Open R1 Video-MLLM Version

[under review] Advancing Pre-trained Teacher: Towards Robust Feature Discrepancy for Anomaly Detection

Solve Visual Understanding with Reinforced VLMs

Train transformer language models with reinforcement learning.

ReAgent: Point Cloud Registration using Imitation and Reinforcement Learning

[INFFUS 2025] CoreNet: Conflict Resolution Network for point-pixel misalignment and sub-task suppression of 3D LiDAR-camera object detection

[2nd Place of CVPR 2024 VAND2.0 Challenge] Generalized Normality Learning for Robust Anomaly Detection

[AAAI 2025] RCTrans: Radar-Camera Transformer via Radar Densiffer and Sequential Decoder for 3D Object Detection

SlowFast-LLaVA: A Strong Training-Free Baseline for Video Large Language Models

[ECCV 2024] Official Implementation and Dataset Release for <A Unified Anomaly Synthesis Strategy with Gradient Ascent for Industrial Anomaly Detection and Localization>

official implementation for Language Supervised Training for Skeleton-based Action Recognition

[ECCV 2024] This repository represents the official implementation of PARE-Net: Position-Aware Rotation-Equivariant Networks for Robust Point Cloud Registration

An Attribute-based Method for Video Anomaly Detection (TMLR 2025)

A curated paper list of awesome skeleton-based action recognition.

A large scale video database for violence detection, which has 2,000 video clips containing violent or non-violent behaviours.

VadCLIP official Pytorch implementation

Normalizing Flows for Human Pose Anomaly Detection [ICCV 2023]

Official code for the paper "PNI : Industrial Anomaly Detection using Position and Neighborhood Information"

TF-CLIP: Learning Text-Free CLIP for Video-Based Person Re-identification (AAAI2024)

[ICLR2023] PLOT: Prompt Learning with Optimal Transport for Vision-Language Models

[CVPR 2023] Official repository of paper titled "MaPLe: Multi-modal Prompt Learning".

[ICCV 2023, Oral] Iterative Prompt Learning for Unsupervised Backlit Image Enhancement

Inpaint anything using Segment Anything and inpainting models.

[CVPR 2023 Workshop] VAND Challenge: 1st Place on Zero-shot AD and 4th Place on Few-shot AD

Accurate reimplementation of WinCLIP (pytorch version)

[CVPR 2023] Unofficial re-implementation of "WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation".

[AAAI 2024 Oral] AnomalyGPT: Detecting Industrial Anomalies Using Large Vision-Language Models

(CVPR 2023) Revisiting Reverse Distillation for Anomaly Detection