Recent advances in deep learning for object detection
Object detection is a fundamental visual recognition problem in computer vision and has
been widely studied in the past decades. Visual object detection aims to find objects of …
been widely studied in the past decades. Visual object detection aims to find objects of …
A review of object detection based on deep learning
With the rapid development of deep learning techniques, deep convolutional neural
networks (DCNNs) have become more important for object detection. Compared with …
networks (DCNNs) have become more important for object detection. Compared with …
MOSE: A new dataset for video object segmentation in complex scenes
Video object segmentation (VOS) aims at segmenting a particular object throughout the
entire video clip sequence. The state-of-the-art VOS methods have achieved excellent …
entire video clip sequence. The state-of-the-art VOS methods have achieved excellent …
A survey of deep learning-based object detection
Object detection is one of the most important and challenging branches of computer vision,
which has been widely applied in people's life, such as monitoring security, autonomous …
which has been widely applied in people's life, such as monitoring security, autonomous …
Behind the curtain: Learning occluded shapes for 3d object detection
Advances in LiDAR sensors provide rich 3D data that supports 3D scene understanding.
However, due to occlusion and signal miss, LiDAR point clouds are in practice 2.5 D as they …
However, due to occlusion and signal miss, LiDAR point clouds are in practice 2.5 D as they …
Bayesian loss for crowd count estimation with point supervision
In crowd counting datasets, each person is annotated by a point, which is usually the center
of the head. And the task is to estimate the total count in a crowd scene. Most of the state-of …
of the head. And the task is to estimate the total count in a crowd scene. Most of the state-of …
SA-FPN: An effective feature pyramid network for crowded human detection
X Zhou, L Zhang - Applied Intelligence, 2022 - Springer
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 …
variety of occlusion patterns ranging from non-occluded situations to heavily occluded …
Deep occlusion-aware instance segmentation with overlapping bilayers
Segmenting highly-overlapping objects is challenging, because typically no distinction is
made between real object contours and occlusion boundaries. Unlike previous two-stage …
made between real object contours and occlusion boundaries. Unlike previous two-stage …
High-level semantic feature detection: A new perspective for pedestrian detection
W Liu, S Liao, W Ren, W Hu… - Proceedings of the IEEE …, 2019 - openaccess.thecvf.com
Object detection generally requires sliding-window classifiers in tradition or anchor-based
predictions in modern deep learning approaches. However, either of these approaches …
predictions in modern deep learning approaches. However, either of these approaches …
Crowd counting in the frequency domain
This paper investigates crowd counting in the frequency domain, which is a novel direction
compared to the traditional view in the spatial domain. By transforming the density map into …
compared to the traditional view in the spatial domain. By transforming the density map into …