Commonly used backbones for semantic segmentation, such as ResNet and
Sw...
In person re-identification (re-ID) task, it is still challenging to lea...
In this work, we study the black-box targeted attack problem from the mo...
Foucaud et al. recently introduced and initiated the study of a new
grap...
In this paper, we discuss the perturbation analysis of the extended vert...
Motion transfer aims to transfer the motion of a driving video to a sour...
Image animation aims to animate a source image by using motion learned f...
Average precision (AP) loss has recently shown promising performance on ...
Automatic snake species recognition is important because it has vast
pot...
Detection transformers like DETR have recently shown promising performan...
Channel (or 3D filter) pruning serves as an effective way to accelerate ...
Existing works typically treat cross-domain semantic segmentation (CDSS)...
Given a source image and a driving video depicting the same object type,...
The goal of video highlight detection is to select the most attractive
s...
Deep models trained on source domain lack generalization when evaluated ...
Cold-start issues have been more and more challenging for providing accu...
Creative image animations are attractive in e-commerce applications, whe...
Triplet loss is a widely adopted loss function in ReID task which pulls ...
Domain adaptation is critical for success when confronting with the lack...
Video super-resolution has recently become one of the most important
mob...
Domain adaptation aims to leverage a label-rich domain (the source domai...
Object recognition advances very rapidly these days. One challenge is to...
Open compound domain adaptation (OCDA) is a domain adaptation setting, w...
While deep learning has been successfully applied to many real-world com...
In this paper, we introduce a new reinforcement learning (RL) based neur...
In this paper, we tackle the problem of convolutional neural network des...
Image-to-image translation is to map images from a given style to
anothe...
Cross-domain object detection has recently attracted more and more atten...
Cross domain object detection is challenging, because object detection m...
C-V2X (Cellular Vehicle-to-Everything) is the important enabling technol...
Due to a lack of medical resources or oral health awareness, oral diseas...
Due to a lack of medical resources or oral health awareness, oral diseas...
In this work, we propose a simple yet effective semi-supervised learning...
Existing domain adaptation methods generally assume different domains ha...
In generative modeling, the Wasserstein distance (WD) has emerged as a u...
In this work, we propose a domain flow generation(DLOW) approach to mode...
Recently, increasing attention has been drawn to training semantic
segme...
We present a machine learning approach to distinguish texts translated t...
Manifold theory has been the central concept of many learning methods.
H...
Object detection typically assumes that training and test data are drawn...
Exploiting synthetic data to learn deep models has attracted increasing
...
Spatiotemporal feature learning in videos is a fundamental and difficult...
In this paper, we present a study on learning visual recognition models ...
In this paper, we propose a new approach called Deep LogCORAL for
unsupe...
In this paper, we aim to introduce the classic Optimal Transport theory ...
We present the 2017 WebVision Challenge, a public image recognition chal...
In this paper, we propose a novel unsupervised domain adaptation algorit...