Back
  1. Home
  2. Profile
Profil

Seddati Omar

Université de Mons - UMONS > Faculté Polytechnique > Service Information, Signal et Intelligence artificielle

Université de Mons - UMONS > Recherche > Service de l'Institut Numédiart pour les Technologies créatives

Université de Mons - UMONS > Faculté Polytechnique > Information, Signal et Intelligence artificielle

ORCID
0000-0002-0573-8480

Main Referenced Co-authors
Dupont, Stéphane  (26)
Mahmoudi, Saïd  (16)
Rossetto, Luca (9)
Schuldt, Heiko (9)
Giangreco, Ivan (7)
Main Referenced Keywords
Sketch-based image retrieval (2); Batch sizes (1); CNN (1); Computer Networks and Communications (1); Computer Vision and Pattern Recognition (1);
Main Referenced Unit & Research Centers
CRTI - Centre de Recherche en Technologie de l'Information (23)
Main Referenced Disciplines
Library & information sciences (21)
Computer science (6)

Publications (total 27)

The most downloaded
7 downloads
Seddati, O., Dupont, S., & Mahmoudi, S. (2015). DeepSketch: Deep convolutional neural networks for sketch recognition and similarity search. International Workshop on Content-Based Multimedia Indexing, CBMI 2015, Prague, Czech Republic, June 10-12, 2015. https://hdl.handle.net/20.500.12907/41752
The most cited
38 citations (Scopus®)
Seddati, O., Dupont, S., Mahmoudi, S., & Amiri Parian, M. (2017). Towards Good Practices for Image Retrieval Based on CNN Features. Paper presented at IEEE International Conference on Computer Vision, Venice, Italy. https://hdl.handle.net/20.500.12907/42060

Seddati, O., Dupont, S., Mahmoudi, S., & Dutoit, T. (2022). Towards Human Performance on Sketch-Based Image Retrieval. In Proceedings of 19th International Conference on Content-based Multimedia Indexing, CBMI 2022. Association for Computing Machinery. doi:10.1145/3549555.3549582
Peer reviewed

Seddati, O., Dupont, S., Mahmoudi, S., & Dutoit, T. (2022). Transformers and CNNs both Beat Humans on SBIR. Eprint/Working paper retrieved from https://orbi.umons.ac.be/20.500.12907/43859. doi:10.48550/arXiv.2209.06629

Seddati, O. (2018). Reconnaissance et Recherche de Données Multimédia par les Réseaux de Neurones Profonds. Unpublished doctoral thesis, Université de Mons.
Jury: Dupont, S. (Promotor), Mahmoudi, S. (Promotor), Manneback, P., Siebert, X., Schuldt, H., Gosselin, B., ... Marc, V. D.

Seddati, O., Dupont, S., Mahmoudi, S., & Amiri Parian, M. (2017). Towards Good Practices for Image Retrieval Based on CNN Features. Paper presented at IEEE International Conference on Computer Vision, Venice, Italy.

Seddati, O., Ben-Lhachemi, N., Dupont, S., & Mahmoudi, S. (2017). UMONS @ MediaEval 2017: Diverse Social Images Retrieval. Paper presented at MediaEval Benchmarking Initiative for Multimedia Evaluation, Dublin, Ireland.

Delbrouck, J.-B., Dupont, S., & Seddati, O. (2017). Visually Grounded Word Embeddings and Richer Visual Features for Improving Multimodal Neural Machine Translation. Paper presented at GLU 2017 International Workshop on Grounding Language Understanding, Stockholm, Sweden.

Seddati, O., Dupont, S., & Mahmoudi, S. (2017). Triplet Networks Feature Masking for Sketch-Based Image Retrieval. Lecture Notes in Computer Science.
Peer reviewed

Seddati, O., Dupont, S., & Mahmoudi, S. (2017). Quadruplet Networks for Sketch-Based Image Retrieval. ACM on International Conference on Multimedia Retrieval.
Peer reviewed

Seddati, O., Dupont, S., & Mahmoudi, S. (2017). DeepSketch 3: Analyzing deep neural networks features for better sketch recognition and sketch-based image retrieval. Multimedia Tools and Applications, 1-27. doi:10.1007/s11042-017-4799-2, 2017
Peer Reviewed verified by ORBi

Seddati, O., Delbrouck, J.-B., Dupont, S., & Mahmoudi, S. (25 April 2017). Deep Features for Big Data. Poster session presented at Journée scientifique du Pôle hainuyer 'Les données au coeur de notre devenir: les enjeux des big data, Tournai, e-campus, Belgium.

Rossetto, L., Giangreco, I., Tanase, C., Schuldt, H., Dupont, S., & Seddati, O. (2017). Enhanced Retrieval and Browsing in the IMOTION System. Paper presented at Conference on Multimedia Modeling, Reykjavik, Iceland.

Seddati, O., Dupont, S., & Mahmoudi, S. (2016). DeepSketch2Image: Deep Convolutional Neural Networks for Partial Sketch Recognition and Image Retrieval. ACM on Multimedia Conference, Amsterdam, The Netherlands, 2016, 739-741.
Peer reviewed

Tanase, C., Rossetto, L., Giangreco, I., Schuldt, H., Dupont, S., & Seddati, O. (2016). The IMOTION System at TRECVID 2016: The Ad-Hoc Video Search Task. Paper presented at TREC Video Retrieval Evaluation, .

Seddati, O., Dupont, S., & Mahmoudi, S. (2016). DeepSketch 2: Deep Convolutional Neural Networks for Partial Sketch Recognition. International Workshop on Content-based Multimedia Indexing, CBMI 2016, Bucharest, Romania, June 15-17, 2016.
Peer reviewed

Seddati, O., Dupont, S., & Mahmoudi, S. (2016). Réseaux de Neurones Convolutionnels Profonds pour la Reconnaissance d'Action dans les Vidéos. Paper presented at CORESA 2016 - COmpression et REprésentation des Signaux Audiovisuels, Nancy, France.

Tanase, C., Giangreco, I., Rossetto, L., Schuldt, H., Seddati, O., Dupont, S., Altiok, O. C., & Sezgin, M. (2016). Semantic Sketch-Based Video Retrieval with Autocompletion. Paper presented at International Conference on Intelligent User Interfaces, Sonoma, United States - California.

Schuldt, H., Dupont, S., Giangreco, I., Rossetto, L., Sahillioglu, Y., Seddati, O., Sen, C., Sezgin, M., Tanase, C., & Yildirim, D. (2016). IMOTION - Intelligent MultiModal Augmented Video Motion Retrieval System - Periodic Report 2.

Seddati, O., Dupont, S., & Mahmoudi, S. (2016). Video Motion Feature Extractors, 1st Prototype - IMOTION Deliverable 2.2.

Rossetto, L., Giangreco, I., Heller, S., Tanase, C., Schuldt, H., Dupont, S., Seddati, O., Sezgin, M., Altiok, O. C., & Sahillioglu, Y. (2016). IMOTION - Searching for Video Sequences Using Multi-Shot Sketch Queries. Lecture Notes in Computer Science.
Peer reviewed

Rossetto, L., Giangreco, I., Tanase, C., Schuldt, H., Dupont, S., Seddati, O., Sezgin, M., & Sahillioglu, Y. (2016). iAutoMotion - an Autonomous Content-Based Video Retrieval Engine. Lecture Notes in Computer Science.
Peer reviewed

Seddati, O., Emre, K., Pironkov, G., Dupont, S., Mahmoudi, S., & Dutoit, T. (2015). UMons at MediaEval 2015 Affective Impact of Movies Task including Violent Scenes Detection. IEEE Multimedia.
Peer Reviewed verified by ORBi

Seddati, O., Dupont, S., & Mahmoudi, S. (2015). DeepSketch: Deep convolutional neural networks for sketch recognition and similarity search. International Workshop on Content-Based Multimedia Indexing, CBMI 2015, Prague, Czech Republic, June 10-12, 2015.
Peer reviewed

Seddati, O., Dupont, S., & Mahmoudi, S. (10 March 2015). DNN for action recognition in videos. Poster session presented at 8ème édition de la Matinée de Chercheurs, Mons, Belgium.

Seddati, O., Dupont, S., & Mahmoudi, S. (2015). Report on Video Motion Feature Extraction - IMOTION Deliverable 2.1.

Schuldt, H., Dupont, S., Giangreco, G., Rossetto, L., Sahillioglu, Y., Seddati, O., Sen, C., Sezgin, M., Tanase, C., & Yildirim, D. (2015). IMOTION - Intelligent MultiModal Augmented Video Motion Retrieval System - Periodic Report 1.

Rossetto, L., Giangreco, I., Schuldt, H., Dupont, S., Seddati, O., Sezgin, M., & Sahillioglu, Y. (01 January 2015). IMOTION - A Content-Based Video Retrieval Engine. Lecture Notes in Computer Science, 8936, 255-260.
Peer reviewed

Giangreco, G., Rossetto, L., Schuldt, H., Sezgin, M., Sahillioglu, Y., Dupont, S., & Seddati, O. (2014). Initial Requirements and System Specification - IMOTION Deliverable 1.1.

Contact ORBi