Keywords:
- 2-D Face
- 2D attacks
- 2D Face Authentication
- 3D Face
- 3D Face Localisation
- 3D face recognition
- 3D Masks
- 3D-Rendered Datasets
- Accent Identification
- Adaboost
- adaptation
- AIM
- ALM
- analysis biometrics python tool
- anomaly detection
- Anti-spoofing
- Attack
- attribution
- audio and video classification
- Audio Language Models
- Audio-visual person authentication
- audio-visual speaker recognition
- authentication
- authentication task
- Auto-encoder
- automatic eye detectors
- Automatic Speech Recognition
- Backdoor attack
- backdoor attack detection
- batch norm
- batch normalization
- BEAT
- behavioral recognition
- Benchmark
- Benchmarking
- bi-modal authentication
- bias
- bias mitigation
- Binary features
- Biohashing
- Biometric Authentication
- biometric recognition
- biometric template protection
- Biometrics
- biometrics (access control)
- biometry
- Blackbox
- bob
- Bob toolbox
- boosting
- C++
- calibration
- calibration performance evaluation
- calibration performance metric
- Cameras
- Cascade
- categorical calibration
- CNN
- CNN Embeddings
- CNN visualization
- commercial face recognition systems
- Comparison studies
- Competition
- computational efficiency
- computer vision
- continuous speech recognition boosted binary features resource management
- Controlled Synthesis
- Convolutional neural network
- Convolutional neural network.
- Convolutional Neural Networks
- Counter-Measures
- Counter-Spoofing
- CPqD mobile biometric database
- cross-database
- cross-database testing
- cross-dataset evaluation
- crossmodal matching
- Custom 3D Silicon masks
- Custom Silicone Masks
- database
- decision trees
- deep features
- deep learning
- Deep neural network
- deep-networks
- deepfake detection
- Deepfakes
- Demographic
- Demographic bias
- demographic fairness
- detection
- diarization
- Differential Performance
- Differential Privacy
- DIHARD challenge
- Disguise
- Dishonest Acts
- dnn
- domain adaptation
- domain generalization
- dynamic Transformer
- embedding
- embedding translation
- End-to-end learning
- error characteristics
- evaluation
- Expectation maximization
- explainability
- eye detection
- eye localization errors
- eye location ambiguity
- Face
- Face Authentication
- Face Detection
- Face Editing
- Face Localisation
- face morph
- face normalization
- Face Presentation Attack Detection
- face presentation-attacks
- Face Recognition
- face recognition algorithms
- face recognition performance
- face recognition system
- face recognition systems
- face reconstruction
- face spoofing
- face verification
- FaceLLM
- facial feature alignment
- Fairness
- Fairness Evaluation.
- Feature Distribution Modelling
- Feature extraction
- Feature Fusion
- feature selection
- Ferns
- Finger vein
- finger vein recognition
- Fingers
- forensic face recognition
- Forensics
- Forgery
- Formants
- Foundation Model
- Foundation Models
- French Regional Accents
- full-view
- Full-view Authentication
- Fundamental frequency
- Fusion
- Gabor
- GANs
- Gaussian Mixture Models (GMM)
- generalization
- generation
- generative models
- GMM
- GMM Modelling
- GMM Parts-Based
- GMMs HMMs 3D facial data face verification feature distribution modelling techniques
- Haar features
- Hashing
- Heterogeneous Face Recognition
- Hill-climbing attack
- HMM
- human assisted learning
- i-vectors
- Identity
- Illumination Invariance
- Image analysis
- image forensics
- Image-to-Image Translation
- Imaging
- inconsistencies detection
- information fusion
- information leakage
- Integer Based Arithmetic
- Inter-session Variability Modelling
- iphoto
- Iris Recognition
- Joint Factor Analysis
- Kaldi toolkit
- Keystroke
- Large Language Models
- Large Multi-modal Models
- Lifelong learning
- likelihood ratio
- likelihood ratio interpretation
- linear score transformation
- linear score transformation.
- linearly calibrated face recognition scores
- linkability
- lip-syncing
- Liveness Detection
- LLM
- Local Binary Patterns
- long-term statistics
- LSTM
- LWIR
- LWIR.
- machine learning
- machine-learning software
- Makeup Attack Detection
- Makeup Attacks
- manual eye annotations
- Mask attack
- maximal leakage
- Membership Inference (MI) Attack
- Memorisation
- Miura-Match
- MLLM
- mobile biometrics
- mobile computing
- mobile environment
- MOBIO
- MOBIO database
- model pairing
- Modified Census Transform
- morph attack
- morphing
- Morphing Attack
- MSU-MFSD
- Mult-channel sensors.
- Multi-channel face-PAD
- Multi-view
- MultiLayer Perceptron (MLP)
- Multimodal
- Multimodal biometrics
- Multimodal Large Language Models
- Multimodal Large Language Models (MLLMs)
- multispectral
- Naive Bayesian
- near-infrared
- NIR
- Noise Robustness
- Old-Age Makeups
- online
- Online Platform
- open science
- Open Source
- open source implementations
- open-set classifica- tion
- open-set classification
- optimal morph
- pad eps epsc anti-spoofing fusion
- pairing
- palm vein
- parts-based approach
- pattern recognition
- Performance Evaluation
- periocular biometrics
- Periocular PAD
- Periocular Recognition
- person recognition
- Phoneme recognition
- photometric stereo
- Photorealism in Synthetic Data
- picasa
- pittpatt
- PLDA
- pose estimation
- presentation attack
- Presentation Attack Detection
- presentation attacks
- pretraining
- privacy
- Probablistic Model
- pruning
- python
- query phases
- raw waveforms
- Realism Transfer
- recognition
- redundancy
- regularization
- Remote photoplethysmography
- Replay
- Replay Attacks
- Replay-Attack
- Replay-Mobile
- Reproducibility Criteria
- Reproducible research
- residual CNN
- RGB/depth cameras
- rotation invariant cross-correlation
- score fusion
- security
- security of data
- semantic segmentation
- session variability
- Shape descriptor
- signal processing
- single-channel and multi-channel speech
- Smartphones
- software
- Software Frameworks
- speaker anti-spoofing
- Speaker Authenitcation
- speaker database
- Speaker Diarization
- Speaker identification
- speaker recognition
- speaker recognition field
- speaker verification
- speaker verification ferns XM2VTS
- speaker-specific features
- spectral statistics
- Spoofing
- Spoofing Attacks
- Spoofing attacks fingervein
- statistical hypothesis testing
- StyleGAN 2
- supervised adaptation
- surveillance camera face databases
- SVM
- Synthetic Data
- Synthetic Dataset
- Taxonomy
- template
- template inversion
- template protection
- temporal pattern extraction
- test
- Textual Explanation
- Texture Analysis
- Texture Descriptor
- thermal cameras
- tool
- toolbox
- transfer learning
- transformers
- Trick
- Trojan
- trojan attack
- trustworthy
- Trustworthy AI
- Unseen Attack Detection.
- vascular biometrics
- vein enhancement
- Vein recognition
- vein segmentation
- verification
- VGG-Face
- Video tampering
- Virtual Reality Dataset
- Vision language models
- Vital signs monitoring
- VLM
- voice biometrics
- vulnerability
- Vulnerability Analysis
- vulnerability evaluation
- web- biometrics
- Wrist biometrics
- wrist vein recognition
- XCSMAD
Publications of Sébastien Marcel
2026
| Autoencoders for Open-Set Presentation Attack Detection, , and , in: IEEE Transactions on Biometrics, Behavior, and Identity Science, 2026 |
|
| Benchmarking Multimodal Large Language Models for Face Recognition, and , in: Proceedings of the 2025 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2026 |
[URL] |
| DriveFace: A Cross-Spectral Through-Glass Face Dataset for On-the-Move Vehicular Border Control, , , , and , in: IJCB, 2026 |
|
| Evaluating Multimodal Large Language Models for Heterogeneous Face Recognition, , and , in: Proceedings of 2026 IEEE International Joint Conference on Biometrics (IJCB), 2026 |
|
| Every Frame You Take: The Video-based Morphing Attack Detection Challenge, , , , and , in: Proceedings of 2026 IEEE International Joint Conference on Biometrics (IJCB), 2026 |
|
| GaitFace: A Multimodal Dataset for Long-Range Person Identification, , , , and , in: IEEE International Joint Conference on Biometrics (IJCB), 2026 |
|
| IJCB-AFMFR 2026: Competition on Adapting Foundation Models for Face Recognition Using Synthetic Training Data, and , in: Proceedings of 2026 IEEE International Joint Conference on Biometrics (IJCB), 2026 |
|
| Improving Low-Resolution Face Recognition under Limited Data: How Synthetic Data Generation Can Close the Domain Gap, , , , and , in: 2026 IEEE International Joint Conference on Biometrics (IJCB), Rome, Italy, pages IEEE, 2026 |
|
| Lightweight Cross-Spectral Face Recognition via Contrastive Alignment and Distillation, and , in: IEEE TBIOM, 2026 |
|
| Quantifying Training Membership Information in the Hyperspherical Embedding Geometry of Face Recognition Models, and , in: Proceedings of 2026 IEEE International Joint Conference on Biometrics (IJCB), 2026 |
|
| SynThermFace: Amplifying Limited Paired Data for Visible–Thermal Face Recognition via Synthetic Data Generation, , and , in: The 37th British Machine Vision Conference Workshops 2026, 2026 |
|
2025
| 3D Face Morph Generation Using Geometry-Aware Template Inversion, , and , in: 2025 IEEE 35th International Workshop on Machine Learning for Signal Processing (MLSP), 2025 |
[DOI] [URL] |
| ArtFace: Towards Historical Portrait Face Identification via Model Adaptation, , and , in: (Non-Archival), pages 4, 2025 |
[URL] |
| AugGen: Synthetic Augmentation using Diffusion Models Can Improve Recognition, , and , in: The Thirty-ninth Annual Conference on Neural Information Processing Systems, 2025 |
|
| Cancelable Face Biometrics With Soft-Biometric Privacy Enhancement, , , , , , , and , in: IEEE Access, 2025 |
[DOI] [URL] |
| DeepID Challenge of Detecting Synthetic Manipulations in ID Documents, , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , and , in: International Conference on Computer Vision (ICCV), 2025 |
|
| Detecting Text Manipulation in Images using Vision Language Models, , , , , and , in: 36th British Machine Vision Conference 2025, 2025 |
|
| Digi2Real: Bridging the Realism Gap in Synthetic Data Face Recognition via Foundation Models, and , in: 2025 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW), 2025 |
|
| EdgeDoc: Hybrid CNN-Transformer Model for Accurate Forgery Detection and Localization in ID Documents, and , Idiap-RR-08-2025 |
|
| EdgeDoc: Hybrid CNN-Transformer Model for Accurate Forgery Detection and Localization in ID Documents, and , in: ICCV, 2025 |
|
| Enhancing Domain Diversity in Synthetic Data Face Recognition with Dataset Fusion, and , in: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops, 2025 |
|
| Exploring ChatGPT for Face Presentation Attack Detection in Zero and Few-Shot in-Context Learning, , , and , in: IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2025 |
|
| Face Reconstruction from Face Embeddings using Adapter to a Face Foundation Model, , and , in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2025 |
|
| FaceLLM: A Multimodal Large Language Model for Face Understanding, and , in: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops, 2025 |
[URL] |
| FantasyID: A dataset for detecting digital manipulations of ID-documents, , , , and , in: Proceedings of IEEE International Joint Conference on Biometrics, 2025 |
|
| Foundation Models and Biometrics: A Survey and Outlook, and , in: IEEE Transactions on Information Forensics and Security, 2025 |
[DOI] [URL] |
| Generating Synthetic Face Recognition Datasets Using Brownian Identity Diffusion and a Foundation Model, and , in: 2025 IEEE 35th International Workshop on Machine Learning for Signal Processing (MLSP), 2025 |
[DOI] [URL] |
| HintsOfTruth: A Multimodal Checkworthiness Detection Dataset with Real and Synthetic Claims, , , and , in: The 63rd Annual Meeting of the Association for Computational Linguistics, 2025 |
|
| HyperFace: Generating Synthetic Face Recognition Datasets by Exploring Face Embedding Hypersphere, and , in: The Thirteenth International Conference on Learning Representations, 2025 |
[URL] |
| Identity-Preserving Aging and De-Aging of Faces in the StyleGAN Latent Space, , and , in: 2025 IEEE International Joint Conference on Biometrics (IJCB), IEEE, 2025 |
|
| Investigation of accuracy and bias in face recognition trained with synthetic data, , , , , and , in: Proceedings of IEEE International Joint Conference on Biometrics, 2025 |
|
| On the Generation of Face Morphs by Inversion of Optimal Morph Embeddings, , and , in: IEEE Transactions on Information Forensics and Security, 2025 |
[DOI] [URL] |
| Review of Demographic Bias in Face Recognition, and , Idiap-RR-01-2025 |
|
| Review of Demographic Fairness in Face Recognition, and , in: IEEE Transactions on Biometrics, Behavior, and Identity Science, 2025 |
|
| Second Competition on Presentation Attack Detection on ID Card, , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , and , in: IEEE International Joint Conference on Biometrics (IJCB), 2025 |
|
| Second FRCSyn-onGoing: Winning Solutions and Post-Challenge Analysis to Improve Face Recognition with Synthetic Data, , , , and , in: Information Fusion, 2025 |
|
| Study of Full-View Finger Vein Biometrics on Redundancy Analysis and Dynamic Feature Extraction, , , and , in: IEEE Transactions on Information Forensics and Security, 2025 |
[DOI] [URL] |
| Synthetic Face Datasets Generation via Latent Space Exploration from Brownian Identity Diffusion, , and , in: The Forty-second International Conference on Machine Learning (ICML), 2025 |
[URL] |
| TEAM SWITZERLAND SUBMISSION TO NIST SRE24 SPEAKER RECOGNITION EVALUATION, , , , , , , , , , , , and , Idiap-RR-10-2025 |
|
| The Invisible Threat: Evaluating the Vulnerability of Cross-Spectral Face Recognition to Presentation Attacks, and , in: International Joint Conference on Biometrics (IJCB 2025), IEEE., 2025 |
|