This paper introduces a new and challenging Hidden Intention Discovery (...
Unsupervised domain adaptive person re-identification (Re-ID) methods
al...
We introduce the preliminary exploration of AniBalloons, a novel form of...
Data augmentation has been widely used in low-resource NER tasks to tack...
Graph contrastive learning (GCL) shows great potential in unsupervised g...
This work studies the multi-human parsing problem. Existing methods, eit...
Although face recognition has made impressive progress in recent years, ...
Quantum error correction codes play a central role in the realisation of...
AI is promising in assisting UX evaluators with analyzing usability test...
Image manipulation on the latent space of the pre-trained StyleGAN can
c...
In cooperative multi-agent tasks, parameter sharing among agents is a co...
Data augmentation is a widely used technique for enhancing the generaliz...
This work presents two astonishing findings on neural networks learned f...
Card game AI has always been a hot topic in the research of artificial
i...
Multi-person pose estimation generally follows top-down and bottom-up
pa...
Recent work demonstrated how we can design and use coding strips, a form...
Deep neural networks are powerful, but they also have shortcomings such ...
Face recognition has achieved considerable progress in recent years than...
Image transformation, a class of vision and graphics problems whose goal...
Data augmentation is a very practical technique that can be used to impr...
In this work, we are dedicated to multi-target active object tracking (A...
Cooperative multi-agent reinforcement learning (MARL) has made prominent...
Deep learning has achieved remarkable results in many computer vision ta...
Recent years have witnessed the great breakthrough of deep reinforcement...
Image animation brings life to the static object in the source image
acc...
Deep neural networks (DNNs) have been proven to be vulnerable to adversa...
Multi-agent reinforcement learning is difficult to be applied in practic...
Due to the partial observability and communication constraints in many
m...
The key challenge of zero-shot learning (ZSL) is how to infer the latent...
Active Multi-Object Tracking (AMOT) is a task where cameras are controll...
In cooperative multi-agent tasks, a team of agents jointly interact with...
In cooperative multi-agent systems, agents jointly take actions and rece...
Emoticons are indispensable in online communications. With users' growin...
Analyzing usability test videos is arduous. Although recent research sho...
Zero-shot learning (ZSL) tackles the novel class recognition problem by
...
Using computational notebooks (e.g., Jupyter Notebook), data scientists
...
Teaching programming through storytelling is a popular pedagogical appro...
A graph is an abstract model that represents relations among entities, f...
Data-driven decision making has been a common task in today's big data e...
Multiple-view visualization (MV) has been heavily used in visual analysi...
Neurofeedback games are an effective and playful approach to enhance cer...
In this paper, we develop face.evoLVe – a comprehensive library that
col...
Unsupervised person re-identification (re-ID) remains a challenging task...
Finding the similarities and differences between groups of datasets is a...
Subtext is a kind of deep semantics which can be acquired after one or m...
We present a versatile model, FaceAnime, for various video generation ta...
Single object tracking (SOT) is currently one of the most important task...
Visual data storytelling is gaining importance as a means of presenting
...
Convolutional neural network (CNN) is a class of artificial neural netwo...
When designing infographics, general users usually struggle with getting...