Small on-device models have been successfully trained with user-level
di...
DeepLab2 is a TensorFlow library for deep labeling, aiming to provide a
...
We introduce a novel representation learning method to disentangle
pose-...
Recognition of human poses and activities is crucial for autonomous syst...
When we watch videos, the visual and auditory information we experience ...
Depictions of similar human body configurations can vary with changing
v...
Many of the recent successful methods for video object segmentation (VOS...
Recently, Neural Architecture Search (NAS) has successfully identified n...
Instance embeddings are an efficient and versatile image representation ...
The design of neural network architectures is an important component for...
Spatial pyramid pooling module or encode-decoder structure are used in d...
In this work, we tackle the problem of instance segmentation, the task o...
In this work, we revisit atrous convolution, a powerful tool to explicit...
Despite significant recent advances in the field of face recognition,
im...