This paper aims to learn a domain-generalizable (DG) person re-identific...
Robotic grasping faces new challenges in human-robot-interaction scenari...
In this paper, we formally address universal object detection, which aim...
In this paper, we are interested in learning a generalizable person
re-i...
Current person image retrieval methods have achieved great improvements ...
A mainstream type of current self-supervised learning methods pursues a
...
Image guided depth completion aims to recover per-pixel dense depth maps...
We propose a task we name Portrait Interpretation and construct a datase...
6-DoF grasp pose detection of multi-grasp and multi-object is a challeng...
Current instance segmentation methods rely heavily on pixel-level annota...
Clustering-based unsupervised domain adaptive (UDA) person re-identifica...
Semi-supervised learning aims to leverage a large amount of unlabeled da...
Transcripts generated by automatic speech recognition (ASR) systems for
...
Detection in large-scale scenes is a challenging problem due to small ob...
Learning pyramidal feature representations is crucial for recognizing ob...
In this paper, we delve into semi-supervised object detection where unla...
This paper proposes a self-supervised learning method for the person
re-...
The softmax loss and its variants are widely used as objectives for embe...
Generic object detection is one of the most fundamental and important
pr...
Video-based person re-id has drawn much attention in recent years due to...
This paper considers a realistic problem in person re-identification (re...
In this paper, we present an accurate and scalable approach to the face
...
Although existing image caption models can produce promising results usi...
We propose a very fast and effective one-step restoring method for blurr...
We address the problem of weakly supervised object localization where on...