978 citations · 7k across the 148 of their papers we have counts for
13 papers · 1 filter
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…
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…
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…
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…
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,…
Developing the Path Signature Methodology and its Application to Landmark-based Human Action Recognition
Weixin Yang, Terry Lyons, Hao Ni +2
Landmark-based human action recognition in videos is a challenging task in computer vision. One key step is to design a generic approach that generates discriminative features for…
AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions
Chunhui Gu, Chen Sun, David A. Ross +9
This paper introduces a video dataset of spatio-temporally localized Atomic Visual Actions (AVA). The AVA dataset densely annotates 80 atomic visual actions in 430 15-minute video…
SCNet: Learning Semantic Correspondence
Kai Han, Rafael S. Rezende, Bumsub Ham +4
This paper addresses the problem of establishing semantic correspondences between images depicting different instances of the same object or scene category. Previous approaches foc…
Action Tubelet Detector for Spatio-Temporal Action Localization
Vicky Kalogeiton, Philippe Weinzaepfel, Vittorio Ferrari +1
Current state-of-the-art approaches for spatio-temporal action localization rely on detections at the frame level that are then linked or tracked across time. In this paper, we lev…
SfM-Net: Learning of Structure and Motion from Video
Sudheendra Vijayanarasimhan, Susanna Ricco, Cordelia Schmid +2
We propose SfM-Net, a geometry-aware neural network for motion estimation in videos that decomposes frame-to-frame pixel motion in terms of scene and object depth, camera motion an…
Learning Video Object Segmentation with Visual Memory
Pavel Tokmakov, Karteek Alahari, Cordelia Schmid
This paper addresses the task of segmenting moving objects in unconstrained videos. We introduce a novel two-stream neural network with an explicit memory module to achieve this. T…
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…
Learning from Synthetic Humans
Gül Varol, Javier Romero, Xavier Martin +4
Estimating human pose, shape, and motion from images and videos are fundamental challenges with many applications. Recent advances in 2D human pose estimation use large amounts of…