Stars
The code "A Dual-Level Cancelable Framework for Palmprint Verification and Hack-Proof Data Storage" (Accepted by TIFS)
🔥 🔥 🔥 [NeurIPS 2024] Official Implementation of Hawk: Learning to Understand Open-World Video Anomalies
Official implementation of "Harnessing Large Language Models for Training-free Video Anomaly Detection", CVPR 2024
🔥[ICML 2024, Official Code] First work to propose a solution to the long-tail problem in IAA. 首篇针对IAA中的长尾问题提出解决方案的工作
🔥[NIPS 2024, Official Code] for paper "Rethinking No-reference Image Exposure Assessment from Holism to Pixel: Models, Datasets and Benchmarks". Official Weights and Demos provided. 首个像素级曝光评估数据集、算法…
Code of ”Comprehensive Competition Mechanism in Palmprint Recognition“ (Accepted by IEEE TIFS)
[ICLR 2025] MMFakeBench: A Mixed-Source Multimodal Misinformation Detection Benchmark for LVLMs
A Survey on Jailbreak Attacks and Defenses against Multimodal Generative Models
[ACM MM 2024] FKA-Owl: Advancing Multimodal Fake News Detection through Knowledge-Augmented LVLMs
Code and datasets of PR 2024 paper《AdvCloak: Customized Adversarial Cloak for Privacy Protection》
Official project page of the paper "Towards Surveillance Video-and-Language Understanding: New Dataset, Baselines, and Challenges" (Accepted by CVPR 2024)
A comprehensive summary of deep face restoration methods.
[TLLM'23] PandaGPT: One Model To Instruction-Follow Them All
Can I Trust Your Answer? Visually Grounded Video Question Answering (CVPR'24, Highlight)
Fast and memory-efficient exact attention
Official implementation of the ICCV2023 paper: Enhancing Generalization of Universal Adversarial Perturbation through Gradient Aggregation
Tool Learning for Big Models, Open-Source Solutions of ChatGPT-Plugins
LAVIS - A One-stop Library for Language-Vision Intelligence
Codes for VPGTrans: Transfer Visual Prompt Generator across LLMs. VL-LLaMA, VL-Vicuna.