Camouflaged objects that blend into natural scenes pose significant
chal...
Achieving machine autonomy and human control often represent divergent
o...
Existing instance segmentation models learn task-specific information us...
Text-to-image (T2I) models based on diffusion processes have achieved
re...
Incorporating human feedback has been shown to be crucial to align text
...
What is an image and how to extract latent features? Convolutional Netwo...
Anomaly detection in videos is a significant yet challenging problem.
Pr...
The state of neural network pruning has been noticed to be unclear and e...
Vision Transformers have shown great promise recently for many vision ta...
Point cloud analysis is challenging due to irregularity and unordered da...
Semi-supervised domain adaptation (SSDA) is quite a challenging problem
...
Anomaly detection is a fundamental yet challenging problem in machine
le...
Recognizing Families In the Wild (RFIW), held as a data challenge in
con...
Adaptive gradient methods, such as Adam, have achieved tremendous
succes...
Several recent works [40, 24] observed an interesting phenomenon in neur...
There are demographic biases in the SOTA CNN used for FR. Our BFW datase...
Over-parameterization of neural networks benefits the optimization and
g...
Regularization has long been utilized to learn sparsity in deep neural
n...
Advances in face rotation, along with other face-based generative tasks,...
We reveal critical insights into problems of bias in state-of-the-art fa...
Current adversarial adaptation methods attempt to align the cross-domain...
Topology optimization by optimally distributing materials in a given dom...
Topology optimization by optimally distributing materials in a given dom...
Topology optimization by distributing materials in a domain requires
sto...
Domain Adaptation (DA) approaches achieved significant improvements in a...