CHAIN: Exploring Global-local Spatio-temporal Information For Improved Self-supervised Video Hashing
2023 · Rukai Wei, Yu Liu, Jingkuan Song, et al.
Abstract
Compressing videos into binary codes can improve retrieval speed and reduce storage overhead. However, learning accurate hash codes for video retrieval can be challenging due to high local redundancy and complex global dependencies between video frames, especially in the absence of labels. Existing self-supervised video hashing methods have been effective in designing expressive temporal encoders, but have not fully utilized the temporal dynamics and spatial appearance of videos due to less challenging and unreliable learning tasks. To address these challenges, we begin by utilizing the contrastive learning task to capture global spatio-temporal information of videos for hashing. With the aid of our designed augmentation strategies, which focus on spatial and temporal variations to create positive pairs, the learning framework can generate hash codes that are invariant to motion, scale, and viewpoint. Furthermore, we incorporate two collaborative learning tasks, i.e., frame order verif
Authors
(none)
Tags
Stats
Related papers
- Self-supervised Video Hashing With Hierarchical Binary Auto-encoder (2018)17.81
- Dual-stream Knowledge-preserving Hashing For Unsupervised Video Retrieval (2023)9.23
- Autossvh: Exploring Automated Frame Sampling For Efficient Self-supervised Video Hashing (2025)7.92
- Encode The Unseen: Predictive Video Hashing For Scalable Mid-stream Retrieval (2020)3.58
- Deep Supervised Discrete Hashing (2017)0.00
- Simultaneous Feature Aggregating And Hashing For Compact Binary Code Learning (2019)9.92
- Deep Heterogeneous Hashing For Face Video Retrieval (2019)9.92
- Hashing In The Zero Shot Framework With Domain Adaptation (2017)10.21