The open source initiative for anonymized, elite-level athletic motion capture data. Run by Driveline Baseball.
-
Updated
Dec 4, 2024 - Jupyter Notebook
The open source initiative for anonymized, elite-level athletic motion capture data. Run by Driveline Baseball.
Code for : [Pattern Recognit. Lett. 2021] "Learn to cycle: Time-consistent feature discovery for action recognition" and [IJCNN 2021] "Multi-Temporal Convolutions for Human Action Recognition in Videos".
This repository contains the code implementation used in the paper Temporally Coherent Embeddings for Self-Supervised Video Representation Learning (TCE).
I3D implemetation in Keras + video preprocessing + visualization of results
[AAAI 2023 (Oral)] CrissCross: Self-Supervised Audio-Visual Representation Learning with Relaxed Cross-Modal Synchronicity
Python script for downloading Kinetics datasets (Kinetics400, Kinetics600, Kinetics700)
Code for VideoSSL: Semi-Supervised Learning for Video Classification.
simple pytorch pipeline for pretraining/finetuning vision models on kinetics-400
Add a description, image, and links to the kinetics-datasets topic page so that developers can more easily learn about it.
To associate your repository with the kinetics-datasets topic, visit your repo's landing page and select "manage topics."