Object detection via inaccurate bounding boxes supervision has boosted a...
Large vision Transformers (ViTs) driven by self-supervised pre-training
...
Camouflaged objects are seamlessly blended in with their surroundings, w...
In this paper, we present an integral pre-training framework based on ma...
The past year has witnessed a rapid development of masked image modeling...
Bounding-box annotation form has been the most frequently used method fo...
The existing neural architecture search algorithms are mostly working on...
Gating modules have been widely explored in dynamic network pruning to r...
In this paper, we propose a self-supervised visual representation learni...
Recognizing images with long-tailed distributions remains a challenging
...
Exploiting relations among 2D joints plays a crucial role yet remains
se...
Encouraging progress in few-shot semantic segmentation has been made by
...
Within Convolutional Neural Network (CNN), the convolution operations ar...
Conventional networks for object skeleton detection are usually hand-cra...
Few-shot segmentation is challenging because objects within the support ...
The search cost of neural architecture search (NAS) has been largely red...
Vision-dialog navigation posed as a new holy-grail task in vision-langua...
Weakly supervised object detection (WSOD) is a challenging task when pro...
Weakly supervised object detection is a challenging task when provided w...
In this paper, we present a large-scale dataset and establish a baseline...
Deep domain adaptation methods can reduce the distribution discrepancy b...
This article studies the domain adaptation problem in person
re-identifi...
In this paper, we establish a baseline for object reflection symmetry
de...
Weakly supervised instance segmentation with image-level labels, instead...
Person re-identification (re-ID) models trained on one domain often fail...
Weakly supervised object localization remains challenging, where only im...
In this paper, we establish a baseline for object symmetry detection in
...
Deep Convolution Neural Networks (DCNNs) are capable of learning
unprece...
In this paper, we explore the redundancy in convolutional neural network...