Recent advances in label assignment in object detection mainly seek to independently
define positive/negative training samples for each ground-truth (gt) object. In this paper, we …

The crowded scenario not only contains instances at various scales but also introduces a
variety of occlusion patterns ranging from non-occluded situations to heavily occluded …

To date, the most powerful semi-supervised object detectors (SS-OD) are based on pseudo-
boxes, which need a sequence of post-processing with fine-tuned hyper-parameters. In this …

Pedestrian detection is an important branch of computer vision, and has important
applications in the fields of autonomous driving, artificial intelligence and video surveillance …

In this paper, we propose a new query-based detection framework for crowd detection.
Previous query-based detectors suffer from two drawbacks: first, multiple predictions will be …

One of the main and most effective measures to contain the recent viral outbreak is the
maintenance of the so-called Social Distancing (SD). To comply with this constraint …

In recent years, several methods and datasets have been proposed to push the performance
of pedestrian detection in crowded scenarios. In this study, three crowd-specific detectors …

Deep learning-based detectors tend to produce duplicate detections of the same objects.
After that, the detections are filtered via a non-maximum suppression algorithm (NMS) so …

摘要在密集行人检测场景中, 目标间的相互遮挡重叠会造成YOLOv3 模型的检测性能下降.
针对造成YOLOv3 性能下降的原因提出三点改进. 一是提出了一种聚拢损失函数 …

Label assignment has been widely studied in general object detection because of its great
impact on detectors' performance. In the field of dense pedestrian detection, human bodies …