Over decades, neuroscience has accumulated a wealth of research results ...
The past few years have witnessed the immense success of object detectio...
Most previous co-salient object detection works mainly focus on extracti...
Advanced Patch Attacks (PAs) on object detection in natural images have
...
Recently, long-tailed image classification harvests lots of research
att...
Recently, inspired by DETR variants, query-based end-to-end instance
seg...
Current mainstream object detection methods for large aerial images usua...
With the rise of deep convolutional neural networks, object detection ha...
Temporal action localization aims at localizing action instances from
un...
Few-shot segmentation, which aims to segment unseen-class objects given ...
Semantic segmentation with limited annotations, such as weakly supervise...
Recently few-shot segmentation (FSS) has been extensively developed. Mos...
Online action detection has attracted increasing research interests in r...
In this paper, we reveal that metric learning would suffer from serious
...
Recent advances in machine learning and prevalence of digital medical im...
Zero-shot object detection aims at incorporating class semantic vectors ...
The great success of deep learning is mainly due to the large-scale netw...
Current weakly supervised semantic segmentation (WSSS) frameworks usuall...
Weakly supervised temporal action localization aims at learning the
inst...
Integrating the special electromagnetic characteristics of Synthetic Ape...
Oriented object detection is a practical and challenging task in remote
...
The application of light field data in salient object de-tection is beco...
Humans perform co-saliency detection by first summarizing the consensus
...
Current state-of-the-art two-stage detectors generate oriented proposals...
Conventional salient object detection models cannot differentiate the
im...
Recently, massive saliency detection methods have achieved promising res...
Significant performance improvement has been achieved for fully-supervis...
With the goal of identifying pixel-wise salient object regions from each...
How to effectively fuse cross-modal information is the key problem for R...
Most of the current action localization methods follow an anchor-based
p...
Weakly supervised temporal action localization is a newly emerging yet w...
As a concrete application of multi-view learning, multi-view classificat...
Remote sensing image scene classification, which aims at labeling remote...
Substantial efforts have been devoted more recently to presenting variou...
Clustering is an effective technique in data mining to group a set of ob...
In saliency detection, every pixel needs contextual information to make
...
Weakly-supervised object detection (WOD) is a challenging problems in
co...
Remote sensing image scene classification plays an important role in a w...
Traditional saliency models usually adopt hand-crafted image features an...
Co-saliency detection is a newly emerging and rapidly growing research a...
Object detection in optical remote sensing images, being a fundamental b...