SF-Net: Single-Frame Supervision for Temporal Action Localization

Ma Fan
Ma Fan
Zhu Linchao
Zhu Linchao
Zha Shengxin
Zha Shengxin
Kundu Gourab
Kundu Gourab
Shou Zheng
Shou Zheng

european conference on computer vision, pp. 420-437, 2020.

Cited by: 6|Views12

Abstract:

In this paper, we study an intermediate form of supervision, i.e., single-frame supervision, for temporal action localization (TAL). To obtain the single-frame supervision, the annotators are asked to identify only a single frame within the temporal window of an action. This can significantly reduce the labor cost of obtaining full supe...More

Code:

Data:

Your rating :
0

 

Tags
Comments