926 citations · 2.2k across the 54 of their papers we have counts for
11 papers · 1 filter
End-to-End Learning of Visual Representations from Uncurated Instructional Videos
Antoine Miech, Jean-Baptiste Alayrac, Lucas Smaira +3
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 data…
Evolving Structures in Complex Systems
Hugo Cisneros, Josef Sivic, Tomas Mikolov
In this paper we propose an approach for measuring growth of complexity of emerging patterns in complex systems such as cellular automata. We discuss several ways how a metric for…
Is This The Right Place? Geometric-Semantic Pose Verification for Indoor Visual Localization
Hajime Taira, Ignacio Rocco, Jiri Sedlar +5
Visual localization in large and complex indoor scenes, dominated by weakly textured rooms and repeating geometric patterns, is a challenging problem with high practical relevance…
Learning to combine primitive skills: A step towards versatile robotic manipulation
Robin Strudel, Alexander Pashevich, Igor Kalevatykh +3
Manipulation tasks such as preparing a meal or assembling furniture remain highly challenging for robotics and vision. Traditional task and motion planning (TAMP) methods can solve…
HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips
Antoine Miech, Dimitri Zhukov, Jean-Baptiste Alayrac +3
Learning text-video embeddings usually requires a dataset of video clips with manually provided captions. However, such datasets are expensive and time consuming to create and ther…
Finding Moments in Video Collections Using Natural Language
Victor Escorcia, Mattia Soldan, Josef Sivic +2
We introduce the task of retrieving relevant video moments from a large corpus of untrimmed, unsegmented videos given a natural language query. Our task poses unique challenges as…
D2-Net: A Trainable CNN for Joint Detection and Description of Local Features
Mihai Dusmanu, Ignacio Rocco, Tomas Pajdla +4
In this work we address the problem of finding reliable pixel-level correspondences under difficult imaging conditions. We propose an approach where a single convolutional neural n…
Cross-task weakly supervised learning from instructional videos
Dimitri Zhukov, Jean-Baptiste Alayrac, Ramazan Gokberk Cinbis +3
In this paper we investigate learning visual models for the steps of ordinary tasks using weak supervision via instructional narrations and an ordered list of steps instead of stro…
Monte-Carlo Tree Search for Efficient Visually Guided Rearrangement Planning
Yann Labbé, Sergey Zagoruyko, Igor Kalevatykh +4
We address the problem of visually guided rearrangement planning with many movable objects, i.e., finding a sequence of actions to move a set of objects from an initial arrangement…
Estimating 3D Motion and Forces of Person-Object Interactions from Monocular Video
Zongmian Li, Jiri Sedlar, Justin Carpentier +3
In this paper, we introduce a method to automatically reconstruct the 3D motion of a person interacting with an object from a single RGB video. Our method estimates the 3D poses of…
Teaching robots to imitate a human with no on-teacher sensors. What are the key challenges?
Radoslav Skoviera, Karla Stepanova, Michael Tesar +5
In this paper, we consider the problem of learning object manipulation tasks from human demonstration using RGB or RGB-D cameras. We highlight the key challenges in capturing suffi…