activity
20152017
most citedWeakly-supervised learning of visual relations

19 citations · 51 across the 5 of their papers we have counts for

collaborators

9 papers

cs.CV2017

Learning to Segment Moving Objects

Pavel Tokmakov, Cordelia Schmid, Karteek Alahari

We study the problem of segmenting moving objects in unconstrained videos. Given a video, the task is to segment all the objects that exhibit independent motion in at least one fra…

cs.CV2017

Incremental Learning of Object Detectors without Catastrophic Forgetting

Konstantin Shmelkov, Cordelia Schmid, Karteek Alahari

Despite their success for object detection, convolutional neural networks are ill-equipped for incremental learning, i.e., adapting the original model trained on a set of classes t…

cs.CV2017

BlitzNet: A Real-Time Deep Network for Scene Understanding

Nikita Dvornik, Konstantin Shmelkov, Julien Mairal +1

Real-time scene understanding has become crucial in many applications such as autonomous driving. In this paper, we propose a deep architecture, called BlitzNet, that jointly perfo…

cs.CV201719 cited

Weakly-supervised learning of visual relations

Julia Peyre, Ivan Laptev, Cordelia Schmid +1

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 predica…

cs.CV2017

Detecting Parts for Action Localization

Nicolas Chesneau, Grégory Rogez, Karteek Alahari +1

In this paper, we propose a new framework for action localization that tracks people in videos and extracts full-body human tubes, i.e., spatio-temporal regions localizing actions,…

cs.CV20171 cited

Proposal Flow: Semantic Correspondences from Object Proposals

Bumsub Ham, Minsu Cho, Cordelia Schmid +1

Finding image correspondences remains a challenging problem in the presence of intra-class variations and large changes in scene layout. Semantic flow methods are designed to handl…