3 citations · 5 across the 4 of their papers we have counts for
4 papers
Evaluating Transformers for Lightweight Action Recognition
Raivo Koot, Markus Hennerbichler, Haiping Lu
In video action recognition, transformers consistently reach state-of-the-art accuracy. However, many models are too heavyweight for the average researcher with limited hardware re…
VideoLightFormer: Lightweight Action Recognition using Transformers
Raivo Koot, Haiping Lu
Efficient video action recognition remains a challenging problem. One large model after another takes the place of the state-of-the-art on the Kinetics dataset, but real-world effi…
PyKale: Knowledge-Aware Machine Learning from Multiple Sources in Python
Haiping Lu, Xianyuan Liu, Robert Turner +5
Machine learning is a general-purpose technology holding promises for many interdisciplinary research problems. However, significant barriers exist in crossing disciplinary boundar…
Team PyKale (xy9) Submission to the EPIC-Kitchens 2021 Unsupervised Domain Adaptation Challenge for Action Recognition
Xianyuan Liu, Raivo Koot, Shuo Zhou +2
This report describes the technical details of our submission to the EPIC-Kitchens 2021 Unsupervised Domain Adaptation Challenge for Action Recognition. The EPIC-Kitchens dataset i…