Positions & Visits
- Present | Senior CNRS Researcher (HDR) at the LIP6 Lab, UPMC, Sorbonne University, France
- 2007–2017 | Senior CNRS Researcher (HDR since 2011) at the LTCI Lab, TELECOM ParisTech, France
- Invited Visiting Researcher at the "Google Faculty Summit", Google, London, UK (September 2012)
- Invited Visiting Associate Professor at the Institute of Automation, Chinese Academy of Science, Beijing, China (October 2009)
- 2006–2007 | Senior Research Associate at ENPC (Chargé de Recherche), Certis Lab, ENPC (joint with ENS-ULM and INRIA-Sophia), France
- 2005–2006 | Research Associate at the Machine Intelligence Lab, Cambridge University, UK
- 2004–2005 | Research Assistant at INRIA-Rocquencourt, France
- 2003–2004 | Post-doctoral Fellow at the Fraunhofer Gesellschaft (GMD Institute), Darmstadt, Germany
- 2000–2003 | PhD Candidate with Professor Donald Geman, INRIA Rocquencourt, France (Defense: April 07, 2003)
- Invited Visiting PhD Student at the Center for Imaging Science, Johns Hopkins University (Dec 2001 & Sept 2002)
Research Interests & Applications
Methodology
Deep Learning & Generative Modeling: Flow-based models, stable invertible networks.
Statistical ML: Deep kernels, Graph Convolutional Networks (GCNs).
Optimization: Label-efficient/Continual learning, network compression/pruning.
Applications
- Autonomous Driving (Scene/Optical Flow)
- Action Recognition (Skeleton/Visual Speech)
- Remote Sensing (Satellite Image Change Detection)
- 3D/4D Point Cloud Modeling
Awards & Recognition
- 2013 | Best Paper Award Nomination (top 10 papers) for "Semantic Subspace Learning for Mental Search in Satellite Images" | IEEE IGARSS
- 2013 | Challenge Winner (1st out of 58 participant runs), Scalable Concept Image Annotation Challenge | ImageCLEF
- 2010 | Best Paper Award Saburo Tsuji Award for "Context Based Support Vector Machines for Interconnected Image Annotation" | Oral acceptance rate: 4.7% | ACCV
- 2008 | Best Paper Award | IEEE CBMI
ORGANIZING-COMMITTEES, MEMBERSHIPS, SCIENTIFIC AND ADMINISTRATIVE RESPONSIBILITIES
Editorial Boards
- IEEE Transactions on Image Processing (TIP): Senior Associate Editor (2024–Present) | Associate Editor (2019–2024)
- Signal Processing: Image Communication (Elsevier): Associate Editor (2017–Present)
- Journal of Imaging: Associate Editor (2020–Present)
- ISTE/Wiley ("SCIENCE Project"): Theme Editorial Board Head (2018–2025)
Organization Assistance and Conference Memberships
- IEEE ICIP (Int. Conf. on Image Processing): Area Chair | 2019, 2020, 2021, 2022, 2023, 2024, 2025, 2026
- IEEE ICME (Int. Conf. on Multimedia and Expo): Area Chair | 2026
- ICIAP (International Conf. on Image Analysis and Processing, IAPR): Track Area Chair (Brave New Ideas) | 2023
- NeurIPS: Technical Program Committee (WANT – Workshop on Advancing Neural Network Training: Computational Efficiency, Scalability, and Resource Optimization) | 2023
- ICML (Int. Conf. on Machine Learning): Technical Program Committee
- 2025: DataWorld Workshop (Unifying Data Curation Frameworks Across Domains)
- 2024: WANT Workshop (Advancing Neural Network Training: Computational Efficiency, Scalability, and Resource Optimization)
- ECML (European Conf. on Machine Learning): Technical Program Committee
- 2023: Workshop on Simplification, Compression, Efficiency and Frugality for Artificial intelligence
- 2008: Main Conference
- RFIAP / RFIA (Reconnaissance des Formes et Intelligence Artificielle): Technical Program Committee | 2006, 2016, 2018, 2020, 2022, 2024, 2026
- ECCV (European Conf. on Computer Vision): Technical Program Committee (Workshop on Web-scale Vision and Social Media) | 2012
- CVPR / ICCV / ECCV: Active Reviewer | 2009–Present
Sessions Chairing
- ACM MM: 2025
- IEEE ICIP: 2025, 2024, 2021, 2020, 2019, 2012, 2009
- IEEE ICASSP: 2024, 2021, 2019
- IEEE IGARSS: 2023, 2013
Committees & Responsibilities
- Member of the CES 23 AI (Phases 1 and 2): Scientific Evaluation Committee in Artificial Intelligence at the ANR (French Research Agency) | 2025–Present
- PhD Thesis Jury Memberships: Rapporteur, Examiner and President for more than 30 PhD theses | 2010–Present
- Recruitment Committees:
- Associate Professor level: CNAM Paris (2019), INSA Lyon (2018), UPMC (2009, 2010), CNRS (2009), Telecom ParisTech (2008)
- Doctoral level: UPMC EDITE School (2018)
- Project Leadership: ANR MLVIS National Project Leader | 2012–2016
- GIS: Scientific Interest Group (Groupe d'Intérêt Scientifique) between LIP6/UPMC and LTCI/Telecom ParisTech | Elected Member and Coordinator of the Machine Learning and Information Retrieval theme | 2009–2011
- Parisian Seminar: Founder and Organizer of the Machine Learning and Computer Vision Seminar at TELECOM ParisTech | 2008–2016
Selected Publications (Rank A*/A conferences) + Major Journals
Y. Huang, J. Mei, Z. Wu, Y. Yang, H. Zhao, M. Jiu, H. Sahbi. Less Is Better: Sparse Instance Learning for Cross-Domain Few-Shot Object Detection. In the 40th Annual AAAI Conference on Artificial Intelligence (AAAI). 2026. [Link]
V. Enescu, H. Sahbi. Learning conditionally untangled latent spaces using Fixed Point Iteration. In the 35th British Machine Vision Conference (BMVC). 2024. [Link]
R. Marsal, F. Chabot, A. Loesch, W. Grolleau, H. Sahbi. MonoProb: Self-Supervised Monocular Depth Estimation with Interpretable Uncertainty. In WACV. 2024. [Link]
R. Marsal, F. Chabot, A. Loesch, H. Sahbi. BrightFlow: Brightness-Change-Aware Unsupervised Learning of Optical Flow. In WACV. 2023. [Link]
M. Jiu and H. Sahbi. Context-Aware Deep Kernel Networks for Image Annotation. In Neurocomputing Journal. 2022. [Link]
H. Sahbi. Learning Laplacians in Chebyshev Graph Convolutional Networks. In ICCV, DLGC. 2021. [Link]
H. Sahbi and H. Zhan. FFNB: Forgetting-Free Neural Blocks for Deep Continual Learning. In BMVC. 2021. [Link]
A. Mazari and H. Sahbi. MLGCN: Multi-Laplacian Graph Convolutional Networks for Human Action Recognition. In BMVC. 2019. [Link]
A. Dutta and H. Sahbi. Stochastic Graphlet Embedding. In IEEE Transactions on Neural Networks and Learning Systems (TNNLS). 2019. [Link]
M. Jiu and H. Sahbi. Nonlinear Deep Kernel Learning for Image Annotation. In IEEE Transactions on Image Processing (TIP). 2017. [Link]
H. Sahbi. Interactive Satellite Image Change Detection with Context-Aware Canonical Correlation Analysis. In IEEE GRSL. 2017. [Link]
L. Wang and H. Sahbi. Directed Acyclic Graph Kernels for Action Recognition. In ICCV. 2013. [Link]
H. Sahbi, L. Ballan, G. Serra, A. Del Bimbo. Context-Dependent Logo Matching and Recognition. In IEEE TIP. 2013. [Link]
P-D. Vo, H. Sahbi. Spacious: an Interactive Mental Search Interface. In ACM SIGIR. 2013. [Link]
F. Yuan, G-S. Xia, H. Sahbi and V. Prinet. Mid-level Features and Spatio-Temporal Context for Activity Recognition. In Pattern Recognition. 2012. [Link]
H. Sahbi, J-Y. Audibert and R. Keriven. Context-Dependent Kernels for Object Classification. In IEEE PAMI. 2011. [Link]
H. Sahbi and X. Li. Context Based Support Vector Machines for Interconnected Image Annotation. The Saburo Tsuji Best Paper Award In ACCV. 2010. [Link]
H. Sahbi and X. Li. Context Dependent SVMs for Interconnected Image Network Annotation. In ACM Multimedia. 2010. [Link]
H. Sahbi, J-Y. Audibert, J. Rabarisoa and R. Keriven. Robust Matching and Recognition using Context-Dependent Kernels. In ICML. 2008. [Link]
H. Sahbi, P. Etyngier, J-Y Audibert and R. Keriven. Manifold Learning using Robust Graph Laplacian for Interactive Image Retrieval. In CVPR. 2008. [Link]
H. Sahbi, J-Y. Audibert, J. Rabarisoa and R. Keriven. Context-Dependent Kernel Design for Object Matching and Recognition. In CVPR. 2008. [Link]
H. Sahbi, J-Y Audibert and R. Keriven. Graph-Cut Transducers for Relevance feedback in Content Based Image Retrieval. In ICCV. 2007. [Link]
H. Sahbi. Kernel PCA for Similarity Invariant Shape Recognition. In Neurocomputing Journal. 2007. [Link]
H. Sahbi and D. Geman. A Hierarchy of Support Vector Machines for Face Detection. In JMLR. 2006. [Link]
All Publications: [Google Scholar] [DBLP]
Past and Current Projects
- ANR PICNICS: AI for Point Cloud Analysis | Local Principal Investigator | 2025–2029
- CEA bilateral project: Scene flow estimation using deep learning | Global Principal Investigator | 2021–2025
- Thales bilateral project: Active learning for remote sensing object recognition | Global Principal Investigator | 2019–2023
- Netatmo bilateral project: Efficient deep learning | Global Principal Investigator | 2019–2023
- XXII bilateral project: Deep continual learning | Global Principal Investigator | 2019–2023
- DCNS bilateral project: Attribute and deep learning for remote sensing ship category recognition | Global Principal Investigator | 2015–2018
- ANR MLVIS: Statistical learning for image annotation | Global Principal Investigator | 2012–2016
- Digiteo Project REMI: Machine learning for social networks | Local Principal Investigator | 2012–2015
- PARROT bilateral project: Lip reading | Global Principal Investigator | 2011–2014
- CNES Projects VENISE/Varissat: Visualization, exploration, navigation in remote sensing satellite images | Global Principal Investigator | 2010–2012
- EADS bilateral project: Remote sensing change detection | Global Principal Investigator | 2010–2013
- Digiteo Project RELIR: Relational machine learning for information retrieval | Local Principal Investigator | 2010–2013
- Digiteo Project VisuNet: Visual information recognition and search in camera networks | Local Principal Investigator | 2010–2013
- EIFFEL French-Chinese bilateral project: Action recognition in videos | Global Principal Investigator | 2010–2011
- ANR AVEIR: Image Annotation and Retrieval | Local Principal Investigator | 2007–2010
- ANR SURF: Statistical Learning | Project Participant | 2006–2009
- AGILE-DARPA: Speech and statistical machine translation (Partners: Cambridge, BBN, ISI, IBM, Stanford, JHU, etc.) | Project Participant | 2005–2006
- Sagem: Mental face retrieval | Project Participant | 2004–2005
- MediaWorks: Face indexing and retrieval in video | Project Participant | 2003
Supervision & Mentoring
Supervised PhD Students (as Thesis Director)
- 2022–2025: Victor Enescu (PhD Student at LIP6 Lab, Sorbonne University): Flow-based models for continual and frugal learning | Thesis defense: Sept 2025
- 2021–2024: Remi Marsal (PhD Student at LIP6 lab, Sorbonne University and CEA): Scene flow estimation using deep learning | Thesis defense: May 2024
- 2019–2023: Robin Dupont (PhD Student at LIP6 Lab, Sorbonne University): Efficient deep learning and model compression | Thesis defense: Dec 2023
- 2019–2023: Sebastien Deschamps (PhD Student at LIP6 Lab, Sorbonne University): Active learning for remote sensing object recognition | Thesis defense: June 2023
- 2017–2020: Ahmed Mazari (PhD Student at LIP6 Lab, Sorbonne University): Deep learning for action recognition | Thesis defense: Sept 2020
- 2016–2020: Tristan Postadjian (PhD Student between IGN Paris and UPMC SU, currently Researcher at Sodexo Group): High Resolution Remote Sensing Satellite Imagery for Soil Occupancy | Thesis defense: Feb 2020
- 2015–2018: Quentin Oliveau (CIFRE PhD Student at TELECOM ParisTech, currently Researcher at DCNS Group): Attribute Learning for Remote Sensing Object Recognition | Thesis defense: April 2018
- 2012–2015: Ling Wang (PhD Student at TELECOM ParisTech, postdoc at ORSAM, Munich and currently at AliBaba China): Kernel methods for action recognition in videos | Thesis defense: Sept 2015
- 2011–2014: Phong Vo (PhD Student at TELECOM ParisTech, postdoc at CEA and currently CTO of KubeSee): Transductive inference for image interpretation and remote sensing image search | Thesis defense: March 2014
- 2010–2013: Nicolas Bourdis (CIFRE PhD Student at TELECOM ParisTech and EADS, currently Researcher at AIRBUS): Remote sensing change detection | Thesis defense: May 2013
- 2010–2012: Fei Yuan (PhD Student at TELECOM ParisTech in collaboration with NLPR, Chinese Academy of Science, currently Researcher at NLPR): Graph based techniques for Event Detection and Recognition | Thesis defense: June 2012
- 2008–2010: Thibault Napoleon (PhD Student at TELECOM ParisTech, currently Associate Professor at ISEN-Brest): 2D to 3D Object Retrieval | Thesis defense: July 2010
Supervised Post-Docs (as Official Postdoc Director)
- 2014–2015: Anjan Dutta (Former Post-doc at LTCI, Telecom ParisTech): Graph hashing for pattern classification
- 2014–2015: Mingyuan Jiu (Former Post-doc at LTCI, Telecom ParisTech, currently Research Associate at ENS Lyon): Deep learning and kernel design image annotation
- 2012–2013: Aymen El-Ghoul (Former Post-doc at LTCI, Telecom ParisTech, currently Research Engineer at AsSystem): Manifold Learning for Remote Sensing Image Classification
- 2010: Giuseppe Serra (Former Post-doc visitor from U. of Florence, currently Research Associate at the University of Modena): Logo detection and recognition | April–June 2010
- 2009–2010: Xi Li (Former Post-doc at LTCI, Telecom ParisTech, currently Professor at Zhejiang University, China): Statistical learning and Image retrieval
- 2008–2009: Marin Ferecatu (Former Post-doc at LTCI, Telecom ParisTech, currently Associate Professor at CNAM Paris) | Jan 2008–Sept 2009
Co-Supervised & Visiting Students (Only as Co-supervisor)
- 2018–2019: Léo Andeol (M.S. Student at LIP6): PLDAC Project on graph kernels
- 2012–2014: Emilie Au (PhD Student at LIP6 and TELECOM ParisTech): Learning on graphs
- 2012: Surrender Varma (PhD Visitor from IIT India): Remote sensing change detection | April–Aug 2012
- 2011–2012: Malek Nadil (PhD Visitor from USTHB Algiers): Face processing
- 2010: Lamberto Ballan (PhD Visitor from U. of Florence, currently Research Associate at Stanford University): Logo detection and recognition
- 2008: Olivier Le Floch (B.S. Candidate from Ecole Polytechnique, Palaiseau): Image search
- 2007–2008: Jiayu Chen (Visiting PhD Student from University of Wuhan): Remote sensing image retrieval
- 2007: Bhavna Agarwal (M.S. Candidate from India): Image matching and recognition
- 2006–2008: Jaonary Rabarisoa (PhD Candidate at Certis, ENPC, currently Research Engineer at CEA): Statistical learning for object recognition
- 2006–2007: Patrick Etyngier (PhD Student at Certis, ENPC, moved to Philips Paris): Graph Laplacian for interactive image retrieval
- 2005–2006: Khe Chai Sim (Post-doc at Cambridge University, currently Professor at Institute of Digital Media, Singapore): System combination for statistical machine translation
- 2004–2007: Stefan Thiemert (PhD Candidate at Fraunhofer IPSI, Germany): Content-based video watermarking
- 2004: Varun Kumta (M.S. Candidate IIT India, currently at IBM India): Robustness of image retrieval to image watermarking
- 2003–2007: Liu Huajian (PhD Candidate at Fraunhofer IPSI, currently Research Staff at Fraunhofer SIT, Germany): Object of interest based image authentication
Biosketch
- Dr. Hichem Sahbi received his M.S. degree in theoretical computer science from the University of Paris Sud, in Orsay, France in 1999, and his PhD in computer vision and machine learning from INRIA/Versailles (currently Paris-Saclay) University, France in 2003. From 2003-2006 he was a research associate first at the Fraunhofer Institute in Darmstadt, Germany, and then at the Machine Intelligence Laboratory at Cambridge University, UK. From 2006-2007, he was a senior research associate at l'Ecole des Ponts Paris Tech, in Paris. Since 2007, he has been a CNRS researcher (and HDR) at Telecom ParisTech and then at UPMC, Sorbonne University, in Paris. Dr. Sahbi has participated in various scientific committees, industrial, national, and international projects, and he is the author of many publications. Dr. Sahbi's research interests include statistical machine and deep learning, remote sensing, computer vision, and image/information retrieval.