OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark

Awesome video understanding toolkits based on PaddlePaddle. It supports video data annotation tools, lightweight RGB and skeleton based action recognition model, practical applications for video tagging and sport action detection.

A one stop shop for all of your activity recognition needs.

EPIC-KITCHENS-55 baselines for Action Recognition

Proof-of-concept for a developer-friendly system service to handle time-sensitive applications.

Code designed for MSc. Telecommunications Engineering Final Project

[ECCV 2016] Temporal Segment Networks: Towards Good Practices for Deep Action Recognition

A DRL-based scheduler for TSN

use TSN pytorch model to discern driver gesture when driving

The repository of the EnGINE framework used for reproducible large scale experiments.

p3d+tsn+attention