mlsanityData to 14 Oct 2026

MissionHD: Hyperdimensional Refinement of Distribution-Deficient Reasoning Graphs for Video Anomaly Detection

arXiv 2508.14746 ↗First posted 20 Aug 2025cs.LGcited by 0

On the map: LLM reasoning → Chain-of-thought reasoning for driving

Abstract (arXiv)

LLM-generated reasoning graphs, referred to as mission-specific graphs (MSGs), are increasingly used for video anomaly detection (VAD) and recognition (VAR). However, they are typically treated as fixed despite being generic and distribution-deficient. Conventional graph structure refinement (GSR) methods are ill-suited to this setting, as they rely on learning structural distributions that are absent in LLM-generated graphs. We propose HDC-constrained Graph Structure Refinement (HDC-GSR), a new paradigm that directly optimizes a decodable, task-aligned graph representation in a single hyperdimensional space without distribution modeling. Leveraging Hyperdimensional Computing (HDC), our framework encodes graphs via binding and bundling operations, aligns the resulting graph code with downstream loss, and decodes edge contributions to refine the structure. We instantiate this approach as MissionHD for weakly supervised VAD/VAR and demonstrate consistent performance gains on benchmark datasets.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Chain-of-thought reasoning for driving, one of 17 directions in LLM reasoning. Builds on 25 of its 30 references that are in the map. First posted on arXiv 20 Aug 2025.

Builds on

25 of 30 references.

References · 25

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2017Graph Attention Networkscited by 8,923
  3. 2023ImageBind: One Embedding Space To Bind Them Allcited by 1,175
  4. 2018Real-world Anomaly Detection in Surveillance Videoscited by 577
  5. 2017Scene Graph Generation by Iterative Message Passingcited by 462
  6. 2023Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoningcited by 328
  7. 2020Not only Look, but also Listen: Learning Multimodal Violence Detection under Weak Supervisioncited by 238
  8. 2021Weakly-supervised Video Anomaly Detection with Robust Temporal Feature Magnitude Learningcited by 230
  9. 2019Graph Convolutional Label Noise Cleaner: Train a Plug-and-play Action Classifier for Anomaly Detectioncited by 171
  10. 2021A Survey on Hyperdimensional Computing aka Vector Symbolic Architectures, Part I: Models and Data Transformationscited by 99
  11. 2023Unbiased Multiple Instance Learning for Weakly Supervised Video Anomaly Detectioncited by 64
  12. 2024Text Prompt with Normality Guidance for Weakly Supervised Video Anomaly Detectioncited by 49
13 more
  1. 2020A Theoretical Perspective on Hyperdimensional Computingcited by 43
  2. 2024A Vision Check-up for Language Modelscited by 36
  3. 2023Delving into CLIP latent space for Video Anomaly Recognitioncited by 27
  4. 2022VQA-GNN: Reasoning with Multimodal Knowledge via Graph Neural Networks for Visual Question Answeringcited by 22
  5. 2024STEP: Enhancing Video-LLMs' Compositional Reasoning by Spatio-Temporal Graph-guided Self-Trainingcited by 22
  6. 2022Self-Supervised Graph Structure Refinement for Graph Neural Networkscited by 20
  7. 2025Building a Mind Palace: Structuring Environment-Grounded Semantic Graphs for Effective Long Video Analysis with LLMscited by 19
  8. 2024GraphOTTER: Evolving LLM-based Graph Reasoning for Complex Table Question Answeringcited by 18
  9. 2024MissionGNN: Hierarchical Multimodal GNN-based Weakly Supervised Video Anomaly Recognition with Mission-Specific Knowledge Graph Generationcited by 14
  10. 2024Hyperdimensional Representation Learning for Node Classification and Link Predictioncited by 5
  11. 2024PV-VTT: A Privacy-Centric Dataset for Mission-Specific Anomaly Detection and Natural Language Interpretationcited by 4
  12. 2024HDReason: Algorithm-Hardware Codesign for Hyperdimensional Knowledge Graph Reasoningcited by 3
  13. 2024Graph Structure Refinement with Energy-based Contrastive Learningcited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Geometry-Aware Semantic Reasoning for Training Free Video Anomaly Detection
  2. 2026SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere
  3. 2026Hypergraph Normal World Models for Logical Visual Anomaly Detection
  4. 2025VADTree: Explainable Training-Free Video Anomaly Detection via Hierarchical Granularity-Aware Tree
  5. 2026Representation--Behavior Alignment for Explainable Weakly-Supervised Video Anomaly Detection
  6. 2026H2VLR: Heterogeneous Hypergraph Vision-Language Reasoning for Few-Shot Anomaly Detection
  7. 2026Reasoning-Guided Grounding: Elevating Video Anomaly Detection through Multimodal Large Language Models
  8. 2026Cog-VADU: A Training-Free Cognitive Reasoning Framework for Video Anomaly Detection and Understanding