REVIEW 7 cited by
Video Anomaly Detection and Explanation via Large Language Models
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Video Anomaly Detection (VAD) aims to localize abnormal events on the timeline of long-range surveillance videos. Anomaly-scoring-based methods have been prevailing for years but suffer from the high complexity of thresholding and low explanability of detection results. In this paper, we conduct pioneer research on equipping video-based large language models (VLLMs) in the framework of VAD, making the VAD model free from thresholds and able to explain the reasons for the detected anomalies. We introduce a novel network module Long-Term Context (LTC) to mitigate the incapability of VLLMs in long-range context modeling. We design a three-phase training method to improve the efficiency of fine-tuning VLLMs by substantially minimizing the requirements for VAD data and lowering the costs of annotating instruction-tuning data. Our trained model achieves the top performance on the anomaly videos of the UCF-Crime and TAD benchmarks, with the AUC improvements of +3.86\% and +4.96\%, respectively. More impressively, our approach can provide textual explanations for detected anomalies.
Forward citations
Cited by 7 Pith papers
-
SmartHome-Bench: A Comprehensive Benchmark for Video Anomaly Detection in Smart Homes Using Multi-Modal Large Language Models
A new smart-home video anomaly benchmark and a taxonomy-driven reflective LLM chain that improves MLLM anomaly detection accuracy by 11.62 percentage points over zero-shot prompting.
-
Period-LLM: Extending the Periodic Capability of Multimodal Large Language Model
Period-LLM improves multimodal LLM performance on periodic tasks such as repetition counting and heart-rate estimation via easy-to-hard curriculum training and a channel-gradient weighting strategy.
-
VAU-R1: Advancing Video Anomaly Understanding via Reinforcement Fine-Tuning
VAU-R1 uses Group Relative Policy Optimization with accuracy, format, and temporal-IoU rewards to improve video anomaly reasoning on a new LLM-generated benchmark, VAU-Bench.
-
Vad-R1: Towards Video Anomaly Reasoning via Perception-to-Cognition Chain-of-Thought
A two-stage trained MLLM with a perception-to-cognition chain-of-thought and a self-verification RL reward outperforms prior models on video anomaly detection and reasoning.
-
Spatiotemporal Semantic V2X Framework for Cooperative Collision Prediction
A V2X system that sends V-JEPA embeddings instead of video can predict collisions with 92% accuracy at ~10^5 lower bandwidth in simulation, but lacks a held-out evaluation.
-
VAGU & GtS: LLM-Based Benchmark and Framework for Joint Video Anomaly Grounding and Understanding
A new benchmark, a training-free framework, and a joint metric for video anomaly detection that combines temporal grounding with semantic understanding.
-
The Evolution of Video Anomaly Detection: A Unified Framework from DNN to MLLM
The paper organizes VAD methods into a five-dimension framework spanning task objective, modality, input, architecture, and optimization, with emphasis on MLLM/LLM-era work.
Discussion (0). Sign in to comment.