Annotating videos is cumbersome, expensive and not scalable. Yet, many strong video
models still rely on manually annotated data. With the recent introduction of the HowTo100M …

This paper introduces a novel approach for modeling visual relations between pairs of
objects. We call relation a triplet of the form (subject, predicate, object) where the predicate …

We generalize the concept of adaptive sampling rules to the sketch-and-project method for
solving linear systems. Analyzing adaptive sampling rules in the sketch-and-project setting …

Support Vector Machine (SVM) has always been one of the most successful learning
algorithms, with the central idea of maximizing the minimum margin, ie, the smallest distance …

Importance sampling has become an indispensable strategy to speed up optimization
algorithms for large-scale applications. Improved adaptive variants--using importance …

Spatio-temporal action detection in videos is typically addressed in a fully-supervised setup
with manual annotation of training videos required at every frame. Since such annotation is …

Coordinate descent methods employ random partial updates of decision variables in order
to solve huge-scale convex optimization problems. In this work, we introduce new adaptive …

Abstract We consider the Frank-Wolfe (FW) method for constrained convex optimization, and
we show that this classical technique can be interpreted from a different perspective: FW …

Conditional gradient algorithms (also often called Frank-Wolfe algorithms) are popular due
to their simplicity of only requiring a linear optimization oracle and more recently they also …

Abstract Conditional Gradients (aka Frank-Wolfe algorithms) form a classical set of methods
for constrained smooth convex minimization due to their simplicity, the absence of projection …