Search Results for author:
Found 3 papers, 0 papers with code
Real-Time Detection of Events in Soccer Videosusing 3D Convolutional Neural Networks
The trade-off is a slightly lower precision compared to the current state-of-the-art, which has higher latency and performs better when a less accurate time estimation can be accepted.
Ranked #7 on
Action Spotting
on SoccerNet
DeepTEGINN: Deep Learning Based Tools to Extract Graphs from Images of Neural Networks
The goals are to simplify the training and usage of deep learning methods for computer vision and facilitate its integration into graph extraction pipelines.
Activity Recognition and Prediction in Real Homes
In this paper, we present work in progress on activity recognition and prediction in real homes using either binary sensor data or depth video data.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
