Welcome
I am a third-year PhD Student the University of Stuttgart, Germany advised by Prof. Andreas Bulling. My research focuses broadly on multi-modal deep models at the intersection of computer vision and natural language processing. Specifically, I develop novel AI model especially geared towards conversational tasks such as visual and video dialog. Furthermore, I research efficient mechanisms of marrying graph neural networks with large multi-modal transformers. Finally, I develop pre-training strategies of multi-modal foundation models specifically geared towards improving the downstream visual/video conversational tasks. I hold a BSc and a MSc degrees in the elite study program Simulation Technology at the University of Stuttgart. The latter was awarded with distinction and received the outstanding work award from the Industrial Consortium SimTech (IC SimTech).
News
- [20.02.2024] 🔥 One paper got accepted to COLING’24, Turin, Italy 🇮🇹
- [01.02.2024] 🆕 Started an internship at the Multimodal AI lab, TU Darmstadt with Marcus Rohrbach and Anna Rohrbach
- [01.11.2023] 📜 Reviewing for ACL Rolling Review’23-24
- [24.10.2023] 🔥 One paper got accepted to WACV’24, Hawaii, USA 🇺🇸
- [29.09.2023] 📜 Reviewing for CHI’24
- [15.04.2023] 📜 Reviewing for ACM MM’23
- [02.02.2023] 📜 Reviewing for the Journal of Artificial Intelligence’23
- [16.08.2022] 🔥 One paper got accepted to COLING’22 (oral), Gyeongju, Korea 🇰🇷
- [27.03.2022] 🔥 One paper got accepted to ACL-W’22, Dublin, Ireland 🇮🇪
- [01.04.2021] 🥇 My master’s thesis received the the outsanding work award from IC SimTech
- [28.02.2021] 🎓 I defended my MSc Thesis with distinction
Publications
OLViT: Multi-Modal State Tracking via Attention-Based Embeddings for Video-Grounded Dialog
Published in International Conference on Computational Linguistics (COLING), 2024
Adnen Abdessaied, Manuel von Hochmeister, Andreas Bulling. [Paper] [Code]
VD-GR: Boosting Visual Dialog with Cascaded Spatial-Temporal Multi-Modal GRaphs
Published in IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2024
Neuro-Symbolic Visual Dialog
Published in International Conference on Computational Linguistics (COLING), 2022
Adnen Abdessaied, Mihai Bace, Andreas Bulling. [Paper] [Code]
Video Language Co-Attention with Multimodal Fast-Learning Feature Fusion for VideoQA
Published in Workshop on Representation Learning for NLP @ ACL, 2022
Adnen Abdessaied, Ekta Sood, Andreas Bulling. [Paper] [Code]