【原】行人检测 | Pedestrian Detection优秀论文整理

AI研习图书馆，发现不一样的精彩世界

论文整理

[CVPR-2019] Pedestrian Detection in Thermal Images using Saliency Maps

• paper: https:///abs/1904.06859

[CVPR-2019] SSA-CNN: SemanticSelf-Attention CNN for Pedestrian Detection

• paper: https:///abs/1902.09080v1

[CVPR-2019] High-level Semantic FeatureDetection:A New Perspective for Pedestrian Detection

• paper：https:///abs/1904.02948

• code：https://github.com/liuwei16/CSP

[CVPR-2018] Occluded Pedestrian DetectionThrough Guided Attention in CNNs

• paper:http://openaccess.thecvf.com/content_cvpr_2018/papers/Zhang_Occluded_Pedestrian_Detection_CVPR_2018_paper.pdf

[CVPR-2018] Repulsion Loss: DetectingPedestrians in a Crowd

• paper:http:///abs/1711.07752

• code:https://github.com/rainofmine/Repulsion_Loss

[TIP-2018] Too Far to See? Not Really:-Pedestrian Detection with Scale-Aware Localization Policy

• paper：https:///abs/1709.00235

[Transactions on Multimedia-2017] Scale-Aware Fast R-CNN for Pedestrian Detection

• paper：https:///abs/1510.08160

[ECCV-2018] Bi-box Regression forPedestrian Detection and Occlusion Estimation

• paper:http://openaccess./content_ECCV_2018/papers/CHUNLUAN_ZHOU_Bi-box_Regression_for_ECCV_2018_paper.pdf

[ECCV-2018] Learning Efficient Single-stagePedestrian Detectors by Asymptotic Localization Fitting

• paper:http://openaccess./content_ECCV_2018/papers/Wei_Liu_Learning_Efficient_Single-stage_ECCV_2018_paper.pdf

[ECCV-2018] Graininess-Aware Deep FeatureLearning for Pedestrian Detection

• paper:http://openaccess./content_ECCV_2018/papers/Chunze_Lin_Graininess-Aware_Deep_Feature_ECCV_2018_paper.pdf

[ECCV-2018] Occlusion-aware R-CNN:Detecting Pedestrians in a Crowd

• paper: http:///abs/1807.08407

[ECCV-2018] Small-scale PedestrianDetection Based on Somatic Topology Localization and Temporal FeatureAggregation

• paper:https:///abs/1807.01438

[CVPR-2018] Improving Occlusion and HardNegative Handling for Single-Stage Pedestrian Detectors

• paper: http://vision./projects/partgridnet/data/noh_2018.pdf

• project : http://vision./projects/partgridnet/

最后，祝大家炼丹愉快，科研顺利~~