Cover Image

Sparse Reasoning is Enough: Biological-Inspired Framework for Video Anomaly Detection with Large Pre-trained Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Huang, He, Hu, Zixuan, Li, Dongxiao, Xiao, Yao, Duan, Ling-Yu
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Adaptive Dual Uncertainty Optimization: Boosting Monocular 3D Object Detection under Test-Time Shifts
by: Hu, Zixuan, et al.
Published: (2025)

Follow the Rules: Reasoning for Video Anomaly Detection with Large Language Models
by: Yang, Yuchen, et al.
Published: (2024)

SEVA: Leveraging Single-Step Ensemble of Vicinal Augmentations for Test-Time Adaptation
by: Hu, Zixuan, et al.
Published: (2025)

CL-BioGAN: Biologically-Inspired Cross-Domain Continual Learning for Hyperspectral Anomaly Detection
by: Wang, Jianing, et al.
Published: (2025)

Fractals as Pre-training Datasets for Anomaly Detection and Localization
by: Ugwu, C. I., et al.
Published: (2024)

Weakly Supervised Video Anomaly Detection with Anomaly-Connected Components and Intention Reasoning
by: Wang, Yu, et al.
Published: (2026)

Revealing Latent Information: A Physics-inspired Self-supervised Pre-training Framework for Noisy and Sparse Events
by: Zhu, Lin, et al.
Published: (2025)

A Reinforcement Learning-Based Automatic Video Editing Method Using Pre-trained Vision-Language Model
by: Hu, Panwen, et al.
Published: (2024)

BIAS: A Biologically Inspired Algorithm for Video Saliency Detection
by: Zhang, Zhao-ji, et al.
Published: (2026)

One Language-Free Foundation Model Is Enough for Universal Vision Anomaly Detection
by: Gao, Bin-Bin, et al.
Published: (2026)

Efficient Vision-Language Pre-training by Cluster Masking
by: Wei, Zihao, et al.
Published: (2024)

Patch is Enough: Naturalistic Adversarial Patch against Vision-Language Pre-training Models
by: Kong, Dehong, et al.
Published: (2024)

Advancing Pre-trained Teacher: Towards Robust Feature Discrepancy for Anomaly Detection
by: Tang, Canhui, et al.
Published: (2024)

One Perturbation is Enough: On Generating Universal Adversarial Perturbations against Vision-Language Pre-training Models
by: Fang, Hao, et al.
Published: (2024)

The Evolution of Video Anomaly Detection: A Unified Framework from DNN to MLLM
by: Gao, Shibo, et al.
Published: (2025)

VADMamba: Exploring State Space Models for Fast Video Anomaly Detection
by: Lyu, Jiahao, et al.
Published: (2025)

A Multimodal Pre-trained Network for Integrated EEG-Video Seizure Detection
by: Lu, Tong, et al.
Published: (2026)

Video Anomaly Detection and Explanation via Large Language Models
by: Lv, Hui, et al.
Published: (2024)

Large-scale Pre-training for Grounded Video Caption Generation
by: Kazakos, Evangelos, et al.
Published: (2025)

Anomaly Detection by Adapting a pre-trained Vision Language Model
by: Cai, Yuxuan, et al.
Published: (2024)

LEAD: Exploring Logit Space Evolution for Model Selection
by: Hu, Zixuan, et al.
Published: (2025)

Low-hallucination Synthetic Captions for Large-Scale Vision-Language Model Pre-training
by: Zhang, Xinsong, et al.
Published: (2025)

Training-free Video Temporal Grounding using Large-scale Pre-trained Models
by: Zheng, Minghang, et al.
Published: (2024)

BridgeNet: A Unified Multimodal Framework for Bridging 2D and 3D Industrial Anomaly Detection
by: Xiang, An, et al.
Published: (2025)

Towards Video Anomaly Retrieval from Video Anomaly Detection: New Benchmarks and Model
by: Wu, Peng, et al.
Published: (2023)

Steering and Rectifying Latent Representation Manifolds in Frozen Multi-modal LLMs for Video Anomaly Detection
by: Cai, Zhaolin, et al.
Published: (2026)

Harnessing Large Language Models for Training-free Video Anomaly Detection
by: Zanella, Luca, et al.
Published: (2024)

Beyond Entropy: Region Confidence Proxy for Wild Test-Time Adaptation
by: Hu, Zixuan, et al.
Published: (2025)

Respecting Modality Gap in Post-hoc Out-of-distribution Detection with Pre-trained Vision-Language Models
by: Hu, Yuanwei, et al.
Published: (2026)

Foundation Model for Endoscopy Video Analysis via Large-scale Self-supervised Pre-train
by: Wang, Zhao, et al.
Published: (2023)

Turning Adaptation into Assets: Cross-Domain Bridging for Online Vision-Language Navigation
by: Hu, Zixuan, et al.
Published: (2026)

Repurposing Pre-trained Video Diffusion Models for Event-based Video Interpolation
by: Chen, Jingxi, et al.
Published: (2024)

Cyclic Sparse Training: Is it Enough?
by: Gadhikar, Advait, et al.
Published: (2024)

Reasoning-Guided Grounding: Elevating Video Anomaly Detection through Multimodal Large Language Models
by: Agarwal, Sakshi, et al.
Published: (2026)

Temporal-Consistent Video Restoration with Pre-trained Diffusion Models
by: Wang, Hengkang, et al.
Published: (2025)

Knowing the Answer Isn't Enough: Fixing Reasoning Path Failures in LVLMs
by: Wang, Chaoyang, et al.
Published: (2025)

One Prompt Word is Enough to Boost Adversarial Robustness for Pre-trained Vision-Language Models
by: Li, Lin, et al.
Published: (2024)

VISA: Reasoning Video Object Segmentation via Large Language Models
by: Yan, Cilin, et al.
Published: (2024)

EndoMamba: An Efficient Foundation Model for Endoscopic Videos via Hierarchical Pre-training
by: Tian, Qingyao, et al.
Published: (2025)

H2VLR: Heterogeneous Hypergraph Vision-Language Reasoning for Few-Shot Anomaly Detection
by: Huang, Jianghong, et al.
Published: (2026)