Uneven Event Modeling For Partially Relevant Video Retrieval
2025 · Sa Zhu, Huashan Chen, Wanqian Zhang, et al.
Abstract
Given a text query, partially relevant video retrieval (PRVR) aims to retrieve untrimmed videos containing relevant moments, wherein event modeling is crucial for partitioning the video into smaller temporal events that partially correspond to the text. Previous methods typically segment videos into a fixed number of equal-length clips, resulting in ambiguous event boundaries. Additionally, they rely on mean pooling to compute event representations, inevitably introducing undesired misalignment. To address these, we propose an Uneven Event Modeling (UEM) framework for PRVR. We first introduce the Progressive-Grouped Video Segmentation (PGVS) module, to iteratively formulate events in light of both temporal dependencies and semantic similarity between consecutive frames, enabling clear event boundaries. Furthermore, we also propose the Context-Aware Event Refinement (CAER) module to refine the event representation conditioned the text's cross-attention. This enables event representation
Authors
(none)
Tags
Stats
Related papers
- PRVR: Partially Relevant Video Retrieval (2022)2.26
- Ambiguity-restrained Text-video Representation Learning For Partially Relevant Video Retrieval (2025)5.84
- Gmmformer: Gaussian-mixture-model Based Transformer For Efficient Partially Relevant Video Retrieval (2023)12.06
- Mitigating Semantic Collapse In Partially Relevant Video Retrieval (2025)0.00
- Imagine Before Concentration: Diffusion-guided Registers Enhance Partially Relevant Video Retrieval (2026)3.80
- Prototypes Are Balanced Units For Efficient And Effective Partially Relevant Video Retrieval (2025)0.00
- Improving Video Corpus Moment Retrieval With Partial Relevance Enhancement (2024)7.89
- Mamfusion: Multi-mamba With Temporal Fusion For Partially Relevant Video Retrieval (2025)1.69