Autossvh: Exploring Automated Frame Sampling For Efficient Self-supervised Video Hashing

Abstract

Self-Supervised Video Hashing (SSVH) compresses videos into hash codes for efficient indexing and retrieval using unlabeled training videos. Existing approaches rely on random frame sampling to learn video features and treat all frames equally. This results in suboptimal hash codes, as it ignores frame-specific information density and reconstruction difficulty. To address this limitation, we propose a new framework, termed AutoSSVH, that employs adversarial frame sampling with hash-based contrastive learning. Our adversarial sampling strategy automatically identifies and selects challenging frames with richer information for reconstruction, enhancing encoding capability. Additionally, we introduce a hash component voting strategy and a point-to-set (P2Set) hash-based contrastive objective, which help capture complex inter-video semantic relationships in the Hamming space and improve the discriminability of learned hash codes. Extensive experiments demonstrate that AutoSSVH achieves sup

Stats

• citations5
• S2 citations—
• github stars10
• HF likes0
• heat score7.92
• arxiv keylian2025autossvh

Related papers

• Self-supervised Video Hashing With Hierarchical Binary Auto-encoder (2018)17.81
• CHAIN: Exploring Global-local Spatio-temporal Information For Improved Self-supervised Video Hashing (2023)8.60
• Dual-stream Knowledge-preserving Hashing For Unsupervised Video Retrieval (2023)9.23
• Self-supervised Bernoulli Autoencoders For Semi-supervised Hashing (2020)3.66
• Unsupervised Deep Hashing For Large-scale Visual Search (2016)9.59
• Encode The Unseen: Predictive Video Hashing For Scalable Mid-stream Retrieval (2020)3.58
• Deep Supervised Discrete Hashing (2017)0.00
• Learnable Locality-sensitive Hashing For Video Anomaly Detection (2021)12.02