MVMR: A New Framework For Evaluating Faithfulness Of Video Moment Retrieval Against Multiple Distractors
2023 · Nakyeong Yang, Minsung Kim, Seunghyun Yoon, et al.
Abstract
With the explosion of multimedia content, video moment retrieval (VMR), which aims to detect a video moment that matches a given text query from a video, has been studied intensively as a critical problem. However, the existing VMR framework evaluates video moment retrieval performance, assuming that a video is given, which may not reveal whether the models exhibit overconfidence in the falsely given video. In this paper, we propose the MVMR (Massive Videos Moment Retrieval for Faithfulness Evaluation) task that aims to retrieve video moments within a massive video set, including multiple distractors, to evaluate the faithfulness of VMR models. For this task, we suggest an automated massive video pool construction framework to categorize negative (distractors) and positive (false-negative) video sets using textual and visual semantic distance verification methods. We extend existing VMR datasets using these methods and newly construct three practical MVMR datasets. To solve the task, w
Authors
(none)
Tags
Stats
Related papers
- When One Moment Isn't Enough: Multi-moment Retrieval With Cross-moment Interactions (2025)1.81
- Hybrid-learning Video Moment Retrieval Across Multi-domain Labels (2024)0.00
- Vlanet: Video-language Alignment Network For Weakly-supervised Video Moment Retrieval (2020)13.28
- Context-enhanced Video Moment Retrieval With Large Language Models (2024)5.84
- Semantic Video Moments Retrieval At Scale: A New Task And A Baseline (2022)0.00
- MUVR: A Multi-modal Untrimmed Video Retrieval Benchmark With Multi-level Visual Correspondence (2025)1.40
- Selective Query-guided Debiasing For Video Corpus Moment Retrieval (2022)9.59
- Improving Video Corpus Moment Retrieval With Partial Relevance Enhancement (2024)7.89