Occlusion is a common problem with biometric recognition in the wild. Th...
With the advancement of robotics and AI technologies in the past decade,...
Transformer-based large language models (LLMs) have achieved great succe...
Image processing algorithms are prime targets for hardware acceleration ...
In this paper, we introduce FastPoints, a state-of-the-art point cloud
r...
As Deep Neural Networks (DNNs) are increasingly deployed in safety criti...
Battery life is an increasingly urgent challenge for today's untethered ...
Factor graph is a graph representing the factorization of a probability
...
Quantization is a technique to reduce the computation and memory cost of...
Deep learning-based face recognition models are vulnerable to adversaria...
Quantization of deep neural networks (DNN) has been proven effective for...
Neighbor search is of fundamental important to many engineering and scie...
Transformer models have achieved promising results on natural language
p...
Many of today's deep neural network accelerators, e.g., Google's TPU and...
The commercialization of autonomous machines is a thriving sector, and l...
Graph neural networks (GNNs) start to gain momentum after showing signif...
Exploiting sparsity is a key technique in accelerating quantized
convolu...
Art and culture, at their best, lie in the act of discovery and explorat...
Face swapping has both positive applications such as entertainment,
huma...
Time synchronization is a critical task in robotic computing such as
aut...
Reconstructing 3D models from large, dense point clouds is critical to e...
Deep learning using Convolutional Neural Networks (CNNs) has been shown ...
Recent researches on robotics have shown significant improvement, spanni...
Network pruning can reduce the high computation cost of deep neural netw...
Deep learning is vulnerable to adversarial attacks, where carefully-craf...
The research interest in specialized hardware accelerators for deep neur...
Machine perception applications are increasingly moving toward manipulat...
Deep Neural Networks (DNNs) are widely applied in a wide range of usecas...
Recently, researchers have started decomposing deep neural network model...
Iris segmentation and localization in non-cooperative environment is
cha...
Many DNN-enabled vision applications constantly operate under severe ene...
Biometric recognition on partial captured targets is challenging, where ...
Systolic Arrays are one of the most popular compute substrates within De...
Systolic Arrays are one of the most popular compute substrates within De...
Deep Neural Networks (DNN) are increasingly deployed in highly
energy-co...
Continuous computer vision (CV) tasks increasingly rely on convolutional...
This paper takes the position that, while cognitive computing today reli...
Machine learning is playing an increasingly significant role in emerging...