Zobrazeno 1 - 10
of 46
pro vyhledávání: '"Dey, Sounak"'
This work investigates the problem of sketch-guided object localization (SGOL), where human sketches are used as queries to conduct the object localization in natural images. In this cross-modal setting, we first contribute with a tough-to-beat basel
Externí odkaz:
http://arxiv.org/abs/2109.11874
Autor:
Souibgui, Mohamed Ali, Biten, Ali Furkan, Dey, Sounak, Fornés, Alicia, Kessentini, Yousri, Gomez, Lluis, Karatzas, Dimosthenis, Lladós, Josep
Low resource Handwritten Text Recognition (HTR) is a hard problem due to the scarce annotated data and the very limited linguistic information (dictionaries and language models). For example, in the case of historical ciphered manuscripts, which are
Externí odkaz:
http://arxiv.org/abs/2105.05300
Scene text instances found in natural images carry explicit semantic information that can provide important cues to solve a wide array of computer vision problems. In this paper, we focus on leveraging multi-modal content in the form of visual and te
Externí odkaz:
http://arxiv.org/abs/2009.09809
Text contained in an image carries high-level semantics that can be exploited to achieve richer image understanding. In particular, the mere presence of text provides strong guiding content that should be employed to tackle a diversity of computer vi
Externí odkaz:
http://arxiv.org/abs/2001.04732
Publikováno v:
2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
In this paper, we investigate the problem of zero-shot sketch-based image retrieval (ZS-SBIR), where human sketches are used as queries to conduct retrieval of photos from unseen categories. We importantly advance prior arts by proposing a novel ZS-S
Externí odkaz:
http://arxiv.org/abs/1904.03451
Publikováno v:
In Neurocomputing 21 January 2023 518:82-94
Embedding data into vector spaces is a very popular strategy of pattern recognition methods. When distances between embeddings are quantized, performance metrics become ambiguous. In this paper, we present an analysis of the ambiguity quantized dista
Externí odkaz:
http://arxiv.org/abs/1806.07171
In this work we introduce a cross modal image retrieval system that allows both text and sketch as input modalities for the query. A cross-modal deep network architecture is formulated to jointly model the sketch and text input modalities as well as
Externí odkaz:
http://arxiv.org/abs/1804.10819
Offline signature verification is one of the most challenging tasks in biometrics and document forensics. Unlike other verification problems, it needs to model minute but critical details between genuine and forged signatures, because a skilled falsi
Externí odkaz:
http://arxiv.org/abs/1707.02131
Publikováno v:
In Optik January 2022 249