Search Results for author: Jiangfan Deng

Found 4 papers, 2 papers with code

Improving Crowded Object Detection via Copy-Paste

no code implementations22 Nov 2022 Jiangfan Deng, Dewen Fan, Xiaosong Qiu, Feng Zhou

Crowdedness caused by overlapping among similar objects is a ubiquitous challenge in the field of 2D visual object detection.

Data Augmentation Object +2

Body-Face Joint Detection via Embedding and Head Hook

1 code implementation ICCV 2021 Junfeng Wan, Jiangfan Deng, Xiaosong Qiu, Feng Zhou

Detecting pedestrians and their associated faces jointly is a challenging task. On one hand, body or face could be absent because of occlusion or non-frontal human pose. On the other hand, the association becomes difficult or even miss-leading in crowded scenes due to the lack of strong correlational evidence.

Pedestrian Detection

Visible Feature Guidance for Crowd Pedestrian Detection

no code implementations23 Aug 2020 Zhida Huang, Kaiyu Yue, Jiangfan Deng, Feng Zhou

Then we perform NMS only on visible bounding boxes to achieve the best fitting full box in inference.

Pedestrian Detection

Matching Guided Distillation

1 code implementation ECCV 2020 Kaiyu Yue, Jiangfan Deng, Feng Zhou

However, this introduces two problems: a) The adaptation module brings more parameters into training.

Cannot find the paper you are looking for? You can Submit a new open access paper.