-Video RetrievalMSRVTT
Recall@144.3
48
Video RetrievalCRB-G
R@182.8
18
Video RetrievalCRB-T
R@148.7
18
Video RetrievalCRB-S
R@183.9
18
Video RetrievalDiDeMo
R@140.3
18
Video RetrievalUVRB Average of 16 datasets
Average Score49.1
18
Video RetrievalVDC-O
R@173.5
18
Video RetrievalDREAM-E
R@126.3
18
Image-to-Video RetrievalMSRVTT I2V
Recall@186.1
18
Video RetrievalVDC-D
R@182
18
Showing 10 of 22 rows

Other info

Follow for update