4 papers
DVPE: Divided View Position Embedding for Multi-View 3D Object Detection
Jiasen Wang, Zhenglin Li, Ke Sun +2
Sparse query-based paradigms have achieved significant success in multi-view 3D detection for autonomous vehicles. Current research faces challenges in balancing between enlarging…
Channel-Temporal Attention for First-Person Video Domain Adaptation
Xianyuan Liu, Shuo Zhou, Tao Lei +1
Unsupervised Domain Adaptation (UDA) can transfer knowledge from labeled source data to unlabeled target data of the same categories. However, UDA for first-person action recogniti…
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…