Beyond Coarse-Grained Matching in Video-Text Retrieval

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Aozhu, Doughty, Hazel, Li, Xirong, Snoek, Cees G. M.
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914976665436160
author Chen, Aozhu
Doughty, Hazel
Li, Xirong
Snoek, Cees G. M.
author_facet Chen, Aozhu
Doughty, Hazel
Li, Xirong
Snoek, Cees G. M.
contents Video-text retrieval has seen significant advancements, yet the ability of models to discern subtle differences in captions still requires verification. In this paper, we introduce a new approach for fine-grained evaluation. Our approach can be applied to existing datasets by automatically generating hard negative test captions with subtle single-word variations across nouns, verbs, adjectives, adverbs, and prepositions. We perform comprehensive experiments using four state-of-the-art models across two standard benchmarks (MSR-VTT and VATEX) and two specially curated datasets enriched with detailed descriptions (VLN-UVO and VLN-OOPS), resulting in a number of novel insights: 1) our analyses show that the current evaluation benchmarks fall short in detecting a model's ability to perceive subtle single-word differences, 2) our fine-grained evaluation highlights the difficulty models face in distinguishing such subtle variations. To enhance fine-grained understanding, we propose a new baseline that can be easily combined with current methods. Experiments on our fine-grained evaluations demonstrate that this approach enhances a model's ability to understand fine-grained differences.
format Preprint
id arxiv_https___arxiv_org_abs_2410_12407
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Beyond Coarse-Grained Matching in Video-Text Retrieval
Chen, Aozhu
Doughty, Hazel
Li, Xirong
Snoek, Cees G. M.
Computer Vision and Pattern Recognition
Computation and Language
Multimedia
Video-text retrieval has seen significant advancements, yet the ability of models to discern subtle differences in captions still requires verification. In this paper, we introduce a new approach for fine-grained evaluation. Our approach can be applied to existing datasets by automatically generating hard negative test captions with subtle single-word variations across nouns, verbs, adjectives, adverbs, and prepositions. We perform comprehensive experiments using four state-of-the-art models across two standard benchmarks (MSR-VTT and VATEX) and two specially curated datasets enriched with detailed descriptions (VLN-UVO and VLN-OOPS), resulting in a number of novel insights: 1) our analyses show that the current evaluation benchmarks fall short in detecting a model's ability to perceive subtle single-word differences, 2) our fine-grained evaluation highlights the difficulty models face in distinguishing such subtle variations. To enhance fine-grained understanding, we propose a new baseline that can be easily combined with current methods. Experiments on our fine-grained evaluations demonstrate that this approach enhances a model's ability to understand fine-grained differences.
title Beyond Coarse-Grained Matching in Video-Text Retrieval
topic Computer Vision and Pattern Recognition
Computation and Language
Multimedia
url https://arxiv.org/abs/2410.12407