HERVE LE BORGNE

69
Documents
Affiliations actuelles
  • Commissariat à l'énergie atomique et aux énergies alternatives (CEA)
  • Laboratoire d'Intégration des Systèmes et des Technologies (LIST (CEA))

Domaines de recherche

Intelligence artificielle [cs.AI] Vision par ordinateur et reconnaissance de formes [cs.CV] Recherche d'information [cs.IR]

Publications

Publications

Image document

Fairer analysis and demographically balanced face generation for fairer face verification

Alexandre Fournier-Montgieux , Michael Soumm , Adrian Popescu , Bertrand Luvison , Hervé Le Borgne
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Feb 2025, Tucson (Arizona), United States
Communication dans un congrès cea-04910990 v1
Image document

Entity-aware cross-modal pretraining for Knowledge-Based Visual Question Answering

Omar Adjali , Olivier Ferret , Sahar Ghannay , Hervé Le Borgne
European Conference on Information Retrieval (ECIR), Apr 2025, Lucca, Italy. pp.391-400, ⟨10.1007/978-3-031-88714-7_38⟩
Communication dans un congrès cea-04910767 v1
Image document

Génération augmentée de récupération multi-niveau pour répondre à des questions visuelles

Omar Adjali , Olivier Ferret , Sahar Ghannay , Hervé Le Borgne
20e Conférence en Recherche d’Information et Applications (CORIA) 32ème Conférence sur le Traitement Automatique des Langues Naturelles (TALN) 27ème Rencontre des Étudiants Chercheurs en Informatique pour le Traitement Automatique des Langues (RECITAL) Les 18e Rencontres Jeunes Chercheurs en RI (RJCRI), 2025, Marseille, France. pp.128-130
Communication dans un congrès hal-05330645 v1
Image document

CaMiT: A time-aware car model dataset for classification and generation

Frédéric Lin , Biruk Abere Ambaw , Adrian Popescu , Hejer Ammar , Romaric Audigier et al.
NeurIPS 2025 - The Thirty-Ninth Annual Conference on Neural Information Processing Systems, Dec 2025, San Diego, United States
Communication dans un congrès cea-05322803 v1
Image document

Semantic Generative Augmentations for Few-Shot Counting

Perla Doubinsky , Nicolas Audebert , Michel Crucianu , Hervé Le Borgne
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Jan 2024, Waikoloa, Hawaii, United States
Communication dans un congrès hal-04259058 v1
Image document

Multi-Level Information Retrieval Augmented Generation for Knowledge-based Visual Question Answering

Omar Adjali , Olivier Ferret , Sahar Ghannay , Hervé Le Borgne
The 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP 2024), Nov 2024, Miami, United States. pp.16499-16513, ⟨10.18653/v1/2024.emnlp-main.922⟩
Communication dans un congrès hal-04852275 v1
Image document

Wasserstein Loss for Semantic Editing in the Latent Space of GANs

Perla Doubinsky , Nicolas Audebert , Michel Crucianu , Hervé Le Borgne
20th International Conference on Content-based Multimedia Indexing, Sep 2023, Orléans, France. ⟨10.1145/3617233.3617237⟩
Communication dans un congrès hal-04036414 v1
Image document

Self-improving SLAM in dynamic environments: learning when to mask

Adrian Bojko , Romain Dupont , Mohamed Tamaazousti , Hervé Le Borgne
BMVC 2022 - The 33rd British Machine Vision Conference, Nov 2022, Londres, United Kingdom
Communication dans un congrès hal-04315226 v1
Image document

ViQuAE, a Dataset for Knowledge-based Visual Question Answering about Named Entities

Paul Lerner , Olivier Ferret , Camille Guinaudeau , Hervé Le Borgne , Romaric Besançon et al.
SIGIR '22: The 45th International ACM SIGIR Conference on Research and Development in Information Retrieval, Jul 2022, Madrid, Spain. ⟨10.1145/3477495.3531753⟩
Communication dans un congrès hal-03650618 v1
Image document

Un jeu de données pour répondre à des questions visuelles à propos d’entités nommées en utilisant des bases de connaissances

Paul Lerner , Olivier Ferret , Camille Guinaudeau , Hervé Le Borgne , Romaric Besançon et al.
Traitement Automatique des Langues Naturelles (TALN 2022), Jun 2022, Avignon, France. pp.434-444
Communication dans un congrès hal-03701521 v1
Image document

AVAE: Adversarial variational auto encoder

Antoine Plumerault , Hervé Le Borgne , Céline Hudelot
ICPR 2020 - 25th International conference on pattern recognition, Jan 2021, Milan, Italy. pp.8687-8694, ⟨10.1109/ICPR48806.2021.9412727⟩
Communication dans un congrès hal-04314595 v1
Image document

Using Sentences as Semantic Representations in Large Scale Zero-Shot Learning

Yannick Le Cacheux , Hervé Le Borgne , Michel Crucianu
ECCV 2020 workshop Transferring and adapting source knowledge in computer vision (TASK-CV), Aug 2020, Glasgow, United Kingdom
Communication dans un congrès hal-03003689 v1
Image document

Multimodal entity linking for tweets

Omar Adjali , Romaric Besançon , Olivier Ferret , Hervé Le Borgne , Brigitte Grau
ECIR 2020 - 42nd European Conference on Information Retrieval Research, Apr 2020, Lisbonne (Online event), Portugal. pp.463-478, ⟨10.1007/978-3-030-45439-5⟩
Communication dans un congrès hal-04315181 v1
Image document

Building a multimodal entity linking dataset from tweets

Omar Adjali , Romaric Besançon , Olivier Ferret , Hervé Le Borgne , Brigitte Grau
LREC 2020 - 12th Language Resources and Evaluation Conference, May 2020, Marseille, France. pp.4885-4292
Communication dans un congrès hal-04315504 v1
Image document

Controlling generative models with continuous factors of variations

Antoine Plumerault , Hervé Le Borgne , Céline Hudelot
ICLR 2020 - Eighth International Conference on Learning Representations, Apr 2020, Addis Abeba (Virtual event), Ethiopia
Communication dans un congrès hal-04314572 v1
Image document

Modeling Inter and Intra-Class Relations in the Triplet Loss for Zero-Shot Learning

Yannick Le Cacheux , Hervé Le Borgne , Michel Crucianu
IEEE International Conference on Computer Vision, Oct 2019, Séoul, South Korea. ⟨10.1109/ICCV.2019.01043⟩
Communication dans un congrès hal-02440364 v1
Image document

Learning finer-class networks for universal representations

Julien Girard , Youssef Tamaazousti , Hervé Le Borgne , Céline Hudelot
BMVC 2018 - the 29th British Machine Vision Conference, Sep 2018, Newcastle, United Kingdom. ⟨10.48550/arXiv.1810.02126⟩
Communication dans un congrès hal-04315371 v1

Scale-Free Content Based Image Retrieval (or Nearly so)

A. Popescu , A. Ginsca , Hervé Le Borgne
2017 IEEE International Conference on Computer Vision Workshops (ICCVW), Oct 2017, Venice, Italy. pp.280-288, ⟨10.1109/ICCVW.2017.42⟩
Communication dans un congrès cea-01841662 v1

Supervised Learning of Entity Disambiguation Models by Negative Sample Selection

Hani Daher , Romaric Besançon , Olivier Ferret , Hervé Le Borgne , Anne-Laure Daquo et al.
18th International Conference on Computational Linguistics and Intelligent Text Processing (CICLing 2017), 2017, Budapest, Hungary
Communication dans un congrès cea-01857878 v1
Image document

CEA LIST Participation to the TAC 2017 Event Nugget Track

Dorian Kodelja , Romaric Besançon , Olivier Ferret , Hervé Le Borgne , E. Boroş
10th Text Analysis Conference (TAC 2017), 2017, Gaithersburg, United States
Communication dans un congrès cea-01857880 v1

AMECON: Abstract meta-concept features for text-illustration

I. Chami , Y. Tamaazousti , Hervé Le Borgne
ICMR 2017 - Proceedings of the 2017 ACM International Conference on Multimedia Retrieval, Jun 2017, Bucharest, Romania. pp.347-355, ⟨10.1145/3078971.3078993⟩
Communication dans un congrès cea-01813718 v1
Image document

IRIM at TRECVID 2017: Instance Search

Boris Mansencal , Jenny Benois-Pineau , Hervé Bredin , Alexandre Benoit , Nicolas Voiron et al.
TRECVid workshop 2017, Nov 2017, Gaithersburg, Maryland, United States
Communication dans un congrès hal-01834223 v1
Image document

Désambiguïsation d’entités nommées par apprentissage de modèles d’entités à large échelle

Hani Daher , Romaric Besançon , Olivier Ferret , Hervé Le Borgne , Anne-Laure Daquo et al.
14ème COnférence en Recherche d'Information et Applications (CORIA 2017), 2017, Marseille, France. pp.185-200
Communication dans un congrès cea-01857881 v1
Image document

MuCaLe-Net: Multi categorical-Level networks to generate more discriminating features

Y. Tamaazousti , Hervé Le Borgne , Céline Hudelot
2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Jul 2017, Honolulu, HI, United States. pp.5282-5291, ⟨10.1109/CVPR.2017.561⟩
Communication dans un congrès cea-01841669 v1

Utilisation des relations d'une base de connaissances pour la désambiguïsation d'entités nommées

Romaric Besançon , Hani Daher , Olivier Ferret , Hervé Le Borgne
23ème Conférence sur le Traitement Automatique des Langues Naturelles (JEP-TALN-RECITAL 2016), 2016, Paris, France. pp.290--303
Communication dans un congrès cea-01858433 v1

Image annotation and two paths to text illustration

Hervé Le Borgne , E. Gadeski , I. Chami , T.Q. Nhi Tran , Y. Tamaazousti et al.
2016 Working Notes of Conference and Labs of the Evaluation Forum, CLEF 2016, 2016, Evora, Portugal. pp.322-333
Communication dans un congrès cea-01843172 v1

Constrained Local Enhancement of Semantic Features by Content-Based Sparsity

Youssef Tamaazousti , Hervé Le Borgne , Adrian Popescu
the 2016 ACM Conference on Multimedia Retrieval, Jun 2016, New York, France. ⟨10.1145/2911996.2912009⟩
Communication dans un congrès cea-01813602 v1

Diverse concept-level features for multi-object classification

Y. Tamaazousti , Hervé Le Borgne , Céline Hudelot
ICMR '16 Proceedings of the 2016 ACM on International Conference on Multimedia Retrieval Pages 63-70, Jun 2016, New York, United States. pp.63-70, ⟨10.1145/2911996.2912013⟩
Communication dans un congrès cea-01813723 v1
Image document

Cross-modal classification by completing unimodal representations

Thi Quynh Nhi Tran , Hervé Le Borgne , M. Crucianu
iV&L-MM '16 Proceedings of the 2016 ACM workshop on Vision and Language Integration Meets Multimedia Fusion, Oct 2016, Amsterdam, Netherlands. pp.17-25, ⟨10.1145/2983563.2983570⟩
Communication dans un congrès cea-01840417 v1
Image document

Aggregating image and text quantized correlated components

Thi Quynh Nhi Tran , Hervé Le Borgne , M. Crucianu
2016 IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2016, 2016, Las Vegas, United States. pp.2046-2054, ⟨10.1109/CVPR.2016.225⟩
Communication dans un congrès cea-01843176 v1

CEA LIST's participation to the scalable concept image annotation task of Image CLEF 2015

E. Gadeski , Hervé Le Borgne , A. Popescu
16th Conference and Labs of the Evaluation Forum, CLEF 2015, Sep 2015, Toulouse, France
Communication dans un congrès cea-01844059 v1

Duplicate image detection in a stream of web visual data

E. Gadeski , Hervé Le Borgne , A. Popescu
2015 13th International Workshop on Content-Based Multimedia Indexing (CBMI), Jun 2015, Prague, Czech Republic. ⟨10.1109/CBMI.2015.7153614⟩
Communication dans un congrès cea-01841168 v1
Image document

IRIM at TRECVID 2015: Semantic Indexing

Hervé Le Borgne , Philippe Gosselin , David Picard , Miriam Redi , Bernard Mérialdo et al.
Proceedings of TRECVid, Nov 2015, Gaithersburg, MD, United States
Communication dans un congrès hal-01233398 v1

Effective training of convolutional networks using noisy Web images

Phong Vo , Alexandru Lucian Ginsca , Hervé Le Borgne , Adrian Popescu
CBMI 2015 : 13th International Workshop on Content-Based Multimedia Indexing, Jun 2015, Prague, Czech Republic. pp.1 - 6, ⟨10.1109/CBMI.2015.7153607⟩
Communication dans un congrès hal-01185757 v1

CEA LIST Participation at TAC EDL English Diagnostic Task

Romaric Besançon , Hani Daher , Hervé Le Borgne , Olivier Ferret , Anne-Laure Daquo et al.
8th Text Analysis Conference (TAC 2015), 2015, Gaithersburg, Maryland, USA, United States
Communication dans un congrès cea-01858467 v1

Towards an automatic evaluation of retrieval performance with large scale image collections

A. Popescu , E. Spyromitros-Xoufis , S. Papadopoulos , Hervé Le Borgne , I. Kompatsiaris
MMCommons '15 Proceedings of the 2015 Workshop on Community-Organized Multimodal Mining: Opportunities for Novel Solutions, Oct 2015, Unknown, Australia. pp.7-12, ⟨10.1145/2814815.2814819⟩
Communication dans un congrès cea-01841022 v1
Image document

Combining generic and specific information for cross-modal retrieval

Thi Quynh Nhi Tran , Hervé Le Borgne , M. Crucianu
ICMR '15 Proceedings of the 5th ACM on International Conference on Multimedia Retrieval, Jun 2015, Shangai, China. pp.551-554, ⟨10.1145/2671188.2749348⟩
Communication dans un congrès cea-01813724 v1
Image document

Large-Scale Image Mining with Flickr Groups

Alexandru Lucian Ginsca , Adrian Popescu , Hervé Le Borgne , Nicolas Ballas , Phong Vo et al.
International Conference on Multimedia Modeling, Jan 2015, Sydney, NSW, Australia. pp.318 - 334, ⟨10.1007/978-3-319-14445-0_28⟩
Communication dans un congrès hal-01172319 v1
Image document

IRIM at TRECVID 2014: Semantic Indexing and Instance Search

Nicolas Ballas , Benjamin Labbé , Hervé Le Borgne , Philippe Gosselin , David Picard et al.
Proceedings of TRECVID, Nov 2014, Orlando, United States
Communication dans un congrès hal-01132491 v1

Tag completion based on belief theory and neighbor voting

Amel Znaidia , Hervé Le Borgne , Céline Hudelot
3rd ACM conference on International conference on multimedia retrieval, 2013, DALLAS, United States. pp.49-56, ⟨10.1145/2461466.2461476⟩
Communication dans un congrès hal-00824600 v1
Image document

IRIM at TRECVID 2013: Semantic Indexing and Instance Search

Nicolas Ballas , Benjamin Labbé , Hervé Le Borgne , Philippe Gosselin , Miriam Redi et al.
Proc. TRECVID Workshop, 2013, Gaithersburg, MD, United States
Communication dans un congrès hal-00953092 v1

Belief Theory for Large-Scale Multi-label Image Classification

Amel Znaidia , Hervé Le Borgne , Céline Hudelot
International Conference on Belief Functions - BELIEF 2012, 2012, Compiègne, France. pp.205-212
Communication dans un congrès hal-00825193 v1
Image document

Prise en compte de l'imperfection des tags pour la classification sémantique d'images

Amel Znaidia , Hervé Le Borgne , Céline Hudelot , Adrian Popescu
RFIA 2012 (Reconnaissance des Formes et Intelligence Artificielle), Jan 2012, Lyon, France. pp.978-2-9539515-2-3
Communication dans un congrès hal-00656498 v1
Image document

IRIM at TRECVID 2012: Semantic Indexing and Instance Search

Nicolas Ballas , Benjamin Labbé , Aymen Shabou , Hervé Le Borgne , Philippe-Henri Gosselin et al.
TRECVID - TREC Video Retrieval Evaluation workshop, Nov 2012, Gaithersburg, MD, United States. 12p
Communication dans un congrès hal-00770258 v1

Multimodal feature generation framework for semantic image classification

Amel Znaidia , Aymen Shabou , Adrian Popescu , Hervé Le Borgne , Céline Hudelot
ICMR '12 Proceedings of the 2nd ACM International Conference on Multimedia Retrieval, 2012, Hong Kong, Hong Kong SAR China. pp.article n° 38
Communication dans un congrès hal-00825190 v1

Bag-of-multimedia-words for image classification

Amel Znaidia , Aymen Shabou , Hervé Le Borgne , Céline Hudelot , Nikos Paragios
Proceedings of the 21st International Conference on Pattern Recognition, ICPR 2012, Nov 2012, Tsukuba, Japan. pp.1509-1512
Communication dans un congrès hal-00825187 v1
Image document

IRIM at TRECVID2009: High Level Feature Extraction

Bertrand Delezoide , Hervé Le Borgne , Pierre-Alain Moëllic , David Gorisse , Frédéric Precioso et al.
TRECVID 2009 - TREC Video Retrieval Evaluation, Nov 2009, Gaithersburg, MD, United States
Communication dans un congrès hal-00468199 v1

Classification of images: ICA filters vs. Human Perception

Hervé Le Borgne , Nathalie Guyader , Anne Guérin-Dugué , Jeanny Hérault
ISSPA, Jul 2003, Paris, France. pp.251-254
Communication dans un congrès hal-00372328 v1

Towards the introduction of human perception in a natural scene classification system

Nathalie Guyader , Hervé Le Borgne , Jeanny Hérault , Anne Guérin-Dugué
NNSP, Sep 2002, Martigny, Switzerland. pp.385-394
Communication dans un congrès hal-00372329 v1
Image document

Contrôle de la cardinalité par navigation dans l'espace latent des GANs

Perla Doubinsky , Nicolas Audebert , Michel Crucianu , Hervé Le Borgne
Reconnaissance des Formes, Image, Apprentissage et Perception (RFIAP), Jul 2022, Vannes, France. , 2022
Poster de conférence cea-04852483 v1
Image document

Multi-attribute balanced sampling for disentangled GAN controls

Perla Doubinsky , Nicolas Audebert , Michel Crucianu , Hervé Le Borgne
Pattern Recognition Letters, 2022, 162, pp.56-62. ⟨10.1016/j.patrec.2022.08.012⟩
Article dans une revue hal-03404279 v1
Image document

Multi-attribute balanced sampling for disentangled GAN controls

Perla Doubinsky , Nicolas Audebert , Michel Crucianu , Hervé Le Borgne
Pattern Recognition Letters, 2022, 162, pp.56-62. ⟨10.1016/j.patrec.2022.08.012⟩
Article dans une revue hal-03404279 v3
Image document

Learning more universal representations for transfer-learning

Youssef Tamaazousti , Hervé Le Borgne , Céline Hudelot , Mohamed-El-Amine Seddik , Mohamed Tamaazousti
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42 (9), pp.2212-2224. ⟨10.1109/TPAMI.2019.2913857⟩
Article dans une revue hal-04314530 v1

GPU deformable part model for object recognition

Etienne Gadeski , Hamidreza Odabai Fard , Hervé Le Borgne
Journal of Real-Time Image Processing, 2018, 14, pp.279-291. ⟨10.1007/s11554-014-0447-5⟩
Article dans une revue cea-01820312 v1
Image document

Fast and robust duplicate image detection on the web

E. Gadeski , Hervé Le Borgne , A. Popescu
Multimedia Tools and Applications, 2017, 76 (9), pp.11839-11858. ⟨10.1007/s11042-016-3619-4⟩
Article dans une revue hal-01845526 v1

Harnessing noisy Web images for deep representation

Phong D. Vo , Alexandru Ginsca , Hervé Le Borgne , Adrian Popescu
Computer Vision and Image Understanding, 2017, 164, pp.68 - 81. ⟨10.1016/j.cviu.2017.01.009⟩
Article dans une revue cea-01756775 v1

Vision-language integration using constrained local semantic features

Youssef Tamaazousti , Hervé Le Borgne , Adrian Popescu , Etienne Gadeski , Alexandru Ginsca et al.
Computer Vision and Image Understanding, 2017, 163, pp.41-57. ⟨10.1016/j.cviu.2017.05.017⟩
Article dans une revue cea-01803830 v1

Descripteur sémantique local contraint basé sur un descripteur RNC diversifié

Youssef Tamaazousti , Hervé Le Borgne , Adrian Popescu , Etienne Gadeski , Alexandru Ginsca et al.
Traitement du Signal, 2016
Article dans une revue hal-02517375 v1

Codage des modèles de tags

Amel Znaidia , Aymen Shabou , Hervé Le Borgne , Céline Hudelot
Revue des Sciences et Technologies de l'Information - Série RIA : Revue d'Intelligence Artificielle, 2013, 27 (1), pp.39-63. ⟨10.3166/ria.27.39-63⟩
Article dans une revue istex hal-00824580 v1

Learning Mid-level Image Features for Natural Scene and Texture Classification

Hervé Le Borgne , Anne Guérin-Dugué , Noël O'Connor
IEEE Transactions on Circuits and Systems for Video Technology, 2007, 17 (3), pp.286-297. ⟨10.1109/TCSVT.2007.890635⟩
Article dans une revue hal-00276879 v1

N-FindR method versus independent component analysis for lithological identification in hyperspectral imagery

Cécile Gomez , Hervé Le Borgne , Pascal Allemand , Christophe Delacourt , Patrick Ledru
International Journal of Remote Sensing, 2007, 28 (23), pp.5315-5338. ⟨10.1080/01431160701227679⟩
Article dans une revue insu-00273351 v1

Zero-shot Learning with Deep Neural Networks for Object Recognition

Yannick Le Cacheux , Hervé Le Borgne , Michel Crucianu
Benois-Pineau, Jenny; Zemmari, Akka. Multi-faceted Deep Learning: Models and Data, Springer, 2021, 978-3-030-74477-9. ⟨10.1007/978-3-030-74478-6_6⟩
Chapitre d'ouvrage hal-03219234 v1
Image document

From Classical to Generalized Zero-Shot Learning: A Simple Adaptation Process

Yannick Le Cacheux , Hervé Le Borgne , Michel Crucianu
Ioannis Kompatsiaris, Benoit Huet, Vasileios Mezaris, Cathal Gurrin, Wen-Huang Cheng, Stefanos Vrochidis. MultiMedia Modeling. 25th International Conference, MMM 2019, Thessaloniki, Greece, January 8–11, 2019, Proceedings, Part II, 11296, Springer Verlag, pp.465-477, 2019, Lecture Notes in Computer Science, 978-3-030-05716-9. ⟨10.1007/978-3-030-05716-9_38⟩
Chapitre d'ouvrage hal-01983612 v1

Detection of Visual Context

Hervé Le Borgne , Aymen Shabou
Intelligent Video Surveillance Systems, 2013, ⟨10.1002/9781118577851.ch16⟩
Chapitre d'ouvrage hal-01849066 v1

Multimodal Image Retrieval over a Large Database

Débora Mayupo , Adrian Popescu , Hervé Le Borgne , Pierre-Alain Moellic
Multilingual Information Access Evaluation II. Multimedia Experiments : 10th Workshop of the Cross-Language Evaluation Forum, CLEF 2009, Corfu, Greece, September 30 - October 2, 2009, Revised Selected Papers, Springer, pp.177-184, 2010, Lecture Notes in Computer Science
Chapitre d'ouvrage hal-00933265 v1
Image document

Analyse de scènes naturelles par Composantes Indépendantes

Hervé Le Borgne
Interface homme-machine [cs.HC]. Institut National Polytechnique de Grenoble - INPG, 2004. Français. ⟨NNT : ⟩
Thèse tel-00005925 v1