MissionHD: Hyperdimensional Refinement of Distribution-Deficient Reasoning Graphs for Video Anomaly Detection
This addresses a domain-specific challenge in video anomaly detection by offering a novel refinement technique for graph structures.
The paper tackles the problem of refining LLM-generated reasoning graphs for video anomaly detection, which suffer from skewed connectivity and lack of training data, by proposing a hyperdimensional computing-based method that improves performance on benchmarks.
LLM-generated reasoning graphs, referred to as mission-specific graphs (MSGs), are increasingly used for video anomaly detection (VAD) and recognition (VAR). These MSGs are novel artifacts: they often exhibit skewed connectivity and lack large-scale datasets for pre-training, which makes existing graph structure refinement (GSR) methods ineffective. To address this challenge, we propose HDC-constrained Graph Structure Refinement (HDC-GSR), a paradigm that leverages hyperdimensional computing (HDC) to optimize decodable graph representations without relying on structural-distribution learning. Building on this paradigm, we introduce MissionHD, an HDC framework that encodes graphs with constrained graph-neural operations, aligns them directly with downstream task loss, and decodes refined structures. Experiments on VAD/VAR benchmarks demonstrate that MissionHD-refined graphs consistently improve performance, establishing HDC-GSR as an effective pre-processing step for structured reasoning in video anomaly tasks.