Pedestrian detection is the task of detecting pedestrians from a camera.
Further state-of-the-art results (e.g. on the KITTI dataset) can be found at 3D Object Detection.
|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
Yet, the widely adopted horizontal bounding box representation is not appropriate for ubiquitous oriented objects such as objects in aerial images and scene texts.
Existing person re-identification benchmarks and methods mainly focus on matching cropped pedestrian images between queries and candidates.
#6 best model for Person Re-Identification on CUHK03
A unified deep neural network, denoted the multi-scale CNN (MS-CNN), is proposed for fast multi-scale object detection.
#11 best model for Face Detection on WIDER Face (Hard)
In this paper, we proposed a novel single stage end-to-end trainable object detection network to overcome this limitation.
In this paper, we first explore how a state-of-the-art pedestrian detector is harmed by crowd occlusion via experimentation, providing insights into the crowd occlusion problem.
#4 best model for Pedestrian Detection on Caltech (using extra training data)
Through this study, we find that existing state-of-the-art pedestrian detectors generalize poorly from one dataset to another.
SOTA for Pedestrian Detection on CityPersons (using extra training data)
Such "in-the-tail" data is notoriously hard to observe, making both training and testing difficult.
Then, the learned feature representations are transferred to a second deep network, which receives as input an RGB image and outputs the detection results.
Multispectral pedestrian detection is essential for around-the-clock applications, e. g., surveillance and autonomous driving.