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

Socpus ID

85062923607 (Scopus)

Source API URL

https://api.elsevier.com/content/abstract/scopus_id/85062923607

This document is currently not available here.

Share

COinS