Activity and relationship modeling driven weakly supervised object detection

Yinlin Li, Yang Qian, Xu Yang, Yuren Zhang

Research output: Chapters, Conference Papers, Creative and Literary WorksRGC 32 - Refereed conference paper (with host publication)peer-review

2 Citations (Scopus)

Abstract

This paper presents a weakly supervised object detection method based on activity label and relationship modeling, which is motivated by the assumption that configuration of human and object are similar in same activity, and joint modeling of human, active object and activity could leverage the recognition of them. Compared to most weakly supervised method taking object as independent instance, firstly, active human and object proposals are learned and filtered based on class activation map of multi-label classification. Secondly, a spatial relationship prior including relative position, scale, overlaps etc are learned dependent on action. Finally, a multi-stream object detection framework integrating the spatial prior and pairwise ROI pooling are proposed to jointly learn the object and action class. Experiments are conducted on HICO-DET dataset, and our approach outperforms the state of the art weakly supervised object detection methods. © 2020 IEEE
Original languageEnglish
Title of host publicationProceedings of ICPR 2020
Subtitle of host publication25th International Conference on Pattern Recognition
PublisherIEEE
Pages9628-9634
ISBN (Electronic)9781728188089
ISBN (Print)978-1-7281-8809-6
DOIs
Publication statusPublished - 2021
Externally publishedYes
Event25th International Conference on Pattern Recognition (ICPR2020) - Virtual, Milan, Italy
Duration: 10 Jan 202115 Jan 2021
https://www.micc.unifi.it/icpr2020/

Publication series

NameProceedings - International Conference on Pattern Recognition
ISSN (Print)1051-4651

Conference

Conference25th International Conference on Pattern Recognition (ICPR2020)
Abbreviated titleICPR 2020
PlaceItaly
CityMilan
Period10/01/2115/01/21
Internet address

Funding

This work is partly supported by the National Key Research and Development Program of China (2017YFB1300200, 2017YFB1300203), the National Natural Science Foundation of China (Grant no. 61702516, 51705515, 61627808), the Joint Research Fund between the National Natural Science Foundation of China (NSFC) and Shen Zhen (Grant no. U1713201) and the Research Fund from Science and Technology on Underwater Vehicle Technology Laboratory (No. 6142215190103).

Fingerprint

Dive into the research topics of 'Activity and relationship modeling driven weakly supervised object detection'. Together they form a unique fingerprint.

Cite this