本项目分享了中山大学计算机学院本科和研究生阶段的课程资料、笔记、期末考试卷和其他实用的相关资源。希望对同学们的学习有所帮助❤️，如果喜欢记得给个star🌟

(CVPR 2023) Coreset Sampling from Open-Set for Fine-Grained Self-Supervised Learning

Code release for Your “An Erudite Fine-Grained Visual Classification Model (CVPR 2023)"

Weakly Supervised Posture Mining with Reverse Cross-entropy for Fine-grained Classification

Awesome Fine-grained Visual Classification

[TGRS2023] Official implement for PETDet.

A fast MoE impl for PyTorch

The official implementation for ICCV'23 paper "Small Object Detection via Coarse-to-fine Proposal Generation and Imitation Learning"

The official implementation of SPTS v2: Single-Point Text Spotting

Operationalize a video anomaly detection model with Azure ML

MUAAD: Manipal Anomaly Activity Detection Dataset, A dataset for multi-scene anomaly activity detection

Anomaly detection on drone footage. The final implementation is underway and is described in the readme.md file!

VadCLIP official Pytorch implementation

Official PyTorch implementation of the “A Unified Transformer Framework for Co-Segmentation, Co-Saliency Detection and Video Salient Object Detection”. (TMM2023)

Official webpage for TeD-SPAD: Temporal Distinctiveness for Self-supervised Privacy-preservation for video Anomaly Detection, accepted at ICCV '23.

Official code for "Learning Prompt-Enhanced Context features for Weakly-Supervised Video Anomlay Detection" (IEEE-TIP)

Mean-Shifted Contrastive Loss for Anomaly Detection (AAAI 2023)

[CVPR 2023] Prompt, Generate, then Cache: Cascade of Foundation Models makes Strong Few-shot Learners

Official code for "Diversity-Measurable Anomaly Detection", CVPR 2023 by Wenrui Liu, Hong Chang, Bingpeng Ma, Shiguang Shan, Xilin Chen.

Use ChatGPT to summarize the arXiv papers. 全流程加速科研，利用chatgpt进行论文全文总结+专业翻译+润色+审稿+审稿回复

[CVPR 2023] VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking

[NeurIPS 2022 Spotlight] VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training

An official implementation for "CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval"

This is the official implement of paper "ActionCLIP: A New Paradigm for Action Recognition"

本仓库将使用Pytorch框架实现经典的图像分类网络、目标检测网络、图像分割网络，图像生成网络等，并会持续更新！！！

OpenMMLab Computer Vision Foundation

这是一个yolo3-pytorch的源码，可以用于训练自己的模型。