Understanding human actions in visual data is tied to advances in complementary research areas including object recognition, human dynamics, domain adaptation and semantic …
G Wilson, DJ Cook - ACM Transactions on Intelligent Systems and …, 2020 - dl.acm.org
Deep learning has produced state-of-the-art results for a variety of tasks. While such approaches for supervised learning have performed well, they assume that training and …
S Zhao, G Wang, S Zhang, Y Gu, Y Li, Z Song… - Proceedings of the AAAI …, 2020 - aaai.org
Deep neural networks suffer from performance decay when there is domain shift between the labeled source domain and unlabeled target domain, which motivates the research on …
The performance of a classifier trained on data coming from a specific domain typically degrades when applied to a related but different one. While annotating many samples from …
J Li, M Jing, K Lu, L Zhu… - IEEE Transactions on …, 2019 - ieeexplore.ieee.org
Domain adaptation aims to leverage knowledge from a well-labeled source domain to a poorly labeled target domain. A majority of existing works transfer the knowledge at either …
C Chen, Z Chen, B Jiang, X Jin - Proceedings of the AAAI conference on …, 2019 - aaai.org
Recently, considerable effort has been devoted to deep domain adaptation in computer vision and machine learning communities. However, most of existing work only concentrates …
J Li, K Lu, Z Huang, L Zhu… - IEEE transactions on …, 2018 - ieeexplore.ieee.org
Currently, unsupervised heterogeneous domain adaptation in a generalized setting, which is the most common scenario in real-world applications, is under insufficient exploration …
Transfer learning has been demonstrated to be effective for many real-world applications as it exploits knowledge present in labeled training data from a source domain to enhance a …
It is widely acknowledged that the success of deep learning is built upon large-scale training data and tremendous computing power. However, the data and computing power are not …