MAIN RESULTS OF THE PROJECT Development of a complete and operational prototype incorporating all planned features. With regard to the primary objective of our work—the development of a proactive multimodal interaction system within the context of human-robot interaction—our major contributions are: (i) An audio-visual temporal fusion model for multi-user speaker diarization, based on a model […]
News
New paper: « LLM-based Agentic Work ow on Verbal and Non-verbal Audiovisual Perceptions and Actions for Proactive Situated Human-Robot Interactions ».
Virgile Sucal, Maxime Jullien, Ahmed Njifenjou, Fabrice Lefèvre. LLM-based Agentic Work ow on Verbal and Non-verbal Audiovisual Perceptions and Actions for Proactive Situated Human-Robot Interactions. 13th International Conference on Human-Agent Interaction (HAI ’25), Nov 2025, Yokohama, Japan. 2025, 979-8-4007-2178-6/25/11. ⟨10.1145/3765766.3765797⟩. ⟨hal-05430382⟩ DOI Ref HAL
New paper « Visual emotion analysis using skill-based multi-teacher knowledge distillation »
Tristan Cladière, Olivier Alata, Christophe Ducottet, Hubert Konik, Anne-Claire Legrand. Visual emotion analysis using skill-based multi-teacher knowledge distillation. Pattern Analysis and Applications, 2025, 28 (2), pp.49. ⟨10.1007/s10044-025-01426-9⟩. ⟨ujm-05122503⟩ DOI Ref on HAL
Mr Ahmed NJIFENJOU will publicly defend his thesis entitled: «Open-domain conversational agents based on transformer-based language models: towards multilingualism and personality» supervised by Mr Fabrice LEFEVRE, on Friday 19 December 2025.
DATE AND PLACE Oral defense scheduled on Friday, 19 December 2025 at 2pmLocation: 339 Chemin des Menajaries, 84911 AvignonRoom: CERI lecture theatre DISCIPLINE Computer Science LABORATORY UPR 4128 LIA – Avignon Computing Laboratory COMPOSITION OF THE JURY Mr Fabrice LEFEVRE Avignon University Thesis supervisor Ms Lina Maria ROJAS-BARAHONA Orange Innovation Rapporteur Mr Didier SCHWAB Grenoble Alpes University […]
New paper: « Open-Source Large Language Models as Multilingual Crowdworkers: Synthesizing Open-Domain Dialogues in Several Languages With No Examples in Targets and No Machine Translation ».
Ahmed Njifenjou, Virgile Sucal, Bassam Jabaian, Fabrice Lefèvre. Open-Source Large Language Models as Multilingual Crowdworkers: Synthesizing Open-Domain Dialogues in Several Languages With No Examples in Targets and No Machine Translation. The 26th Annual Meeting of the Special Interest Group on Discourse and Dialogue, Aug 2025, Avignon, France. pp.697-749. ⟨hal-05450721⟩ Ref HAL
In 2025 LIA co-organizes SIGDIAL on « Discourse and Dialogue »
Fabrice Lefèvre, from LIA of Avignon University, co-organizes the next events of SIGDIAL. The main topic will be « Dialogue and Discourse ». More details on the website: https://2025.sigdial.org
New paper: « FlowAct: A Proactive Multimodal Human-Robot Interaction System with Continuous Flow of Perception and Modular Action Sub-Systems ».
Timothée Dhaussy, Bassam Jabaian, Fabrice Lefèvre. FlowAct: A Proactive Multimodal Human-Robot Interaction System with Continuous Flow of Perception and Modular Action Sub-Systems. 14th International Conference on Pattern Recognition Applications and Methods, Feb 2025, Porto, Portugal. pp. 771 – 779, ⟨10.5220/0013265700003905⟩. ⟨hal-05444837⟩ DOI Ref HAL
New paper: « Knowledge Amalgamation for Single-Shot Context-Aware Emotion Recognition »
Tristan Cladière, Olivier Alata, Christophe Ducottet, Hubert Konik, Anne-Claire Legrand. Knowledge Amalgamation for Single-Shot Context-Aware Emotion Recognition. 20th International Conference on Computer Vision Theory and Applications, Feb 2025, Porto, Portugal. pp.410-419,⟨10.5220/0013169800003912⟩. ⟨ujm-05122265⟩ DOI Ref HAL
PHD DEFENSE TRISTAN CLADIÈRE: « CONTEXT-AWARE EMOTION RECOGNITION: EXPLORING COMPACT ARCHITECTURES FOR SOCIAL ROBOTICS »
Monday, December 9, 2024 at 10am Telecom Saint-Etienne Amphithéâtre J02042000 Saint Etienne « Context-aware emotion recognition: exploring compact architectures for social robotics » ABSTRACT: In order to improve human-robot exchanges, it is necessary to exploit both verbal and non-verbal information emitted by humans, and to integrate them into the decision-making process of robots. The main non-verbal indicator of […]
Mr Timothée DHAUSSY will publicly defend his thesis entitled: « L’interaction humain-robot multimodal proactive dans un cadre hospitalier », on Monday 21 October 2024.
DATE AND PLACE Oral defense scheduled on Monday 21 October 2024 at 2pmVenue: 74 Rue Louis Pasteur, 84029 AvignonThesis room DISCIPLINE Computer Science LABORATORY UPR 4128 LIA – Avignon Computing Laboratory COMPOSITION OF THE JURY MR FABRICE LEFEVRE Avignon University Thesis supervisor Mr Julien PINQUIER Paul Sabatier University Rapporteur Ms Aurélie CLODIC LAAS-CNRS Rapporteur Bassam JABAIAN Avignon […]
For further information, please contact muDialBot’s coordinator: