DIRV: Dense Interaction Region Voting for End-to-End Human-Object Interaction Detection

Cited by: 0|Views209
Weibo:
To compensate for the detection flaws of single interaction region, a voting strategy is applied as an alternative to conventional Non-Maximal Suppression

Abstract:

Recent years, human-object interaction (HOI) detection has achieved impressive advances. However, conventional two-stage methods are usually slow in inference. On the other hand, existing one-stage methods mainly focus on the union regions of interactions, which introduce unnecessary visual information as disturbances to HOI detection. ...More

Code:

Data:

0
Full Text
Bibtex
Weibo
Your rating :
0

 

Tags
Comments