Salvato in:
Dettagli Bibliografici
Autori principali: Wang, Yuting, Wang, Jinpeng, Chen, Bin, Dai, Tao, Luo, Ruisheng, Xia, Shu-Tao
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2405.13824
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916257394065408
author Wang, Yuting
Wang, Jinpeng
Chen, Bin
Dai, Tao
Luo, Ruisheng
Xia, Shu-Tao
author_facet Wang, Yuting
Wang, Jinpeng
Chen, Bin
Dai, Tao
Luo, Ruisheng
Xia, Shu-Tao
contents Given a text query, partially relevant video retrieval (PRVR) aims to retrieve untrimmed videos containing relevant moments. Due to the lack of moment annotations, the uncertainty lying in clip modeling and text-clip correspondence leads to major challenges. Despite the great progress, existing solutions either sacrifice efficiency or efficacy to capture varying and uncertain video moments. What's worse, few methods have paid attention to the text-clip matching pattern under such uncertainty, exposing the risk of semantic collapse. To address these issues, we present GMMFormer v2, an uncertainty-aware framework for PRVR. For clip modeling, we improve a strong baseline GMMFormer with a novel temporal consolidation module upon multi-scale contextual features, which maintains efficiency and improves the perception for varying moments. To achieve uncertainty-aware text-clip matching, we upgrade the query diverse loss in GMMFormer to facilitate fine-grained uniformity and propose a novel optimal matching loss for fine-grained text-clip alignment. Their collaboration alleviates the semantic collapse phenomenon and neatly promotes accurate correspondence between texts and moments. We conduct extensive experiments and ablation studies on three PRVR benchmarks, demonstrating remarkable improvement of GMMFormer v2 compared to the past SOTA competitor and the versatility of uncertainty-aware text-clip matching for PRVR. Code is available at \url{https://github.com/huangmozhi9527/GMMFormer_v2}.
format Preprint
id arxiv_https___arxiv_org_abs_2405_13824
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle GMMFormer v2: An Uncertainty-aware Framework for Partially Relevant Video Retrieval
Wang, Yuting
Wang, Jinpeng
Chen, Bin
Dai, Tao
Luo, Ruisheng
Xia, Shu-Tao
Computer Vision and Pattern Recognition
Given a text query, partially relevant video retrieval (PRVR) aims to retrieve untrimmed videos containing relevant moments. Due to the lack of moment annotations, the uncertainty lying in clip modeling and text-clip correspondence leads to major challenges. Despite the great progress, existing solutions either sacrifice efficiency or efficacy to capture varying and uncertain video moments. What's worse, few methods have paid attention to the text-clip matching pattern under such uncertainty, exposing the risk of semantic collapse. To address these issues, we present GMMFormer v2, an uncertainty-aware framework for PRVR. For clip modeling, we improve a strong baseline GMMFormer with a novel temporal consolidation module upon multi-scale contextual features, which maintains efficiency and improves the perception for varying moments. To achieve uncertainty-aware text-clip matching, we upgrade the query diverse loss in GMMFormer to facilitate fine-grained uniformity and propose a novel optimal matching loss for fine-grained text-clip alignment. Their collaboration alleviates the semantic collapse phenomenon and neatly promotes accurate correspondence between texts and moments. We conduct extensive experiments and ablation studies on three PRVR benchmarks, demonstrating remarkable improvement of GMMFormer v2 compared to the past SOTA competitor and the versatility of uncertainty-aware text-clip matching for PRVR. Code is available at \url{https://github.com/huangmozhi9527/GMMFormer_v2}.
title GMMFormer v2: An Uncertainty-aware Framework for Partially Relevant Video Retrieval
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.13824