Introduction

About Me

Greetings! My name is Hoàng-Ân Lê. I am from Ho Chi Minh city, Vietnam.

I obtained the PhD degree in Computer Science in 2021 from the Computer Vision lab, University of Amsterdam under the supervision of Prof. Theo Gevers and Dr. Thomas Mensink. The doctoral study was fully funded by the EUHorizon 2020 program within the TrimBot2020 project. My doctoral thesis is titled Outdoor Image Understanding from Multiple Vision Modalities.

I have been a regular reviewer for several high-ranking conferences and journals, including CVPR (IEEE/CVF), BMVC (BMVA), WACV (IEEE/CVF), ACCV (AFCV), JSTARS (IEEE)

My CV can be found here , last updated in Sep 2025.

  • [March 2026] Accepted paper. "Leveraging Membership Inference Attacks for Privacy Measurement in Federated Learning for Remote Sensing Images", joint work with Anh-Kiet Duong, Petra Gomez-Krämer, and Minh-Tan Pham is accepted for IGARS'26.
  • [June 2025] Meta-reviewer for WACV 2026 conference.
  • [Mar 2025] Outstanding reviewer recognition for the WACV 2025 conference.
  • [Aug 2024] Accepted paper. "Box for Mask and Mask for Box: weak losses for multi-task partially supervised learning", joint work with Minh-Tan Pham and Paul Berg, is accepted for BMVC'24.
  • [Apr 2024] Accepted paper. "Leveraging feature communication in federated learning for remote sensing image classification", joint work with Anh-Kiet Duong and Minh-Tan Pham, is accepted for IGARSS'24
  • [Apr 2024] Accepted paper. "Leveraging knowledge distillation for partial multi-task learning from multiple remote sensing datasets", joint work with Minh-Tan Pham, is accepted for IGARSS'24
  • [Aug 2023] Accepted paper. "Data exploitation: multi-task learning of object detection and semantic segmentation on partially annotated data", joint work with Minh-Tan Pham, is accepted for BMVC'23.
  • [Jul 2023] Accepted paper. "Self-Training and Multi-Task Learning for Limited Data: Evaluation Study on Object Detection", joint work with Minh-Tan Pham, is accepted for the ICCV'23 workshop LIMIT23.
  • [Apr 2023] Accepted paper. "Knowledge Distillation for Object Detection: from generic to remote sensing datasets", joint work with Minh-Tan Pham, is accepted for IGARSS'23
  • [Nov 2022] Outstanding reviewer recognition for the BMVC 2022 conference.
  • [Aug 2022] Accepted paper. "Mutual Guidance Meets Supervised Contrastive Learning: Vehicle Detection in Remote Sensing Images", joint work with Zhang, Pham, Lefèvre, is accepted for Remote Sensing journal
  • [Mar 2022] Accepted papers. "Detection of Degraded Acacia tree species using deep neural networks on uav drone imagery", and "CroCo: Cross-Modal Contrastive learning for localization of Earth Observation data" are accepted for XXIV ISPRS Congress.
  • [Feb 2022] I am joining the ROMMEO project on "Robust multitask learning via mutual knowledge distillation for earth observation" working with Dr. Minh-Tan Pham
  • [Sep 08th, 2021] Accepted paper. Our paper titled Automatic Generation of Dense Non-rigid Optical Flow, joint work with Nimbhorkar, Mensink, Baslamisli, Karaoglu, Gevers, is accepted for CVIU.
  • [May 28th, 2021] Accepted paper. Anil's paper titled ShadingNet: Image Intrinsics by Fine-Grained Shading Decomposition, joint work with Das, Karaoglu, Gevers, is accepted for IJCV.
  • [May 18th, 2021] I have successfully defended my doctoral thesis, titled Outdoor Image Understanding from Multiple Vision Modalities.
  • [Jan 2021] I am joining the France Énergies Marine as a post doctoral researcher for development of artificial intelligence for multimodal analysis on the OWFSOMM project.
  • [Nov 2020] Accepted paper. Our paper titled EDEN: Multimodal Synthetic Dataset of Enclosed GarDEN Scenes, joint work with Das, Mensink, and Gevers, is accepted for WACV'21.
  • [Oct 2020] Accepted paper. Our paper titled Object features and face detection performance: Analyses with 3D-rendered synthetic data, joint work with Han, Karaoglu, and Gevers, is accepted for ICPR'20.
  • [Aug 2020] Accepted paper. Our paper titled Novel View Synthesis from Single Images via Point Cloud Transformation, joint work with Mensink, Das, and Gevers, is accepted for BMVC'20
  • [Oct 2019] Being interviewed for the TrimBot2020 project's Human Face of Robotics and featured on the Newsletter of the UvA.
  • [Jan 23rd, 2019] Accepted paper. Our paper discussing The Second Workshop on 3D Reconstruction Meets Semantics: Challenge Results Discussion at ECCV'18 is now onlined, joint work with Tylecek, Sattler, Brox, Pollefeys, Fisher, and Gevers.
  • [Jul 11th, 2018] Taking part in the challenge organizers of the ECCV'18 workshop 3D Reconstruction Meet Semantics
  • [Jul 6th, 2018] Accepted paper. Our paper titled Three for one and one for three: Flow, Segmentation, and Surface Normal, joint work with Baslamisli, Mensink, and Gevers, is accepted for Oral presentation at BMVC'18 (acceptance rate 4.3%).
  • [Jul 3rd, 2018] Accepted paper. Our paper titled Joint Learning of Intrinsic Images and Semantic Segmentation and Surface Normal, joint work with Baslamisli, Groenestege, Das, Karaoglu, and Gevers, is accepted for ECCV'18.
  • [Feb 20th, 2018] Accepted paper. Our paper titled CNN based Learning using Reflection and Retinex Models for Intrinsic Image Decomposition, joint work with Baslamisli and Gevers, is accepted for CVPR'18.
  • [Mar 31st, 2017] Our project hosts the ICCV'17 workshop named 3D Reconstruction Meet Semantics.
  • [Oct 6th, 2016] Student volunteer for European Conference in Computer Vision (ECCV) 2016 in Amsterdam, the Netherlands.
  • [Sep 1st, 2016] Visiting the University of Edinburgh, Scotland, UK for TrimBot2020 consortium | photo.
  • [May 11th, 2016] Joining the TrimBot2020 consortium at the University of Groningen, the Netherlands | photo.
  • [Apr 1st, 2016] Joining the Computer Vision lab, University of Amsterdam for PhD research on 3D Scene Understanding
  • [Sep 1st, 2015] Graduate at EURECOM insitute, Télécom ParisTech with diplôme d'Ingénieur (Master of Science degree in Engineering)
  • [Mar 1st, 2015] Visiting scholar at Coordinate Science Lab (CSL), University of Illinois at Urbana-Champaign, USA for 6-month graduation project.
|

Following is the list of the wonderful people with whom I have had a chance to work.

  • Prof. Sébastien Lefèvre
  • Dr. Minh-Tan Pham
  • Prof. Theo Gevers (UvA, Ph.D promotor)
  • Dr. Thomas Mensink (UvA, Ph.D co-promotor)
  • Anil Baslamisli
  • Prof. Minh Do (UIUC, Master thesis advisor)
  • Prof. Benoit Huet
  • Quoc-Minh Bui
  • Assoc/Prof. Minh-Triet Tran (HCMUS-VNU, Bachelor thesis advisor)
  • Truong-An Pham
  • Khoi-Nguyen C. Mac
  • Minh-Thong Doan
  • SUPERVISION

  • 2024 Anh-Kiet Duong (Université de Limoges), Towards Privacy-Preserving Federated Learning Across Multiple Datasets, co-supervised with Dr. Minh-Tan Pham
  • 2021 Wei-Hsin Tseng, (Copernicus Master in Digital Earth program, Université Bretagne-Sud), Contrastive Learning for Localizing Elevation Data, co-supervised with Sébastien Lefèvre, Dirk Tiede, and Alexandre Boulch.
  • Research

    Publications

    List of publications on Goole Scholar

    le21eden

    EDEN: Multimodal Synthetic Dataset of Enclosed GarDEN Scenes

    Hoàng-Ân Lê, Partha Das, Thomas Mensink, Theo Gevers
    arxiv | project page |
    le20bmvc

    Novel View Synthesis from Single Images via Point Cloud Transformation

    Hoàng-Ân Lê, Thomas Mensink, Partha Das, Theo Gevers
    arxiv | project page |
    le18bmvc

    Three for one and one for three: Flow, Segmentation, and Surface Normals

    Hoàng-Ân Lê, Anil Baslamisli, Thomas Mensink, Theo Gevers
    arxiv | project page |
    baslamili18eccv

    Joint Learning of Intrinsic Images and Semantic Segmentation

    Anil S. Baslamisli, Thomas Tiel Groenestege, Partha Das, Hoàng-Ân Lê, Sezer Karaoglu, Theo Gevers
    arxiv | project page | code |
  • Hoàng-Ân Lê, Outdoor Image Understanding from Multiple Vision Modalities, Doctoral Thesis at University of Amsterdam, 2021 | project page |
  • JOURNALS

  • Hoàng-Ân Lê, Florent Guiotte, Minh-Tan Pham, Sébastien Lefèvre, Thomas Corpetti, Learning Digital Terrain Models From Point Clouds: ALS2DTM Dataset and Rasterization-Based GAN, in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing (JSTARS), 2022 |
  • Hoàng-Ân Lê, Heng Zhang, Minh-Tan Pham, Sébastien Lefèvre, Mutual Guidance Meets Supervised Contrastive Learning: Vehicle Detection in Remote Sensing Images, in Remote Sensing, 2022 |
  • Hoàng-Ân Lê, Tushar Nimbhokar, Thomas Mensink, Anil S. Baslamisli, Sezer Karaoglu, Theo Gevers, Automatic generation of dense non-rigid optical flow, in Computer Vision and Image Understanding (CVIU), 2021 |
  • Anil S. Baslamisli, Partha Das, Hoàng-Ân Lê, Sezer Karaoglu, Theo Gevers, ShadingNet: Image Intrinsics by Fine-Grained Shading Decomposition, in International Journal of Computer Vision (IJCV), 2021 |
  • Hoàng-Ân Lê, Minh-Thong Doan, Minh-Triet Tran, Webcam-based Laser Dot Detection Technique in Computer Remote Control, in International Conference on Theories and Applications of Computer Science: Special issue of the Journal of Science and Technology (ICTACS), 2010 | slides | demo |
  • CONFERENCES

  • Anh-Kiet Duong, Petra Gomez-Krämer, Hoàng-Ân Lê, Minh-Tan Pham, Leveraging Membership Inference Attacks for Privacy Measurement in Federated Learning for Remote Sensing Images, in IEEE International Geoscience and Remote Sensing Symposium (IGARSS), 2026 | arxiv |
  • Hoàng-Ân Lê; Minh-Tan Pham, Box for Mask and Mask for Box: weak losses for multi-task partially supervised learning, in British Machine Vision Conference (BMVC), 2024 | arxiv | project page |
  • Anh-Kiet Duong, Hoàng-Ân Lê, Minh-Tan Pham, Leveraging feature communication in federated learning for remote sensing image classification, in IEEE International Geoscience and Remote Sensing Symposium (IGARSS), 2024 | arxiv |
  • Hoàng-Ân Lê, Minh-Tan Pham, Leveraging knowledge distillation for partial multi-task learning from multiple remote sensing datasets, in IEEE International Geoscience and Remote Sensing Symposium (IGARSS), 2024 | arxiv |
  • Hoàng-Ân Lê; Minh-Tan Pham, Novel View Synthesis from Single Images via Point Cloud Transformation, in British Machine Vision Conference (BMVC), 2023 | arxiv | project page |
  • Hoàng-Ân Lê, Minh-Tan Pham, Knowledge Distillation for Object Detection: from generic to remote sensing datasets, in IEEE International Geoscience and Remote Sensing Symposium (IGARSS), 2023 | arxiv |
  • Anne Achieng Osio, Hoàng-Ân Lê, Samson Ayugi, Fred Onyango, Peter Odwe, Sébastien Lefèvre, Detection of Degraded Acacia tree species using deep neural networks on uav drone imagery, in ISPRS Annals of the Photogrammetry, 2022 | arxiv |
  • Wei-Hsin Tseng, Hoàng-Ân Lê, Alexandre Boulch, Sébastien Lefèvre, Dirk Tiede, CroCo: Cross-Modal Contrastive learning for localization of Earth Observation data, in ISPRS Annals of the Photogrammetry, 2022 | arxiv |
  • Hoàng-Ân Lê, Partha Das, Thomas Mensink, Theo Gevers, EDEN: Multimodal Synthetic Dataset of Enclosed GarDEN Scenes, in Winter Conference of Applications on Computer Vision (WACV), 2021 | arxiv | project page |
  • Jian Han, Sezer Karaoglu, Hoàng-Ân Lê, Theo Gevers, Object features and face detection performance: Analyses with 3D-rendered synthetic data, in International Conference on Pattern Recognition (ICPR), 2020 | arxiv |
  • Hoàng-Ân Lê, Thomas Mensink, Partha Das, Theo Gevers, Novel View Synthesis from Single Images via Point Cloud Transformation, in British Machine Vision Conference (BMVC), 2020 | arxiv | project page |
  • Hoàng-Ân Lê, Anil Baslamisli, Thomas Mensink, Theo Gevers, Three for one and one for three: Flow, Segmentation, and Surface Normals, in British Machine Vision Conference (BMVC), 2018 | arxiv | project page |
  • Anil S. Baslamisli, Thomas Tiel Groenestege, Partha Das, Hoàng-Ân Lê, Sezer Karaoglu, Theo Gevers, Joint Learning of Intrinsic Images and Semantic Segmentation, in European Conference in Computer Vision (ECCV), 2018 | arxiv | project page | code |
  • Anil S. Baslamisli, Hoàng-Ân Lê, Theo Gevers, CNN based Learning using Reflection and Retinex Models for Intrinsic Image Decomposition, in Computer Vision and Pattern Recognition (CVPR), 2018 | arxiv | project page |
  • I. Pratikakis, M. A. Savelonas, F. Arnaoutoglou, G. Ioannakis, A. Koutsoudis, T. Theoharis, M.-T. Tran, V.-T. Nguyen, V.-K. Pham, H.-D. Nguyen, Hoàng-Ân Lê, B.-H. Tran, Q. H. To, M.-B. Truong, T. V. Phan, M.-D. Nguyen, T.-A. Than, K.-N. C. Mac, M. N. Do, A-D. Duong, T. Furuya, R. Ohbuchi, M. Aono, S. Tashiro, D. Pickup, X. Sun, P. L. Rosin, R. R. Martin, Partial Shape Queries for 3D Object Retrieval, in Eurographics 2016 Workshop on 3D Object Retrieval, 2016 |
  • Hoàng-Ân Lê, Khoi-Nguyen C. Mac, Truong-Ân Pham, Vinh-Tiep Nguyen, Minh-Triet Tran, Multimodal Smart Interactive Presentation System, in International Conference on Human-Computer Interaction (HCII), 2013 | demo |
  • Hoàng-Ân Lê, Khoi-Nguyen C. Mac, Truong-Ân Pham, Minh-Triet Tran, Realtime Pointing Gesture Recognition and Applications in Multi-user Interaction, in Asian Conference on Intelligent Information and Database Systems (ACIIDS), 2013 | demo |
  • Hoàng-Ân Lê, Khoi-Nguyen C. Mac, Truong-Ân Pham, Vinh-Tiep Nguyen, Minh-Triet Tran, And-Duc Duong, SIM-Smart Interactive Map with Pointing Gestures, in International Conference on Intelligent Human-Machine Systems and Cybernetics (IHMSC), 2012 | demo |
  • WORKSHOPS

  • Radim Tylecek, Torsten Sattler, Hoàng-Ân Lê, Thomas Brox, Marc Pollefeys, Robert B. Fisher, Theo Gevers, The Second Workshop on 3D Reconstruction Meets Semantics: Challenge Results Discussion, in European Conference in Computer Vision (ECCV) Workshop, 2018 | project page |
  • Maria Eskevich, Quoc-Minh Bui, Hoàng-Ân Lê, Benoit Huet, Exploring Video Hyperlinking in Broadcast Media, in Workshop on Speech, Language, and Audio in Multimedia (SLAM), 2016 |
  • Hoàng-Ân Lê, Quoc-Minh Bui, Benoit Huet, Barbora Cervenkova, Jan Bouchner, Evlampios Apostolidis, Fotini Markatopoulou, Alexandros Pournaras, Vasileios Mezaris, Daniel Stein, S. Eickeler, M. Stadtschnitzer, LinkedTV at MediaEval 2014 Search and Hyperlinking Task, in MediaEval Benchmarking Initiative for Multimedia Evaluation Workshop, 2014 |