Learnable Locality-sensitive Hashing For Video Anomaly Detection

Abstract

Video anomaly detection (VAD) mainly refers to identifying anomalous events that have not occurred in the training set where only normal samples are available. Existing works usually formulate VAD as a reconstruction or prediction problem. However, the adaptability and scalability of these methods are limited. In this paper, we propose a novel distance-based VAD method to take advantage of all the available normal data efficiently and flexibly. In our method, the smaller the distance between a testing sample and normal samples, the higher the probability that the testing sample is normal. Specifically, we propose to use locality-sensitive hashing (LSH) to map samples whose similarity exceeds a certain threshold into the same bucket in advance. In this manner, the complexity of near neighbor search is cut down significantly. To make the samples that are semantically similar get closer and samples not similar get further apart, we propose a novel learnable version of LSH that embeds LSH

Stats

• citations39
• S2 citations—
• github stars0
• HF likes0
• heat score12.02
• arxiv keylu2021learnable

Related papers

• Autossvh: Exploring Automated Frame Sampling For Efficient Self-supervised Video Hashing (2025)7.92
• An Improved Video Analysis Using Context Based Extension Of LSH (2017)0.00
• 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
• Context Recovery And Knowledge Retrieval: A Novel Two-stream Framework For Video Anomaly Detection (2022)11.39
• Deep Supervised Discrete Hashing (2017)0.00
• Dual-stream Knowledge-preserving Hashing For Unsupervised Video Retrieval (2023)9.23
• SLOSH: Set Locality Sensitive Hashing Via Sliced-wasserstein Embeddings (2021)5.24