The repository for IEEE CVPR 2023 (A Light Weight Model for Active Speaker Detection)

[MM24 Oral] Identity-Driven Multimedia Forgery Detection via Reference Assistance

Code for the TASLP paper "PSLA: Improving Audio Tagging With Pretraining, Sampling, Labeling, and Aggregation".

Compact Bilinear Pooling for PyTorch

[ICCV 2021] Continual Learning for Image-Based Camera Localization.

This is the Pytorch implementation of LwF

Official PyTorch implementation of "Multi-Head Distillation for Continual Unsupervised Domain Adaptation in Semantic Segmentation"

Multi-level Online Sequential Experts (MOSE) for online continual learning problem. (CVPR2024)

Continual Learning Method RAWM for ICML 2023

Relevant papers in Continual Learning

[ACM MM'23] UMMAFormer: A Universal Multimodal-adaptive Transformer Framework For Temporal Forgery Localization

Continual Learning Method RWM for AAAI 2024

The official repository for the ICASSP paper, "Hearing and Seeing Abnormality: Self-Supervised Audio-Visual Mutual Learning for Deepfake Detection"."

The repo host the code and model of MAViL.

Paper list and datasets for industrial image anomaly/defect detection (updating). 工业异常/瑕疵检测论文及数据集检索库(持续更新)。

Implementation of Generating Diverse High-Fidelity Images with VQ-VAE-2 in PyTorch

A Multi-Task Evaluation Benchmark for Audio-Visual Representation Models (ICASSP 2024)

Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"

A curated list of awesome anomaly detection resources

NOMAD is a fully unsupervised non-matching reference audio quality metric

Official code for Leveraging Real Talking Faces via Self-Supervision for Robust Forgery Detection (CVPR 2022)

[ACM MM] AV-Deepfake1M: A Large-Scale LLM-Driven Audio-Visual Deepfake Dataset

Code for Cross-Modality and Within-Modality Regularization for Audio-Visual DeepFake Detection

Official PyTorch implementation of TATS: A Long Video Generation Framework with Time-Agnostic VQGAN and Time-Sensitive Transformer (ECCV 2022)

Awesome Incremental Learning

Recurrent Video Restoration Transformer with Guided Deformable Attention (NeurlPS2022, official repository)

为GPT/GLM等LLM大语言模型提供实用化交互接口，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, m…

[ICLR 2024] Efficient Streaming Language Models with Attention Sinks