V
Vasil Khalidov
Researcher at Facebook
Publications - 27
Citations - 506
Vasil Khalidov is an academic researcher from Facebook. The author has contributed to research in topics: Mixture model & Cluster analysis. The author has an hindex of 13, co-authored 26 publications receiving 366 citations. Previous affiliations of Vasil Khalidov include Idiap Research Institute & French Institute for Research in Computer Science and Automation.
Papers
More filters
Journal ArticleDOI
DINOv2: Learning Robust Visual Features without Supervision
Maxime Oquab,T Moutakanni,Huy Q. Vo,Marc Szafraniec,Vasil Khalidov,Pierre Fernandez,Daniel Haziza,Francisco Massa,Alaaeldin El-Nouby,Mahmoud Assran,Nicolas Ballas,Wojciech Galuba,Russell Howes,Po-Yao Huang,Shang-Wen Li,Ishan Misra,Michael G. Rabbat,Vasu Sharma,Gabriel Synnaeve,Huijiao Xu,Hervé Jégou,Julien Mairal,Patrick Labatut,Armand Joulin,Piotr Bojanowski +24 more
TL;DR: In this article , the authors proposed an automatic pipeline to build a dedicated, diverse, and curated image dataset instead of uncurated data, as typically done in the self-supervised literature.
Proceedings ArticleDOI
Transferring Dense Pose to Proximal Animal Classes
TL;DR: This work establishes a DensePose model for the new animal which is also geometrically aligned to humans, introducing a multi-head R-CNN architecture that facilitates transfer of multiple recognition tasks between classes, and finding which combination of known classes can be transferred most effectively to the newAnimal.
Proceedings ArticleDOI
The vernissage corpus: a conversational human-robot-interaction dataset
Dinesh Babu Jayagopi,Samira Sheiki,David Klotz,Johannes Wienke,Jean-Marc Odobez,Sebastien Wrede,Vasil Khalidov,Laurent Nyugen,Britta Wrede,Daniel Gatica-Perez +9 more
TL;DR: A new conversational Human-Robot-Interaction (HRI) dataset with a real-behaving robot inducing interactive behavior with and between humans, involving a humanoid robot NAO1 explaining paintings in a room and then quizzing the participants, who are naive users.
Journal ArticleDOI
Conjugate mixture models for clustering multimodal data
TL;DR: This letter forms the problem as a likelihood maximization task and derives the associated conjugate expectation-maximization algorithm, which is tested and evaluated within the task of 3D localization of several speakers using both auditory and visual data.
Proceedings Article
Engagement-based Multi-party Dialog with a Humanoid Robot
David Klotz,Johannes Wienke,Julia Peltason,Britta Wrede,Sebastian Wrede,Vasil Khalidov,Jean-Marc Odobez +6 more
TL;DR: This demonstration presents the integration of an engagement model in an existing dialog system based on interaction patterns that enables the humanoid robot Nao to play a quiz game with multiple participants.