Part-Level Convolutional Neural Networks for Pedestrian Detection Using Saliency and Boundary Box Alignment
Sign Up to like & getrecommendations! Published in 2019 at "IEEE Access"
DOI: 10.1109/access.2019.2899105
Abstract: Pedestrians in videos have a wide range of appearance factors, such as body poses, occlusions, and complex backgrounds, which make their detection difficult. Moreover, a proposal shift problem causes the loss of body parts, such… read more here.
Keywords: saliency; part level; detection; pedestrian detection ... See more keywords
KE-RCNN: Unifying Knowledge based Reasoning into Part-level Attribute Parsing
Sign Up to like & getrecommendations! Published in 2022 at "IEEE transactions on cybernetics"
DOI: 10.48550/arxiv.2206.10146
Abstract: Part-level attribute parsing is a fundamental but challenging task, which requires the region-level visual understanding to provide explainable details of body parts. Most existing approaches address this problem by adding a regional convolutional neural network… read more here.
Keywords: attribute; rcnn; knowledge; part level ... See more keywords