Our Research

We are established experts in the scientific research community holding PhD degrees in machine learning related fields, and having more than 15 years of research experience in state-of-the-art high-end technological research and development projects, with numerous publications in peer-reviewed journals, international conferences and book chapters. Our research has focused on several areas such as computer vision, visual relationships detection, recommender systems, transfer learning, continual learning, automatic speech recognition, human action/activity recognition and multimodal gesture, multiple sensors’ and modalities’ fusion, natural language processing, object recognition and sign language modeling and recognition. We have also strong a interest in HRI, assistive and biomedical interdisciplinary applications. Next, follows a list of our recent publications:
  1. A community effort to discover small molecule SARS-CoV-2 inhibitors, (under submission) 2023, [preprint]
  2. Α. Krasoulis, N. Antonopoulos, V. Pitsikalis, S. Theodorakis, "DENVIS: Scalable and high- throughput virtual screening using graph neural networks with atomic and surface protein pocket features", Journal of Chemical Information and Modeling (in press) 2022, [doi, preprint]
  3. P. Katsileros, N. Mandilaras, D. Mallis, V. Pitsikalis, S. Theodorakis, G. Chamiel, "An Incremental Framework for Large- scale CTR Prediction", RecSys, 2022
  4. M. Diomataris, N. Gkanatsios, V. Pitsikalis, P. Maragos, Grounding Consistency: Distilling Spatial Common Sense for Precise Visual Relationship Detection", ICCV, 2021
  5. N. Gkanatsios, V. Pitsikalis, P. Maragos, From Saturation to Zero-Shot Visual Relationship Detection Using Local Context", BMVC, 2020
  6. N. Gkanatsios, V. Pitsikalis, P. Koutras, P. Maragos, "Attention-Translation-Relation Network for Scalable Scene Graph Generation", Scene Graph Representation and Learning, ICCVW, 2019
  7. N. Gkanatsios, V. Pitsikalis, P. Koutras, A. Zlatintsi, P. Maragos, "Showcasing Deeply Supervised Multimodal Attentional Translation Embeddings: a Demo for Visual Relationship Detection", International Conference of Image Processing (ICIP), 2019.
  8. N. Gkanatsios, V. Pitsikalis, P. Koutras, A. Zlatintsi, P. Maragos, "Deeply Supervised Multimodal Attentional Translation Embeddings for Visual Relationship Detection", International Conference of Image Processing (ICIP), 2019
  9. Y. Zeldes, S. Theodorakis, E. Solodnik, A. Rotman, G. Chamiel, D. Friedman, “Deep density networks and uncertainty in recommender systems”, KDD 2017
We have accumulated rich experience in research and innovation projects, having participated in 7 National, 6 FP6/7 and 3 H2020 EU funded projects.
Next, follows a list of selected recent projects that Deeplab members have participated:
  1. MOBOT: Intelligent Active MObility Assistance RoBOT integrating Multimodal Sensory Processing, Proactive Autonomy and Adaptive Interaction", European Union FP7: Specific Targeted Research-Innovation Project (STREP), 2013-2016. [ V. Pitsikalis while at cvsp.cs.ntua.gr ]
  2. MMGest: “Multimodal Gesture Recognition for Paraplegics”, Onassis Foundation, 2014-2016.
  3. I-SUPPORT: “A service robotics system for bathing tasks”, Sponsor: European Union Horizon 2020, 2015-2017. [ V. Pitsikalis while at cvsp.cs.ntua.gr ]
  4. BabyRobot: “Child-Robot Communication and Collaboration", European Union Horizon 2020 (Research and Innovation Action), 2016-2018. [ N. Katsamanis, V. Pitsikalis while at cvsp.cs.ntua.gr ]
  5. DIRHA: Distant-Speech Interaction for Robust Home Applications", European Union FP7: Specific Targeted Research-Innovation Project (STREP). [ N. Katsamanis while at cvsp.cs.ntua.gr ]
  6. Dicta-Sign: “Sign Language Recognition, Generation and Modeling with Application in Deaf Communication" European Union: FP7, Specific Targeted Research-Innovation Project. [ S. Theodorakis, V. Pitsikalis while at cvsp.cs.ntua.gr ]