The focal point of egocentric video understanding is modelling hand-obje...
We call on the Document AI (DocAI) community to reevaluate current
metho...
The focal point of egocentric video understanding is modelling hand-obje...
In recent years, we have seen significant steps taken in the development...
To protect sensitive training data, differentially private stochastic
gr...
Federated learning frameworks have been regarded as a promising approach...
The task of visual grounding requires locating the most relevant region ...
Knee osteoarthritis (OA) is one of the highest disability factors in the...
The Dice score and Jaccard index are commonly used metrics for the evalu...
Superpixel algorithms are a common pre-processing step for computer visi...
Scattering networks are a class of designed Convolutional Neural Network...
We consider structure discovery of undirected graphical models from
obse...
Empirical risk minimization frequently employs convex surrogates to
unde...
Structure discovery in graphical models is the determination of the topo...
Learning with non-modular losses is an important problem when sets of
pr...
A family of maximum mean discrepancy (MMD) kernel two-sample tests is
in...
This paper introduces FGVC-Aircraft, a new dataset containing 10,000 ima...