A Zero-Shot Architecture For Action Recognition In Still Images
Keywords
Predicted temporal patterns; Still image action recognition; Tensor decomposition
Abstract
Motion is a missing information in an image, however, it is a valuable cue for action recognition. Therefore, not only actions depend on the spatial-salient pixels, but also the temporal patterns of those pixels are evidently crucial. In this paper, we propose a novel unsupervised zero-shot approach, employing both spatial and temporal patterns, to perform action recognition in still images through Tensor Decomposition. In the proposed model, (1) we devise a novel strategy to form tensors from individual images in a way that each tensor encodes useful spatial-temporal information regarding the action being performed in images. Tensor decomposition is then used to estimate the overall signature of the action, while action is encoded in the spatial-temporal descriptions of images. (2) We show that appearance and motion are complementary sources of information. Comprehensive experiments on four benchmarks: Stanford-40, Willow, WIDER and the newly introduced UCFSI -101 still images dataset clearly demonstrate that our method outperforms state-of-the-art approaches.
Publication Date
8-29-2018
Publication Title
Proceedings - International Conference on Image Processing, ICIP
Number of Pages
460-464
Document Type
Article; Proceedings Paper
Personal Identifier
scopus
DOI Link
https://doi.org/10.1109/ICIP.2018.8451197
Copyright Status
Unknown
Socpus ID
85062923607 (Scopus)
Source API URL
https://api.elsevier.com/content/abstract/scopus_id/85062923607
STARS Citation
Safaei, Marjaneh and Foroosh, Hassan, "A Zero-Shot Architecture For Action Recognition In Still Images" (2018). Scopus Export 2015-2019. 10094.
https://stars.library.ucf.edu/scopus2015/10094