When One Moment Isn't Enough: Multi-moment Retrieval With Cross-moment Interactions
2025 · Zhuo Cao, Heming Du, Bingqing Zhang, et al.
Abstract
Existing Moment retrieval (MR) methods focus on Single-Moment Retrieval (SMR). However, one query can correspond to multiple relevant moments in real-world applications. This makes the existing datasets and methods insufficient for video temporal grounding. By revisiting the gap between current MR tasks and real-world applications, we introduce a high-quality datasets called QVHighlights Multi-Moment Dataset (QV-M\(^2\)), along with new evaluation metrics tailored for multi-moment retrieval (MMR). QV-M\(^2\) consists of 2,212 annotations covering 6,384 video segments. Building on existing efforts in MMR, we propose a framework called FlashMMR. Specifically, we propose a Multi-moment Post-verification module to refine the moment boundaries. We introduce constrained temporal adjustment and subsequently leverage a verification module to re-evaluate the candidate segments. Through this sophisticated filtering pipeline, low-confidence proposals are pruned, and robust multi-moment alignment
Authors
(none)
Tags
Stats
Related papers
- Improving Video Corpus Moment Retrieval With Partial Relevance Enhancement (2024)7.89
- MVMR: A New Framework For Evaluating Faithfulness Of Video Moment Retrieval Against Multiple Distractors (2023)1.40
- Momentseeker: A Task-oriented Benchmark For Long-video Moment Retrieval (2025)0.00
- Towards Efficient And Robust Moment Retrieval System: A Unified Framework For Multi-granularity Models And Temporal Reranking (2025)2.26
- Frame-wise Cross-modal Matching For Video Moment Retrieval (2020)13.17
- Hybrid-learning Video Moment Retrieval Across Multi-domain Labels (2024)0.00
- Selective Query-guided Debiasing For Video Corpus Moment Retrieval (2022)9.59
- Context-enhanced Video Moment Retrieval With Large Language Models (2024)5.84