Human Action Adverb Recognition: ADHA Dataset and a Three-Stream Hybrid Model

Bo Pang, Kaiwen Zha, Cewu Lu; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2018, pp. 2325-2334

Abstract


We introduce the first benchmark for a new problem -- recognizing human action adverbs (HAA): "Adverbs Describing Human Actions" (ADHA). We demonstrate some key features of ADHA: a semantically complete set of adverbs describing human actions, a set of common, describable human actions, and an exhaustive labelling of simultaneously emerging actions in each video. We commit an in-depth analysis on the implementation of current effective models in action recognition and image captioning on adverb recognition, and the results reveal that such methods are unsatisfactory. Furthermore, we propose a novel three-stream hybrid model to tackle the HAA problem, which achieves better performances and receives relatively promising results.

Related Material


[pdf] [arXiv]
[bibtex]
@InProceedings{Pang_2018_CVPR_Workshops,
author = {Pang, Bo and Zha, Kaiwen and Lu, Cewu},
title = {Human Action Adverb Recognition: ADHA Dataset and a Three-Stream Hybrid Model},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {June},
year = {2018}
}