User post-click conversion prediction is of high interest to researchers...
Recently, transformers have shown strong ability as visual feature
extra...
The Collaborative Qualitative Analysis (CQA) process can be time-consumi...
Active learning selects informative samples for annotation within budget...
Currently, most existing person re-identification methods use Instance-L...
Imaging and perception in photon-limited scenarios is necessary for vari...
The ground plane prior is a very informative geometry clue in monocular ...
In medical imaging, surface registration is extensively used for perform...
A combinatorial recommender (CR) system feeds a list of items to a user ...
Supervised person re-identification methods rely heavily on high-quality...
Binary pointwise labels (aka implicit feedback) are heavily leveraged by...
A series of unsupervised video-based re-identification (re-ID) methods h...
Nowadays, real data in person re-identification (ReID) task is facing pr...
While recent deep deblurring algorithms have achieved remarkable progres...
The existence of redundancy in Convolutional Neural Networks (CNNs) enab...
Node classification is a central task in graph data analysis. Scarce or ...
Channel pruning (a.k.a. filter pruning) aims to slim down a convolutiona...
We present PANDA, the first gigaPixel-level humAN-centric viDeo dAtaset,...
We propose a novel model for a topic-aware chatbot by combining the
trad...
Deep Neural Network (DNN) is powerful but computationally expensive and
...
Context: Conducting experiments is central to research machine learning
...
As designing appropriate Convolutional Neural Network (CNN) architecture...
Background: Unsupervised machine learners have been increasingly applied...
It is not easy to design and run Convolutional Neural Networks (CNNs) du...
The redundancy is widely recognized in Convolutional Neural Networks (CN...