Imagen de Portada

Steering and Rectifying Latent Representation Manifolds in Frozen Multi-modal LLMs for Video Anomaly Detection

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Cai, Zhaolin, Li, Fan, Duan, Huiyu, He, Lijun, Zhai, Guangtao
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Generative Human-Object Interaction Detection via Differentiable Cognitive Steering of Multi-modal LLMs
por: Cai, Zhaolin, et al.
Publicado: (2025)

HeadHunt-VAD: Hunting Robust Anomaly-Sensitive Heads in MLLM for Tuning-Free Video Anomaly Detection
por: Cai, Zhaolin, et al.
Publicado: (2025)

MMHead: Towards Fine-grained Multi-modal 3D Facial Animation
por: Wu, Sijing, et al.
Publicado: (2024)

HiProbe-VAD: Video Anomaly Detection via Hidden States Probing in Tuning-Free Multimodal LLMs
por: Cai, Zhaolin, et al.
Publicado: (2025)

ManipShield: A Unified Framework for Image Manipulation Detection, Localization and Explanation
por: Xu, Zitong, et al.
Publicado: (2025)

AIGV-Assessor: Benchmarking and Evaluating the Perceptual Quality of Text-to-Video Generation with LMM
por: Wang, Jiarui, et al.
Publicado: (2024)

TDVE-Assessor: Benchmarking and Evaluating the Quality of Text-Driven Video Editing with LMMs
por: Wang, Juntong, et al.
Publicado: (2025)

MVBIND: Self-Supervised Music Recommendation For Videos Via Embedding Space Binding
por: Teng, Jiajie, et al.
Publicado: (2024)

How is Visual Attention Influenced by Text Guidance? Database and Model
por: Sun, Yinan, et al.
Publicado: (2024)

Quality Assessment for AI Generated Images with Instruction Tuning
por: Wang, Jiarui, et al.
Publicado: (2024)

Facial Attractiveness Prediction in Live Streaming: A New Benchmark and Multi-modal Method
por: Li, Hui, et al.
Publicado: (2025)

DPC-VQA: Decoupling Quality Perception and Residual Calibration for Video Quality Assessment
por: Li, Xinyue, et al.
Publicado: (2026)

Perceptual Video Quality Assessment: A Survey
por: Min, Xiongkuo, et al.
Publicado: (2024)

FVQ: A Large-Scale Dataset and an LMM-based Method for Face Video Quality Assessment
por: Wu, Sijing, et al.
Publicado: (2025)

On Learning Multi-Modal Forgery Representation for Diffusion Generated Video Detection
por: Song, Xiufeng, et al.
Publicado: (2024)

VideoAesBench: Benchmarking the Video Aesthetics Perception Capabilities of Large Multimodal Models
por: Li, Yunhao, et al.
Publicado: (2026)

UniProcessor: A Text-induced Unified Low-level Image Processor
por: Duan, Huiyu, et al.
Publicado: (2024)

VTONQA: A Multi-Dimensional Quality Assessment Dataset for Virtual Try-on
por: Wei, Xinyi, et al.
Publicado: (2026)

DHQA-4D: Perceptual Quality Assessment of Dynamic 4D Digital Human
por: Li, Yunhao, et al.
Publicado: (2025)

Exploring Instruction Data Quality for Explainable Image Quality Assessment
por: Li, Yunhao, et al.
Publicado: (2025)

DynT2I-Eval: A Dynamic Evaluation Framework for Text-to-Image Models
por: Wang, Juntong, et al.
Publicado: (2026)

Multi-Dimensional Quality Assessment for Text-to-3D Assets: Dataset and Model
por: Fu, Kang, et al.
Publicado: (2025)

ESVQA: Perceptual Quality Assessment of Egocentric Spatial Videos
por: Zhu, Xilei, et al.
Publicado: (2024)

EEmo-Logic: A Unified Dataset and Multi-Stage Framework for Comprehensive Image-Evoked Emotion Assessment
por: Gao, Lancheng, et al.
Publicado: (2026)

How Does Audio Influence Visual Attention in Omnidirectional Videos? Database and Model
por: Zhu, Yuxin, et al.
Publicado: (2024)

RGC-VQA: An Exploration Database for Robotic-Generated Video Quality Assessment
por: Jin, Jianing, et al.
Publicado: (2025)

ReasonEdit: Towards Interpretable Image Editing Evaluation via Reinforcement Learning
por: Chen, Honghua, et al.
Publicado: (2026)

LMM4LMM: Benchmarking and Evaluating Large-multimodal Image Generation with LMMs
por: Wang, Jiarui, et al.
Publicado: (2025)

TIT-Score: Evaluating Long-Prompt Based Text-to-Image Alignment via Text-to-Image-to-Text Consistency
por: Wang, Juntong, et al.
Publicado: (2025)

I2I-Bench: A Comprehensive Benchmark Suite for Image-to-Image Editing Models
por: Wang, Juntong, et al.
Publicado: (2025)

Robust Mesh Saliency Ground Truth Acquisition in VR via View Cone Sampling and Manifold Diffusion
por: Zheng, Guoquan, et al.
Publicado: (2026)

ResAD++: Towards Class Agnostic Anomaly Detection via Residual Feature Learning
por: Yao, Xincheng, et al.
Publicado: (2025)

Multi-modal Instruction Tuned LLMs with Fine-grained Visual Perception
por: He, Junwen, et al.
Publicado: (2024)

GMFVAD: Using Grained Multi-modal Feature to Improve Video Anomaly Detection
por: Dai, Guangyu, et al.
Publicado: (2025)

Preference-Guided Debiasing for No-Reference Enhancement Image Quality Assessment
por: Gao, Shiqi, et al.
Publicado: (2026)

LOVE: Benchmarking and Evaluating Text-to-Video Generation and Video-to-Text Interpretation
por: Wang, Jiarui, et al.
Publicado: (2025)

ESIQA: Perceptual Quality Assessment of Vision-Pro-based Egocentric Spatial Images
por: Zhu, Xilei, et al.
Publicado: (2024)

Q-Bench-Portrait: Benchmarking Multimodal Large Language Models on Portrait Image Quality Perception
por: Wu, Sijing, et al.
Publicado: (2026)

Holmes-VAD: Towards Unbiased and Explainable Video Anomaly Detection via Multi-modal LLM
por: Zhang, Huaxin, et al.
Publicado: (2024)

Q-Bench+: A Benchmark for Multi-modal Foundation Models on Low-level Vision from Single Images to Pairs
por: Zhang, Zicheng, et al.
Publicado: (2024)