VVS: Video-to-video Retrieval With Irrelevant Frame Suppression
2023 · Won Jo, Geuntaek Lim, Gwangjin Lee, et al.
Abstract
In content-based video retrieval (CBVR), dealing with large-scale collections, efficiency is as important as accuracy; thus, several video-level feature-based studies have actively been conducted. Nevertheless, owing to the severe difficulty of embedding a lengthy and untrimmed video into a single feature, these studies have been insufficient for accurate retrieval compared to frame-level feature-based studies. In this paper, we show that appropriate suppression of irrelevant frames can provide insight into the current obstacles of the video-level approaches. Furthermore, we propose a Video-to-Video Suppression network (VVS) as a solution. VVS is an end-to-end framework that consists of an easy distractor elimination stage to identify which frames to remove and a suppression weight generation stage to determine the extent to suppress the remaining frames. This structure is intended to effectively describe an untrimmed video with varying content and meaningless information. Its efficacy
Authors
(none)
Tags
Stats
Related papers
- Efficient Cross-modal Video Retrieval With Meta-optimized Frames (2022)7.16
- PRVR: Partially Relevant Video Retrieval (2022)2.26
- VRAG: Region Attention Graphs For Content-based Video Retrieval (2022)0.00
- Self-supervised Video Retrieval Transformer Network (2021)0.00
- Vision-language Models Learn Super Images For Efficient Partially Relevant Video Retrieval (2023)3.58
- Delving Deeper: Hierarchical Visual Perception For Robust Video-text Retrieval (2026)1.24
- Differentiable Resolution Compression And Alignment For Efficient Video Classification And Retrieval (2023)5.27
- HVD: Human Vision-driven Video Representation Learning For Text-video Retrieval (2026)0.00