ETRI-Knowledge Sharing Plaform

KOREAN
논문 검색
Type SCI
Year ~ Keyword

Detail

Conference Paper Various-Level Spatio-Temporal Alignment for Cross-Domain Action Recognition
Cited 0 time in scopus Share share facebook twitter linkedin kakaostory
Authors
Hyungmin Kim, Dohyung Kim, Jaehong Kim
Issue Date
2021-12
Citation
International Conference on Robot Intelligence Technology and Applications (RITA) 2021 (LNNS 429), v.429, pp.323-335
Publisher
Springer
Language
English
Type
Conference Paper
DOI
https://dx.doi.org/10.1007/978-3-030-97672-9_29
Abstract
Cross-domain action recognition is a less explored field of research until recently. The previous approaches usually feed the pre-extracted video-level or segment-level feature vectors to shallow networks for regenerating them. These approaches cannot directly affect the full capability of the action recognition models. Considering the recent researches, CNN has an inductive bias towards the texture of images. In a domain-changing situations, this information is affected and changed easily. Moreover theses low-level information is mainly encoded in intermediate features and is also needed to be aligned. For exploring the effect of the adaptation between various levels of spatial dimensions of the feature map, we divided the model into several parts and performed adaptation for each step. However, not every stage play the important role in action recognition in the temporal axis. To more sensitive adaptation, we propose a similarity-based weighting strategy. We first calculate the discrimination loss for each stage. Next, these discrimination losses are weighted by their similarity. The discrimination losses become large if the source and target sample's similarity values are small in a certain stage. The proposed method achieves state-of-the-art performance on UCF101-HMDB full dataset.
KSP Keywords
Action recognition, Art performance, Cross Domain, Feature Map, Feature Vector, Inductive bias, Recognition model, Similarity-based, Weighting strategy, shallow networks, similarity values