Recognition of Transitional Action for Short-Term Action Prediction using Discriminative Temporal CNN Feature

Hirokatsu Kataoka, Yudai Miyashita, Masaki Hayashi, Kenji Iwata and Yutaka Satoh

Abstract

Herein, we address transitional actions class as a class between actions. Transitional actions should be useful for producing short-term action predictions while an action is transitive. However, transitional action recognition is difficult because actions and transitional actions partially overlap each other. To deal with this issue, we propose a subtle motion descriptor (SMD) that identifies the sensitive differences between actions and transitional actions. The two primary contributions in this paper are as follows: (i) defining transitional actions for short-term action predictions that permit earlier predictions than early action recognition, and (ii) utilizing convolutional neural network (CNN) based SMD to present a clear distinction between actions and transitional actions.Using three different datasets, we will show that our proposed approach produces better results than do other state-of-the-art models. The experimental results clearly show the recognition performance effectiveness of our proposed model, as well as its ability to comprehend temporal motion in transitional actions.

Session

Posters 1

Files

Extended Abstract (PDF, 779K)
Paper (PDF, 4M)

DOI

10.5244/C.30.12
https://dx.doi.org/10.5244/C.30.12

Citation

Bibtex

        @inproceedings{BMVC2016_12,
        	title={Recognition of Transitional Action for Short-Term Action Prediction using Discriminative Temporal CNN Feature},
        	author={Hirokatsu Kataoka, Yudai Miyashita, Masaki Hayashi, Kenji Iwata and Yutaka Satoh},
        	year={2016},
        	month={September},
        	pages={12.1-12.12},
        	articleno={12},
        	numpages={12},
        	booktitle={Proceedings of the British Machine Vision Conference (BMVC)},
        	publisher={BMVA Press},
        	editor={Richard C. Wilson, Edwin R. Hancock and William A. P. Smith},
        	doi={10.5244/C.30.12},
        	isbn={1-901725-59-6},
        	url={https://dx.doi.org/10.5244/C.30.12}
        }