Výsledky vyhledávání

Toward unsupervised, multi-object discovery in large-scale image collections

Autor: Jean Ponce, Huy V. Vo, Patrick Pérez

Publikováno v: Computer Vision – ECCV 2020 ISBN: 9783030585914
ECCV (23)
Computer Vision – ECCV 2020
ECCV 2020-16th European Conference on Computer Vision
ECCV 2020-16th European Conference on Computer Vision, Aug 2020, Glasgow / Virtual, United Kingdom. ⟨10.1007/978-3-030-58592-1_46⟩

This paper addresses the problem of discovering the objects present in a collection of images without any supervision. We build on the optimization approach of Vo et al. (CVPR'19) with several key novelties: (1) We propose a novel saliency-based regi

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c366f1750565557b64b694a4075c6cfb

Zobrazit plný text záznamu

Unsupervised Image Matching and Object Discovery as Optimization

Autor: Minsu Cho, Yann LeCun, Huy V. Vo, Francis Bach, Jean Ponce, Kai Han, Patrick Pérez

Publikováno v: Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun 2019, Long Beach, United States. pp.8279-8288, ⟨10.1109/CVPR.2019.00848⟩
CVPR

Learning with complete or partial supervision is powerful but relies on ever-growing human annotation efforts. As a way to mitigate this serious problem, as well as to serve specific applications, unsupervised learning has emerged as an important fie

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::662bc6acea528ca9df1fbc3ef73bb0a1
https://hal.archives-ouvertes.fr/hal-02952012

Zobrazit plný text záznamu

Structural inpainting

Autor: Patrick Pérez, Ngoc Q. K. Duong, Huy V. Vo

Publikováno v: Proceedings of the 26th ACM international conference on Multimedia.

Scene-agnostic visual inpainting remains very challenging despite progress in patch-based methods. Recently, Pathak et al. 2016 have introduced convolutional "context encoders" (CEs) for unsupervised feature learning through image completion tasks. W

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::23e3a99d40661fb99a355ad79e96ceb9
https://doi.org/10.1145/3240508.3240678

Zobrazit plný text záznamu

A Semiosis Model of the Natures and Relationships among Categories of Information in IS

Autor: Tuan M. Nguyen, Huy V. Vo

Publikováno v: International Journal of Information Technologies and Systems Approach. 6:35-52

The paper explores, in a semiotics approach, the natures and the relationships between the category of information and its relatives that are data and knowledge. The resultant process model makes clear both the evolutionary natures and the triadic re

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::3abf0d05fa0e97c25f3183c749495d93
https://doi.org/10.4018/jitsa.2013070104

Zobrazit plný text záznamu

Integrating systems thinking into IS education

Autor: Huy V. Vo, David L. Olson, Bongsug Chae

Publikováno v: Systems Research and Behavioral Science. 23:107-121

IS failure has been observed and documented in various articles (Barker and Frolick, 2003; Beresford et al., 1976; Bostrom and Heinen, 1977; Bussen andMichael, 1997; Heeks, 2002; Kay et al., 1999; Kaye, 1990; Keil and Robey, 2001, Mitev, 1994). Many

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::7d14322b998d4bb188e9ae3a5e9e752a
https://doi.org/10.1002/sres.720

Zobrazit plný text záznamu

DYNAMIC MCDM: THE CASE OF URBAN INFRASTRUCTURE DECISION MAKING

Autor: David L. Olson, Huy V. Vo, Bongsug Chae

Publikováno v: International Journal of Information Technology & Decision Making. :269-292

Many societal decisions involve complexity and conflicting objectives. Preferences in such environments can be expected to change as situations evolve. In this paper, we propose a procedure that incorporates Multiple Criteria Decision Making (MCDM) i

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::b641b0779606efd9cf50d1b041cb6625
https://doi.org/10.1142/s0219622002000166

Zobrazit plný text záznamu

Information-As-System in Information Systems

Autor: Tuan M. Nguyen, Huy V. Vo

This article investigates the complex nature of information in information systems (IS). Based on the systems thinking framework, this study argues that information in IS is a system in its own right. A conceptual model of information-as-system is bu

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::1b5eb4b1cbe73349b3cbd6eeffa9e01f
https://doi.org/10.4018/978-1-60566-976-2.ch007

Zobrazit plný text záznamu

An Empirical Comparison of Collective Causal Mapping Approaches

Autor: Huy V. Vo, Marshall Scott Poole, James F. Courtney

Recently, capturing and evaluating group causal maps has come to attention of IS researchers (Tegarden and Sheetz, 2003; Lee, Courtney & O’Keefe, 1992; Vennix, 1996; Kwahk and Kim, 1999). This chapter summarizes two studies that formally compare th

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::62dde68ac316b2f6786eb82b3e0f425a
https://doi.org/10.4018/978-1-59140-396-8.ch006

Zobrazit plný text záznamu

Akademický článek

Disentangling Structure and Appearance in ViT Feature Space.

Autor: Tumanyan, Narek, Bar-Tal, Omer, Amir, Shir, Bagon, Shai, Dekel, Tali

Publikováno v: ACM Transactions on Graphics; Feb2024, Vol. 43 Issue 1, p1-16, 16p

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání