Learning Term Discrimination

Autor: Jibril Frej, Jean-Pierre Chevallet, Philippe Mulhem, Didier Schwab

Publikováno v: 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2020)
43rd International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2020), Jul 2020, Xi'an, China. pp.1993-1996, ⟨10.1145/3397271.3401211⟩
SIGIR

Document indexing is a key component for efficient information retrieval (IR). After preprocessing steps such as stemming and stop-word removal, document indexes usually store term-frequencies (tf). Along with tf (that only reflects the importance of

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6464cbcbb0b79644c59c81a30b016562
https://hal.archives-ouvertes.fr/hal-03024756

Object Instance Identification with Fully Convolutional Networks

Autor: Philippe Mulhem, Georges Quénot, Matthias Kohl, Maxime Portaz, Jean-Pierre Chevallet

Publikováno v: Multimedia Tools and Applications
Multimedia Tools and Applications, Springer Verlag, 2018, https://doi.org/10.1007/s11042-018-5798-7. ⟨10.1007/s11042-018-5798-7⟩

International audience; This paper presents a novel approach for instance search and object detection, applied to museum visits. This approach relies on fully convo-lutional networks (FCN) to obtain region proposals and object representation. Our pro

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c5da5bde883f39c441ce70ae11e8bbad
https://hal.archives-ouvertes.fr/hal-01802287

Logics, Lattices and Probability: The Missing Links to Information Retrieval

Autor: Jean-Pierre Chevallet, Catherine Berrut, Karam Abdulahhad

Publikováno v: The Computer Journal
The Computer Journal, Oxford University Press (UK), 2016, ⟨10.1093/comjnl/bxw034⟩

International audience; Logic-based information retrieval (IR) models represent the retrieval decision as an implication d→q between a document d and a query q, where d and q are logical sentences. However, d→q is generally a binary decision, thu

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::322dfa10237accedd1f4c21e1a33a4a4
https://hal.archives-ouvertes.fr/hal-01394116

A Comparison of Deep Learning Based Query Expansion with Pseudo-Relevance Feedback and Mutual Information

Autor: Jean-Pierre Chevallet, Catherine Berrut, Mohannad Almasri

Publikováno v: Conférence ECIR
Conférence ECIR, Mar 2016, Padoue, Italy. pp.369-715, ⟨10.1007/978-3-319-30671-1_57⟩
Lecture Notes in Computer Science ISBN: 9783319306704
ECIR

International audience; Automatic query expansion techniques are widely applied for improving text retrieval performance, using a variety of approaches that exploit several data sources for finding expansion terms. Selecting expansion terms is challe

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::70191538cda756a3e516a65bbfc4fbfd
https://hal.archives-ouvertes.fr/hal-01576603/file/ECIR2016.pdf

Medical-Image Retrieval Based on Knowledge-Assisted Text and Image Indexing

Autor: Jean-Pierre Chevallet, Diem Thi Hoang Le, Caroline Lacoste, Joo-Hwee Lim

Publikováno v: IEEE Transactions on Circuits and Systems for Video Technology. 17:889-900

Voluminous medical images are generated daily. They are critical assets for medical diagnosis, research, and teaching. To facilitate automatic indexing and retrieval of large medical-image databases, both images and associated texts are indexed using

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::c9106aa3467bf4487689c5df173203ba
https://doi.org/10.1109/tcsvt.2007.897114