Gmmformer: Gaussian-mixture-model Based Transformer For Efficient Partially Relevant Video Retrieval
2023 · Yuting Wang, Jinpeng Wang, Bin Chen, et al.
Abstract
Given a text query, partially relevant video retrieval (PRVR) seeks to find untrimmed videos containing pertinent moments in a database. For PRVR, clip modeling is essential to capture the partial relationship between texts and videos. Current PRVR methods adopt scanning-based clip construction to achieve explicit clip modeling, which is information-redundant and requires a large storage overhead. To solve the efficiency problem of PRVR methods, this paper proposes GMMFormer, a Gaussian-Mixture-Model based Transformer which models clip representations implicitly. During frame interactions, we incorporate Gaussian-Mixture-Model constraints to focus each frame on its adjacent frames instead of the whole video. Then generated representations will contain multi-scale clip information, achieving implicit clip modeling. In addition, PRVR methods ignore semantic differences between text queries relevant to the same video, leading to a sparse embedding space. We propose a query diverse loss to
Authors
(none)
Tags
Stats
Related papers
- PRVR: Partially Relevant Video Retrieval (2022)2.26
- Uneven Event Modeling For Partially Relevant Video Retrieval (2025)1.40
- Mamfusion: Multi-mamba With Temporal Fusion For Partially Relevant Video Retrieval (2025)1.69
- Hlformer: Enhancing Partially Relevant Video Retrieval With Hyperbolic Learning (2025)3.50
- Ambiguity-restrained Text-video Representation Learning For Partially Relevant Video Retrieval (2025)5.84
- Prototypes Are Balanced Units For Efficient And Effective Partially Relevant Video Retrieval (2025)0.00
- Multi-modal Transformer For Video Retrieval (2020)19.47
- Mitigating Semantic Collapse In Partially Relevant Video Retrieval (2025)0.00