EA-VTR: Event-Aware Video-Text Retrieval

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Ma, Zongyang, Zhang, Ziqi, Chen, Yuxin, Qi, Zhongang, Yuan, Chunfeng, Li, Bing, Luo, Yingmin, Li, Xu, Qi, Xiaojuan, Shan, Ying, Hu, Weiming
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866914864857874432
author Ma, Zongyang
Zhang, Ziqi
Chen, Yuxin
Qi, Zhongang
Yuan, Chunfeng
Li, Bing
Luo, Yingmin
Li, Xu
Qi, Xiaojuan
Shan, Ying
Hu, Weiming
author_facet Ma, Zongyang
Zhang, Ziqi
Chen, Yuxin
Qi, Zhongang
Yuan, Chunfeng
Li, Bing
Luo, Yingmin
Li, Xu
Qi, Xiaojuan
Shan, Ying
Hu, Weiming
contents Understanding the content of events occurring in the video and their inherent temporal logic is crucial for video-text retrieval. However, web-crawled pre-training datasets often lack sufficient event information, and the widely adopted video-level cross-modal contrastive learning also struggles to capture detailed and complex video-text event alignment. To address these challenges, we make improvements from both data and model perspectives. In terms of pre-training data, we focus on supplementing the missing specific event content and event temporal transitions with the proposed event augmentation strategies. Based on the event-augmented data, we construct a novel Event-Aware Video-Text Retrieval model, ie, EA-VTR, which achieves powerful video-text retrieval ability through superior video event awareness. EA-VTR can efficiently encode frame-level and video-level visual representations simultaneously, enabling detailed event content and complex event temporal cross-modal alignment, ultimately enhancing the comprehensive understanding of video events. Our method not only significantly outperforms existing approaches on multiple datasets for Text-to-Video Retrieval and Video Action Recognition tasks, but also demonstrates superior event content perceive ability on Multi-event Video-Text Retrieval and Video Moment Retrieval tasks, as well as outstanding event temporal logic understanding ability on Test of Time task.
format Preprint
id arxiv_https___arxiv_org_abs_2407_07478
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle EA-VTR: Event-Aware Video-Text Retrieval
Ma, Zongyang
Zhang, Ziqi
Chen, Yuxin
Qi, Zhongang
Yuan, Chunfeng
Li, Bing
Luo, Yingmin
Li, Xu
Qi, Xiaojuan
Shan, Ying
Hu, Weiming
Computer Vision and Pattern Recognition
Understanding the content of events occurring in the video and their inherent temporal logic is crucial for video-text retrieval. However, web-crawled pre-training datasets often lack sufficient event information, and the widely adopted video-level cross-modal contrastive learning also struggles to capture detailed and complex video-text event alignment. To address these challenges, we make improvements from both data and model perspectives. In terms of pre-training data, we focus on supplementing the missing specific event content and event temporal transitions with the proposed event augmentation strategies. Based on the event-augmented data, we construct a novel Event-Aware Video-Text Retrieval model, ie, EA-VTR, which achieves powerful video-text retrieval ability through superior video event awareness. EA-VTR can efficiently encode frame-level and video-level visual representations simultaneously, enabling detailed event content and complex event temporal cross-modal alignment, ultimately enhancing the comprehensive understanding of video events. Our method not only significantly outperforms existing approaches on multiple datasets for Text-to-Video Retrieval and Video Action Recognition tasks, but also demonstrates superior event content perceive ability on Multi-event Video-Text Retrieval and Video Moment Retrieval tasks, as well as outstanding event temporal logic understanding ability on Test of Time task.
title EA-VTR: Event-Aware Video-Text Retrieval
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2407.07478