Search Results for author:
Found 3 papers, 0 papers with code
Evaluating Transformers for Lightweight Action Recognition
Our experiments conclude that current video transformers are not yet capable of lightweight action recognition on par with traditional convolutional baselines, and that the previously mentioned shortcomings need to be addressed to bridge this gap.
VideoLightFormer: Lightweight Action Recognition using Transformers
Efficient video action recognition remains a challenging problem.
Team PyKale (xy9) Submission to the EPIC-Kitchens 2021 Unsupervised Domain Adaptation Challenge for Action Recognition
Under the team name xy9, our submission achieved 5th place in terms of top-1 accuracy for verb class and all top-5 accuracies.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
