… Video UDA on action recognition is extended to more realistic settings, using videos collected
from surveillance cameras … federated learning, which is another important transfer learning …

… For MDA, 8 cameras located in different intersections are selected, each with more than
2,000 labeled images. We can view each camera as a domain. Scene segmentation. …

… data in transfer learning [155], [156], [157], semi-supervised learning [158], [159], [160], and
… To evaluate the domain adaptation methods under crosscamera adaptation settings, most …

… Because domain adaptation can be viewed as a special case of transfer learning [182],
we first review transfer learning to highlight the role of domain adaptation within this topic. …

… Competitors We provide several transfer learning approaches in our benchmark for efficient
imageto-video transfer learning. Note that the parameters of the linear classifier are always …

… technique is suitable for application in EV’s BMS and portable electronic systems. In a sense,
the proposed estimation approach can be viewed as follows; first, train the SNs offline with …

… , improving the feature alignment across domains. (Right): Clip order prediction. The top and
bottom videos are from different domains, but all capture … identified for transfer learning, and …

… Thus they are very different from human-borne camera videos (Fig. 1a). In this paper, we
focus on an unsupervised video domain adaptation setting. We aim to leverage the existing …

… Hence, all the systems reported in this work have been trained and evaluated at 8kHz. The
acoustic models are TDNN networks trained with framelevel cross-entropy loss criterion [24]. …

… In [26], Chan and NG proposed to adapt existing Word Sense Disambiguation (WSD)
systems to a target domain by using domain adaptation techniques and employing an active …