Zobrazeno 1 - 9
of 9
pro vyhledávání: '"Dey, Arka Ujjal"'
We address the problem of detecting and mapping all books in a collection of images to entries in a given book catalogue. Instead of performing independent retrieval for each book detected, we treat the image-text mapping problem as a many-to-many ma
Externí odkaz:
http://arxiv.org/abs/2407.19812
Social Media posts, where real images are unscrupulously reused along with provocative text to promote a particular idea, have been one of the major sources of disinformation. By design, these claims are without editorial oversight and accessible to
Externí odkaz:
http://arxiv.org/abs/2404.10702
Publikováno v:
IEEE.ACCESS 10 (2022) 72092-72106
The open-ended question answering task of Text-VQA often requires reading and reasoning about rarely seen or completely unseen scene-text content of an image. We address this zero-shot nature of the problem by proposing the generalized use of externa
Externí odkaz:
http://arxiv.org/abs/2108.09717
Images with visual and scene text content are ubiquitous in everyday life. However, current image interpretation systems are mostly limited to using only the visual features, neglecting to leverage the scene text content. In this paper, we propose to
Externí odkaz:
http://arxiv.org/abs/1905.10622
We propose a framework for automated classification of Advertisement Images, using not just Visual features but also Textual cues extracted from embedded text. Our approach takes inspiration from the assumption that Ad images contain meaningful textu
Externí odkaz:
http://arxiv.org/abs/1806.08279
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Publikováno v:
In Pattern Recognition Letters September 2021 149:164-171
Autor:
Dey, Arka Ujjal, Harit, Gaurav
Publikováno v:
ACM International Conference Proceeding Series; 12/18/2016, p1-8, 8p
Autor:
Dey, Arka Ujjal, Harit, Gaurav
Publikováno v:
2015 Fifth National Conference on Computer Vision, Pattern Recognition, Image Processing & Graphics (NCVPRIPG); 2015, p1-4, 4p