VRAG: Region Attention Graphs For Content-based Video Retrieval

Abstract

Content-based Video Retrieval (CBVR) is used on media-sharing platforms for applications such as video recommendation and filtering. To manage databases that scale to billions of videos, video-level approaches that use fixed-size embeddings are preferred due to their efficiency. In this paper, we introduce Video Region Attention Graph Networks (VRAG) that improves the state-of-the-art of video-level methods. We represent videos at a finer granularity via region-level features and encode video spatio-temporal dynamics through region-level relations. Our VRAG captures the relationships between regions based on their semantic content via self-attention and the permutation invariant aggregation of Graph Convolution. In addition, we show that the performance gap between video-level and frame-level methods can be reduced by segmenting videos into shots and using shot embeddings for video retrieval. We evaluate our VRAG over several video retrieval tasks and achieve a new state-of-the-art for

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyng2022vrag

Related papers

• Graph Based Temporal Aggregation For Video Retrieval (2020)0.00
• Learning Audio-guided Video Representation With Gated Attention For Video-text Retrieval (2025)5.24
• RAVU: Retrieval Augmented Video Understanding With Compositional Reasoning Over Graph (2025)0.00
• Temporal Context Aggregation For Video Retrieval With Contrastive Learning (2020)13.23
• VVS: Video-to-video Retrieval With Irrelevant Frame Suppression (2023)9.42
• Viseret: A Simple Yet Effective Approach To Moment Retrieval Via Fine-grained Video Segmentation (2021)0.00
• Fine-grained Video-text Retrieval With Hierarchical Graph Reasoning (2020)18.27
• Channel Recurrent Attention Networks For Video Pedestrian Retrieval (2020)0.00