Multi-scale resolution training has seen an increased adoption across
mu...
Modern deep learning approaches usually transform inputs into a
modality...
We propose Dataset Reinforcement, a strategy to improve a dataset once s...
Inferring the full transportation network, including sidewalks and cycle...
The inspection of the Public Right of Way (PROW) for accessibility barri...
State-of-the-art automatic augmentation methods (e.g., AutoAugment and
R...
Recent isotropic networks, such as ConvMixer and vision transformers, ha...
Mobile vision transformers (MobileViT) can achieve state-of-the-art
perf...
We introduce CVNets, a high-performance open-source library for training...
Communicating with humans is challenging for AIs because it requires a s...
Light-weight convolutional neural networks (CNNs) are the de-facto for m...
Semantic segmentation aims to robustly predict coherent class labels for...
In this study, we propose the Ductal Instance-Oriented Pipeline (DIOP) t...
Video transmission applications (e.g., conferencing) are gaining momentu...
Understanding the relationship between figures and text is key to scient...
We introduce a very deep and light-weight transformer, DeLighT, that del...
Training end-to-end networks for classifying gigapixel size histopatholo...
For sequence models with large word-level vocabularies, a majority of ne...
In this paper, we propose a new CNN model DiCENet, that is built using: ...
In this paper, we introduce an end-to-end machine learning-based system ...
We introduce a light-weight, power efficient, and general purpose
convol...
Gliomas are the most common primary brain malignancies, with different
d...
LSTMs are powerful tools for modeling contextual information, as evidenc...
In this paper, we introduce a conceptually simple network for generating...
We introduce a fast and efficient convolutional neural network, ESPNet, ...
We present an approach for identifying the most walkable direction for
n...
Impact of soiling on solar panels is an important and well-studied probl...
We trained and applied an encoder-decoder model to semantically segment
...
In this paper, we propose a multi-object detection and tracking method u...