This repository is intended to host tools and demos for ActivityNet

Pre-trained and Reproduced Deep Learning Models （『飞桨』官方模型库，包含多种学术前沿和工业场景验证的深度学习模型）

Revisiting Anchor Mechanisms for Temporal Action Localization (TIP 2020)

PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.

Temporal Relation Networks

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

3D ResNets for Action Recognition (CVPR 2018)

PyTorch implementation of SENet

Code & Models for Temporal Segment Networks (TSN) in ECCV 2016

Fast, modular reference implementation of Instance Segmentation and Object Detection algorithms in PyTorch.

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

Code for "Single Shot Temporal Action Detection"

Open MMLab Detection Toolbox and Benchmark

pytorch version of pseudo-3d-residual-networks(P-3D), pretrained model is supported

A repository of common methods, datasets, and tasks for video research

NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection.

Object detection, 3D detection, and pose estimation using center point detection:

Most popular metrics used to evaluate object detection algorithms.

mutil-class focal loss implemented in keras

Codes for our paper "CenterNet: Keypoint Triplets for Object Detection" .

Timeception for Complex Action Recognition, CVPR 2019 (Oral Presentation)

Simple Online Realtime Tracking with a Deep Association Metric

cvpr2019 papers，极市团队整理

Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow

Improve yolo with latest paper

[CVPR2019] Fast Online Object Tracking and Segmentation: A Unifying Approach

Use the Mask RCNN for the human pose estimation