Point Cloud Registration (PCR) is a critical and challenging task in com...
Robust obstacle avoidance is one of the critical steps for successful
go...
This paper introduces an approach, named DFormer, for universal image
se...
3D scene flow estimation aims to estimate point-wise motions between two...
Vision Transformers have shown promising progress in various object dete...
Self-supervised learning (SSL) has made remarkable progress in visual
re...
Masked image modeling (MIM) has attracted much research attention due to...
Learning-based outlier (mismatched correspondence) rejection for robust ...
We propose an end-to-end one-step person search approach with learnable
...
Point Clouds Registration is a fundamental and challenging problem in 3D...
In contrastive self-supervised learning, the common way to learn
discrim...
Due to the few annotated labels of 3D point clouds, how to learn
discrim...
Learning robust feature matching between the template and search area is...
Unsupervised domain adaptation for point cloud semantic segmentation has...
Contrastive learning has shown great promise in the field of graph
repre...
Siamese network based trackers formulate 3D single object tracking as
cr...
Existing self-supervised monocular depth estimation methods can get rid ...
Cross-spectrum depth estimation aims to provide a depth map in all
illum...
We propose a novel one-step transformer-based person search framework, P...
Double Q-learning is a popular reinforcement learning algorithm in Marko...
Surgical scheduling optimization is an active area of research. However,...
Sketch-based 3D shape retrieval is a challenging task due to the large d...
Unsupervised point cloud registration algorithm usually suffers from the...
3D object tracking in point clouds is still a challenging problem due to...
In this paper, by modeling the point cloud registration task as a Markov...
Job shop scheduling problem (JSP) is a widely studied NP-complete
combin...
Extensive research efforts have been dedicated to deep learning based
od...
Point cloud registration is a fundamental problem in 3D computer vision....
Point clouds obtained from 3D sensors are usually sparse. Existing metho...
Double Q-learning is a popular reinforcement learning algorithm in Marko...
Point cloud semantic segmentation is a crucial task in 3D scene
understa...
LiDAR-based 3D object detection pushes forward an immense influence on
a...
In recent years, how to strike a good trade-off between accuracy and
inf...
Point cloud based retrieval for place recognition is still a challenging...
Vehicles, pedestrians, and riders are the most important and interesting...
Pedestrian detection is an important but challenging problem in computer...
In this paper, we propose a cascaded non-local neural network for point ...
In this paper, we propose an effective point cloud generation method, wh...
Detecting pedestrians, especially under heavy occlusions, is a challengi...
Eye movements have been widely investigated to study the atypical visual...
Pedestrian detection relying on deep convolution neural networks has mad...
A key focus in current cancer research is the discovery of cancer biomar...
With the increased affordability and availability of whole-genome sequen...