fangevo/ViT-LSTM-Foot-Contact-Detection
Official implementation of a hybrid ViT-BiLSTM framework for fine-grained foot contact detection in long jump athletics, specifically optimized for monocular, low-frame-rate video analysis.
This tool helps sports scientists, coaches, and biomechanics researchers analyze an athlete's foot contact during a long jump. You provide standard video footage (25 frames per second) of a long jump, and it outputs a detailed classification of the foot-ground interaction at each moment, from no contact to sandpit contact. It's designed for professionals who need precise insights into athletic technique.
No commits in the last 6 months.
Use this if you need to analyze the specific stages of foot contact during long jump videos captured with a regular camera, without requiring high-speed or specialized equipment.
Not ideal if you need to analyze sports other than long jump or require real-time feedback during live athletic performance.
Stars
13
Forks
—
Language
Python
License
—
Category
Last pushed
Jun 26, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/fangevo/ViT-LSTM-Foot-Contact-Detection"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
BR-IDL/PaddleViT
:robot: PaddleViT: State-of-the-art Visual Transformer and MLP Models for PaddlePaddle 2.0+
pathak22/unsupervised-video
[CVPR 2017] Unsupervised deep learning using unlabelled videos on the web
IBM/CrossViT
Official implementation of CrossViT. https://arxiv.org/abs/2103.14899
NVlabs/GCVit
[ICML 2023] Official PyTorch implementation of Global Context Vision Transformers
ViTAE-Transformer/ViTDet
Unofficial implementation for [ECCV'22] "Exploring Plain Vision Transformer Backbones for Object...