Title |
Activity recognition based on egocentric object detection |
Author |
Saptarshi Sinha, Hiroki Ohashi, Mitsuhiro Okada, Takuto Sato, Katsuyuki Nakamura, |
Vo.No. start page.end page |
Vol., No., pp.- |
Category |
|
specialty |
|
keyword |
Activity recognition, Object detection, Egocentric video
|
Date of Issue |
2019-08-20
|
Abstract |
This paper studies first person activity recognition using egocentric videos. Object information is important for activity recognition but how much fine-grained object knowledge is helpful for the process is still an unresolved research area. We conducted an extensive study on how much fine-grained object location is useful for classifying activities. We experimentally found that too much fine or course grained information can harm activity recognition. We concatenated the object features from fine-tuned YOLOv3 to the features calculated by pretrained 3D-ResNext for activity recognition. We achieved a f-measure of 0.669, which is higher than when only 3D-ResNext features are used(0.653).
|
PDF |
[download]PDF download (1.7MB)
|