CASIA-LMC-Lab ORG

ISP-reID

Adaptive Class Suppression Loss for Long-Tail Object Detection--CVPR2021

DPT: Deformable Patch-based Transformer for Visual Recognition (ACM MM2021)

Fast Segment Anything

FastSAM is a real-time image segmentation tool that draws precise outlines around every object in a photo, reportedly 50x faster than Meta's SAM, with support for text, bounding box, point, or automatic prompts.

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

Official implementation of paper FiLo: Zero-Shot Anomaly Detection by Fine-Grained Description and High-Quality Localization (ACM MM 2024).

Obj2Seq: Formatting Objects as Sequences with Class Prompt for Visual Tasks (NeurIPS2022)

[AAAI 2024] Fluctuation-based Adaptive Structured Pruning for Large Language Models

[ECCV2022] PASS: Part-Aware Self-Supervised Pre-Training for Person Re-Identification

ZBS: Zero-shot Background Subtraction via Instance-level Background Modeling and Foreground Selection (CVPR2023)

[AAAI 2026] AnomalyMoE: Towards a Language-free Generalist Model for Unified Visual Anomaly Detection

Task Decoupled Knowledge Distillation For Lightweight Face Detectors

DCFST

No description.

[AAAI 2026] Quality-Aware Language‑Conditioned Local Auto‑Regressive Anomaly Synthesis and Detection

[IJCAI 2025] FLARE: A Framework for Stellar Flare Forecasting using Stellar Physical Properties and Historical Records