Text Proxy: Decomposing Retrieval from a 1-to-N Relationship into N 1-to-1 Relationships for Text-Video Retrieval

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Xiao, Jian, Hu, Zhenzhen, Li, Jia, Hong, Richang
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866929632004014080
author Xiao, Jian
Hu, Zhenzhen
Li, Jia
Hong, Richang
author_facet Xiao, Jian
Hu, Zhenzhen
Li, Jia
Hong, Richang
contents Text-video retrieval (TVR) has seen substantial advancements in recent years, fueled by the utilization of pre-trained models and large language models (LLMs). Despite these advancements, achieving accurate matching in TVR remains challenging due to inherent disparities between video and textual modalities and irregularities in data representation. In this paper, we propose Text-Video-ProxyNet (TV-ProxyNet), a novel framework designed to decompose the conventional 1-to-N relationship of TVR into N distinct 1-to-1 relationships. By replacing a single text query with a series of text proxies, TV-ProxyNet not only broadens the query scope but also achieves a more precise expansion. Each text proxy is crafted through a refined iterative process, controlled by mechanisms we term as the director and dash, which regulate the proxy's direction and distance relative to the original text query. This setup not only facilitates more precise semantic alignment but also effectively manages the disparities and noise inherent in multimodal data. Our experiments on three representative video-text retrieval benchmarks, MSRVTT, DiDeMo, and ActivityNet Captions, demonstrate the effectiveness of TV-ProxyNet. The results show an improvement of 2.0% to 3.3% in R@1 over the baseline. TV-ProxyNet achieved state-of-the-art performance on MSRVTT and ActivityNet Captions, and a 2.0% improvement on DiDeMo compared to existing methods, validating our approach's ability to enhance semantic mapping and reduce error propensity.
format Preprint
id arxiv_https___arxiv_org_abs_2410_06618
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Text Proxy: Decomposing Retrieval from a 1-to-N Relationship into N 1-to-1 Relationships for Text-Video Retrieval
Xiao, Jian
Hu, Zhenzhen
Li, Jia
Hong, Richang
Computer Vision and Pattern Recognition
Information Retrieval
Multimedia
Text-video retrieval (TVR) has seen substantial advancements in recent years, fueled by the utilization of pre-trained models and large language models (LLMs). Despite these advancements, achieving accurate matching in TVR remains challenging due to inherent disparities between video and textual modalities and irregularities in data representation. In this paper, we propose Text-Video-ProxyNet (TV-ProxyNet), a novel framework designed to decompose the conventional 1-to-N relationship of TVR into N distinct 1-to-1 relationships. By replacing a single text query with a series of text proxies, TV-ProxyNet not only broadens the query scope but also achieves a more precise expansion. Each text proxy is crafted through a refined iterative process, controlled by mechanisms we term as the director and dash, which regulate the proxy's direction and distance relative to the original text query. This setup not only facilitates more precise semantic alignment but also effectively manages the disparities and noise inherent in multimodal data. Our experiments on three representative video-text retrieval benchmarks, MSRVTT, DiDeMo, and ActivityNet Captions, demonstrate the effectiveness of TV-ProxyNet. The results show an improvement of 2.0% to 3.3% in R@1 over the baseline. TV-ProxyNet achieved state-of-the-art performance on MSRVTT and ActivityNet Captions, and a 2.0% improvement on DiDeMo compared to existing methods, validating our approach's ability to enhance semantic mapping and reduce error propensity.
title Text Proxy: Decomposing Retrieval from a 1-to-N Relationship into N 1-to-1 Relationships for Text-Video Retrieval
topic Computer Vision and Pattern Recognition
Information Retrieval
Multimedia
url https://arxiv.org/abs/2410.06618