FCOS: Fully Convolutional One-Stage Object Detection (ICCV'19)

The source code for the challenge "Small Object Detection Challenge for Spotting Birds" in International Conference on Machine Vision Applications 2023 (MVA2023)

This is the repository with the baseline code for the "Small Object Detection Challenge for Spotting Birds" at MVA2023.

A local chatbot fine-tuned by bilibili user comments.

BISHENG is an open LLM devops platform for next generation Enterprise AI applications.

Langchain-Chatchat（原Langchain-ChatGLM）基于 Langchain 与 ChatGLM, Qwen 与 Llama 等语言模型的 RAG 与 Agent 应用 | Langchain-Chatchat (formerly langchain-ChatGLM), local knowledge based LLM (like ChatGLM, Qwen and…

OpenMMLab Pose Estimation Toolbox and Benchmark.

NEW - YOLOv8 🚀 in PyTorch > ONNX > OpenVINO > CoreML > TFLite

reflective-clothes-detect-dataset、helemet detection yolov5、工作服(反光衣)检测数据集、安全帽检测、施工人员穿戴检测

Create 🔥 videos with Stable Diffusion by exploring the latent space and morphing between text prompts

Awesome multilingual OCR toolkits based on PaddlePaddle (practical ultra lightweight OCR system, support 80+ languages recognition, provide data annotation and synthesis tools, support training and…

SAFC — 元平台、弱中心 — 不只是评价导师 | Student Anti-Fraud Center - Meta & Decentralization - not just reviewing supervisor

收集“导师评价”相关资源，及原“导师评价网”存档数据

A Large-Scale Few-Shot Relation Extraction Dataset

OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched

Object Detection toolkit based on PaddlePaddle. It supports object detection, instance segmentation, multiple object tracking and real-time multi-person keypoint detection.

Base on YOLOv5 Head Person Helmet Detection on Construction Sites，基于目标检测工地安全帽和禁入危险区域识别系统，🚀😆附 YOLOv5 训练自己的数据集超详细教程🚀😆2021.3新增可视化界面❗❗

XITS - OpenType implementation of STIX fonts with math support

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

[CVPR2022 Oral] The official code for "TransRank: Self-supervised Video Representation Learning via Ranking-based Transformation Recognition"

Compressed Video Action Recognition

【AAAI'2021】MVFNet: Multi-View Fusion Network for Efficient Video Recognition

train C3D with keras for action recognition

Excitation Backprop for RNNs

Major refactor works ongoing

[ICCV 2019] TSM: Temporal Shift Module for Efficient Video Understanding

Surveillance Perspective Human Action Recognition Dataset: 7759 Videos from 14 Action Classes, aggregated from multiple sources, all cropped spatio-temporally and filmed from a surveillance-camera …

This is an official implementation for "Video Swin Transformers".