Multiple object tracking (MOT) tends to become more challenging when sev...
Interpretable machine learning and explainable artificial intelligence h...
Scene text recognition has been studied for decades due to its broad
app...
Scene text recognition (STR) has attracted much attention due to its bro...
Person Re-IDentification (Re-ID) as a retrieval task, has achieved treme...
Cloth-changing person Re-IDentification (Re-ID) is a particularly challe...
The prominent progress in generative models has significantly improved t...
The abstract visual reasoning ability in human intelligence benefits
dis...
In the context of the rapid development of large language models, we hav...
Detecting abnormal patterns that deviate from a certain regular repeatin...
Pre-training fine-tuning is a prevalent paradigm in computer vision ...
Humans possess the cognitive ability to comprehend scenes in a compositi...
Diffusion models (DMs) have recently gained attention with state-of-the-...
Recent deep neural networks (DNNs) have come to rely on vast amounts of
...
Poisoning efficiency is a crucial factor in poisoning-based backdoor att...
In the paper, we investigate the coordination process of sensing and
com...
The captivating realm of Minecraft has attracted substantial research
in...
The emergence of text-driven motion synthesis technique provides animato...
In Chinese text recognition, to compensate for the insufficient local da...
The medical conversational question answering (CQA) system aims at provi...
Federated learning is a privacy-preserving collaborative learning approa...
Transmitting images for communication on social networks has become rout...
Integrating unmanned aerial vehicles (UAVs) into vehicular networks have...
Domain generalization (DG), aiming at models able to work on multiple un...
Predicting high-fidelity future human poses, from a historically observe...
Resource sharing between multiple workloads has become a prominent pract...
Let us rethink the real-world scenarios that require human motion predic...
Java deserialization vulnerability is a severe threat in practice.
Resea...
We present FengWu, an advanced data-driven global medium-range weather
f...
Language models have achieved impressive results in natural language
pro...
In many applications, ads are displayed together with the prices, so as ...
Text segmentation is a challenging vision task with many downstream
appl...
Heatmap-based methods play an important role in anatomical landmark
dete...
Java (de)serialization is prone to causing security-critical vulnerabili...
Needle picking is a challenging surgical task in robot-assisted surgery ...
For any video codecs, the coding efficiency highly relies on whether the...
Recent advancements toward perception and decision-making of flexible
en...
Task automation of surgical robot has the potentials to improve surgical...
A new timeliness metric, called Age-of-Information (AoI), has recently
a...
Neural image compression has surpassed state-of-the-art traditional code...
In this study, we investigate the task of few-shot Generative Domain
Ada...
In the surface defect detection, there are some suspicious regions that
...
When perceiving the world from multiple viewpoints, humans have the abil...
Deep Neural Networks have been widely used in many fields. However, stud...
As the deep learning rapidly promote, the artificial texts created by
ge...
Estimating precise metric depth and scene reconstruction from monocular
...
Due to the proliferation and widespread use of deep neural networks (DNN...
The flourishing blossom of deep learning has witnessed the rapid develop...
The appearance of the same object may vary in different scene images due...
To effectively exploit the potential of large-scale models, various
pre-...