Activity And Relationship Modeling Driven Weakly Supervised Object Detection
2020 25TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR)(2020)
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 multistream 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 HICODET dataset, and our approach outperforms the state of the art weakly supervised object detection methods.
MoreTranslated text
Key words
relationship modeling driven weakly supervised object detection,activity label,joint modeling,active object,active human,multilabel classification,spatial relationship,multistream object detection framework,spatial prior ROI pooling,pairwise ROI pooling,activity modeling driven weakly supervised object detection method,filtered based on class activation map,HICO-DET dataset
AI Read Science
Must-Reading Tree
Example
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined