2023
Scientific journals/Article
- Parian-Scherb, M., Uhrig, P., Rossetto, L., Dupont, S., & Schuldt, H. (2023). Gesture retrieval and its application to the study of multimodal communication. "International Journal on Digital Libraries". doi:10.1007/s00799-023-00367-0
Scientific congresses and symposiums/Paper published in a book
- Hammoudeh, A. T. A., Ghannam, I., Mubarak, H., Jean, E., Vandenbulcke, V., & Dupont, S. (2023). A Neuro-Symbolic Approach for Marine Vessels Power Prediction Under Distribution Shifts. In "2023 IEEE Jordan International Joint Conference on Electrical Engineering and Information Technology, JEEIT 2023". Institute of Electrical and Electronics Engineers Inc. doi:10.1109/JEEIT58638.2023.10185803
E-prints, Working papers and Research blog/Eprint already available on another site
- Seddati, O., Hubens, N., Dupont, S., & Dutoit, T. (2023). "A Recipe for Efficient SBIR Models: Combining Relative Triplet Loss with Batch Normalization and Knowledge Distillation". ORBi UMONS-University of Mons. https://orbi.umons.ac.be/handle/20.500.12907/48304.
- Hammoudeh, A. T. A., & Dupont, S. (2023). "Deep learning in medical image registration: introduction and survey". ORBi UMONS-University of Mons. https://orbi.umons.ac.be/handle/20.500.12907/48339.
2022
Scientific journals/Article
- Abdellatif, A., Mubarak, H., Ahmad, S., Ahmed, T., Shafiullah, M., Hammoudeh, A. T. A., Abdellatef, H., Rahman, M., & Gheni, H. (September 2022). Forecasting Photovoltaic Power Generation with a Stacking Ensemble Model. "Sustainability, 14" (17), 11083. doi:10.3390/su141711083
- Brousmiche, M., Rouat, J., & Dupont, S. (September 2022). Multimodal Attentive Fusion Network for audio-visual event recognition. "Information Fusion, 85", 52 - 59. doi:10.1016/j.inffus.2022.03.001
- Hammoudeh, A. T. A., Vanderplaetse, B., & Dupont, S. (2022). Soccer captioning: dataset, transformer-based model, and triple-level evaluation. "Procedia Computer Science, 210" (C), 104-111. doi:10.1016/j.procs.2022.10.125
- Hammoudeh, A. T. A., & Dupont, S. (2022). The prediction of residential building consumption using profiling and time encoding. "Procedia Computer Science, 210" (C), 7-11. doi:10.1016/j.procs.2022.10.113
- Mubarak, H., Hammoudeh, A. T. A., Ahmad, S., Abdellatif, A., Mekhilef, S., Mokhlis, H., & Dupont, S. (2022). A hybrid machine learning method with explicit time encoding for improved Malaysian photovoltaic power prediction. "Journal of Cleaner Production", 134979. doi:10.1016/j.jclepro.2022.134979
Scientific congresses and symposiums/Paper published in a book
- 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
Scientific congresses and symposiums/Paper published in a journal
- Bohy, H., Hammoudeh, A. T. A., Maiorca, A., Dupont, S., & Dutoit, T. (2022). Analysis of Co-Laughter Gesture Relationship on RGB videos in Dyadic Conversation Context. "Proceedings of LREC".
- Hammoudeh, A. T. A., Maiorca, A., Dupont, S., & Dutoit, T. (2022). Are there any Body-movement Differences between Women and Men when they Laugh? "Proceedings of LREC".
Scientific congresses and symposiums/Poster
- Hammoudeh, A. T. A., Vanderplaetse, B., & Dupont, S. (30 March 2022). "Deep soccer captioning with transformer" [Poster presentation]. Infortech' Day, Mons, Belgium.
Scientific congresses and symposiums/Paper published on a website
- Hammoudeh, A. T. A., & Dupont, S. (19 June 2022). "How does explicit orientation encoding affect image classification of ConvNets?" [Paper presentation]. CVPR 2022 workshop: Neurovision.
E-prints, Working papers and Research blog/Eprint first made available on ORBi
- Seddati, O., Dupont, S., Mahmoudi, S., & Dutoit, T. (2022). "Transformers and CNNs both Beat Humans on SBIR". ORBi UMONS-University of Mons. https://orbi.umons.ac.be/handle/20.500.12907/43859. doi:10.48550/arXiv.2209.06629
Diverse speeches and writings/Other
- Hammoudeh, A. T. A., & Dupont, S. (2022). "How does orientation encoding affect image classification of ConvNets?"
- Hammoudeh, A. T. A., & et al, E. A. (2022). "How can the EU regulate digital platforms without limiting freedom of speech and free exchange of thoughts?"
2021
Scientific journals/Article
- Parian, M., Walzer, C., Rossetto, L., Heller, S., Dupont, S., & Schuldt, H. (2021). Gesture of Interest: Gesture Search for Multi-Person, Multi-Perspective TV Footage. "International Conference on Content-Based Multimedia Indexing". doi:10.1109/CBMI50038.2021.9461887
2020
Scientific congresses and symposiums/Paper published in a book
- Delbrouck, J.-B., Tits, N., & Dupont, S. (2020). Modulated Fusion using Transformer for Linguistic-Acoustic Emotion Recognition. In "NLP Beyond Text (NLPBT) - EMNLP 2020 (2020)". -.
- Brousmiche, M., Dupont, S., & Rouat, J. (2020). Intra and Inter-Modality Interactions for Audio-Visual Event Detection. In "ACM International Conference on Multimedia". -.
- Delbrouck, J.-B., Tits, N., Brousmiche, M., & Dupont, S. (2020). A Transformer-based joint-encoding for Emotion Recognition and Sentiment Analysis. In "Second Grand Challenge and Workshop on Multimodal Language - ACL 2020 (2020)". -. doi:10.18653/v1/2020.challengehml-1.1
Scientific congresses and symposiums/Paper published in a journal
- Vanderplaetse, B., & Dupont, S. (2020). Improved Soccer Action Spotting Using Both Audio and Video Streams. "Conference on Computer Vision and Pattern Recognition Workshops".
- Brousmiche, M., Rouat, J., & Dupont, S. (2020). SECL-UMONS DATABASE FOR SOUND EVENT CLASSIFICATION AND LOCALIZATION. "IEEE International Conference on Acoustics, Speech and Signal Processing. Proceedings". doi:10.1109/ICASSP40776.2020.9053298
2019
Scientific congresses and symposiums/Paper published in a book
- Delbrouck, J.-B., Maiorca, A., Hubens, N., & Dupont, S. (2019). Modulated Self-attention Convolutional Network for VQA. In "NeurIPS 2019 Workshop on Visually-Grounded Interaction and Language (ViGIL) (2019)". -.
Scientific congresses and symposiums/Paper published in a journal
- Brousmiche, M., Dupont, S., & Rouat, J. (2019). Audio-Visual Fusion And Conditioning With Neural Networks For Event Recognition. "International Workshop on Machine Learning for Signal Processing".
E-prints, Working papers and Research blog/Eprint already available on another site
- Delbrouck, J.-B., & Dupont, S. (2019). "Adversarial reconstruction for Multi-modal Machine Translation". ORBi UMONS-University of Mons. https://orbi.umons.ac.be/handle/20.500.12907/42275.
2018
Scientific journals/Book review
- Delbrouck, J.-B., & Dupont, S. (2018). Bringing back simplicity and lightliness into neural image captioning. "ArXiv e-prints".
Scientific journals/Article
- Dimitropoulos, K., Manitsaris, S., Tsalakanidou, F., Denby, B., Buchman, L., Dupont, S., Nikolopoulos, S., Kompatsiaris, I., Charisis, V., Hadjileontiadis, L., Pozzi, F., Cotescu, M., Ciftci, S., Katos, A., Manitsaris, A., & Grammalidis, N. (2018). A Multimodal Approach for the Safeguarding and Transmission of Intangible Cultural Heritage: The Case of i-Treasures. "IEEE Intelligent Systems".
Scientific congresses and symposiums/Paper published in a book
- Delbrouck, J.-B., & Dupont, S. (2018). Object-oriented Targets for Visual Navigation using Rich Semantic Representations. In "NIPS 2018 Workshop on Visually-Grounded Interaction and Language (ViGIL)". -.
Scientific congresses and symposiums/Paper published on a website
- Delbrouck, J.-B., & Dupont, S. (30 October 2018). "UMONS Submission for WMT18 Multimodal Translation Task" [Paper presentation]. Third Conference on Machine Translation, Brussels, Belgium.
Diverse speeches and writings/Article for a general audience
- Dupont, S., Dutoit, T., & Curcio, G. (2018). Intelligence Artificielle (IA) et Apprentissage Profond (Deep Learning). "LUMONS élément - Magazine de l'Université de Mons".
1996
Scientific congresses and symposiums/Paper published in a book
- Bourlard, H., Dupont, S., Hermansky, H., & Morgan, N. (1996). Towards sub-band-based speech recognition. In "EUSIPCO (1996)". -.