Rethinking deep active learning: Using unlabeled data at model training O Siméoni, M Budnik, Y Avrithis, G Gravier 2020 25th International conference on pattern recognition (ICPR), 1220-1227, 2021 | 81 | 2021 |
Asymmetric metric learning for knowledge transfer M Budnik, Y Avrithis Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2021 | 36 | 2021 |
Irim at TRECVID 2014: Semantic indexing and instance search N Ballas, B Labbé, H Le Borgne, P Gosselin, D Picard, M Redi, ... Proceedings of TRECVID, 2014 | 30 | 2014 |
The CAMOMILE collaborative annotation platform for multi-modal, multi-lingual and multi-media documents J Poignant, M Budnik, H Bredin, C Barras, M Stefas, P Bruneau, G Adda, ... LREC 2016 Conference, 2016 | 24 | 2016 |
On optimal settings of classification tree ensembles for medical decision support M Budnik, B Krawczyk Health informatics journal 19 (1), 3-15, 2013 | 17 | 2013 |
Learned features versus engineered features for multimedia indexing M Budnik, EL Gutierrez-Gomez, B Safadi, D Pellerin, G Quénot Multimedia Tools and Applications 76, 11941-11958, 2017 | 15 | 2017 |
Learned features versus engineered features for semantic video indexing M Budnik, EL Gutierrez-Gomez, B Safadi, G Quénot 2015 13th International Workshop on Content-Based Multimedia Indexing (CBMI …, 2015 | 12 | 2015 |
Automatic propagation of manual annotations for multimodal person identification in TV shows M Budnik, J Poignant, L Besacier, G Quénot 2014 12th International Workshop on Content-Based Multimedia Indexing (CBMI …, 2014 | 12 | 2014 |
LIG at TRECVid 2014: Semantic indexing B Safadi, N Derbas, A Hamadi, M Budnik, P Mulhem, G Quénot Proceedings of TRECVID, 2014 | 9 | 2014 |
A study on multimodal video hyperlinking with visual aggregation M Budnik, M Demirdelen, G Gravier 2018 IEEE International Conference on Multimedia and Expo (ICME), 1-6, 2018 | 8 | 2018 |
Immersive browsing in an image sphere G Schaefer, M Budnik, B Krawczyk Proceedings of the 11th international conference on ubiquitous information …, 2017 | 8 | 2017 |
Construction et évaluation d'un corpus pour la recherche d'instances d'images muséales. M Portaz, J Poignant, B Mateusz, P Mulhem, JP Chevallet, L Goeuriot COnférence en Recherche d'Informations et Applications-CORIA 2017, 14th …, 2017 | 7 | 2017 |
Deep complementary features for speaker identification in TV broadcast data M Budnik, L Besacier, A Khodabakhsh, C Demiroglu Odyssey Workshop 2016, 2016 | 6 | 2016 |
Active selection with label propagation for minimizing human effort in speaker annotation of tv shows B Mateusz, J Poignant, L Besacier, G Quénot Workshop on Speech, Language and Audio in Multimedia (SLAM 2014), 5 p., 2014 | 6 | 2014 |
Irisa at trecvid 2017: Beyond crossmodal and multimodal models for video hyperlinking M Demirdelen, M Budnik, G Sargent, R Bois, G Gravier Working notes of the TRECVID 2017 workshop, 2017 | 4 | 2017 |
MRIM-LIG at imageclef 2016 scalable concept image annotation task M Portaz, M Budnik, P Mulhem, J Poignant Clef 2016 Conference 1609, 363-370, 2016 | 4 | 2016 |
IRIM at TRECVid 2015: semantic indexing H Le Borgne, P Gosselin, D Picard, M Redi, B Mérialdo, B Mansencal, ... Proceedings of TRECVID, 2015 | 4 | 2015 |
Active and deep learning for multimedia M Budnik l’Université de Grenoble-Alpes, 2017 | 2 | 2017 |
Lig at mediaeval 2015 multimodal person discovery in broadcast tv task M Budnik, B Safadi, L Besacier, G Quénot, A Khodabakhsh, C Demiroglu MediaEval 2015 Workshop, 2015 | 2 | 2015 |
Unsupervised active learning for video annotation E Demir, Z Cataltepe, U Ekmekci, M Budnik, L Besacier ICML Active Learning Workshop 2015, 2015 | 2 | 2015 |