M. Sarfraz

Most-cited papers

A Pose-Sensitive Embedding for Person Re-identification with Expanded Cross Neighborhood Re-ranking
M. Sarfraz, Arne Schumann, Andreas Eberle, R. Stiefelhagen
20172018 IEEE/CVF Conference on Computer Vision and Pattern Recognition526 citations Open access
Semantic Scholar
Temporally-Weighted Hierarchical Clustering for Unsupervised Action Segmentation
M. Sarfraz, Naila Murray, Vivek Sharma, Ali Diba +2 more
2021Computer Vision and Pattern Recognition112 citations Open access
Semantic Scholar
Deep View-Sensitive Pedestrian Attribute Inference in an end-to-end Model
M. Sarfraz, Arne Schumann, Yan Wang, R. Stiefelhagen
2017British Machine Vision Conference100 citations
Semantic Scholar
Deep Perceptual Mapping for Cross-Modal Face Recognition
M. Sarfraz, R. Stiefelhagen
2016International Journal of Computer Vision86 citations Open access
Semantic Scholar
Head Pose Estimation in Face Recognition Across Pose Scenarios
M. Sarfraz, O. Hellwich
2008International Conference on Computer Vision Theory and Applications85 citations Open access
Semantic Scholar
Vi2CLR: Video and Image for Visual Contrastive Learning of Representation
Ali Diba, Vivek Sharma, Reza Safdari, Dariush Lotfi +3 more
2021IEEE International Conference on Computer Vision69 citations
Semantic Scholar
Deep Perceptual Mapping for Thermal to Visible Face Recogntion
M. Sarfraz, R. Stiefelhagen
2015British Machine Vision Conference64 citations
Semantic Scholar
Clustering based Contrastive Learning for Improving Face Representations
Vivek Sharma, Makarand Tapaswi, M. Sarfraz, R. Stiefelhagen
2020IEEE International Conference on Automatic Face & Gesture Recognition56 citations Open access
Semantic Scholar
Improving Single Domain-Generalized Object Detection: A Focus on Diversification and Alignment
M. S. Danish, Muhammad Haris Khan, Muhammad Akhtar Munir, M. Sarfraz +1 more
2024Computer Vision and Pattern Recognition54 citations Open access
Semantic Scholar
Self-Supervised Learning of Face Representations for Video Face Clustering
Vivek Sharma, Makarand Tapaswi, M. Sarfraz, R. Stiefelhagen
2019IEEE International Conference on Automatic Face & Gesture Recognition54 citations Open access
Semantic Scholar
Synergizing between Self-Training and Adversarial Learning for Domain Adaptive Object Detection
Muhammad Akhtar Munir, M. H. Khan, M. Sarfraz, Mohsen Ali
2021Neural Information Processing Systems53 citations
Semantic Scholar
Probabilistic learning for fully automatic face recognition across pose
M. Sarfraz, O. Hellwich
2010Image and Vision Computing51 citations
Semantic Scholar
Navigating Open Set Scenarios for Skeleton-based Action Recognition
Kun-Yu Peng, Cheng Yin, Junwei Zheng, Rui-Ping Liu +6 more
2023AAAI Conference on Artificial Intelligence47 citations
Semantic Scholar
Breaking with Fixed Set Pathology Recognition through Report-Guided Contrastive Training
C. Seibold, Simon Reiß, M. Sarfraz, R. Stiefelhagen +1 more
2022International Conference on Medical Image Computing and Computer-Assisted Intervention40 citations Open access
Semantic Scholar
Towards Improving Calibration in Object Detection Under Domain Shift
Muhammad Akhtar Munir, M. H. Khan, M. Sarfraz, Mohsen Ali
2022Neural Information Processing Systems37 citations Open access
Semantic Scholar
Anchor-free Small-scale Multispectral Pedestrian Detection
Alexander Wolpert, Michael Teutsch, M. Sarfraz, R. Stiefelhagen
2020British Machine Vision Conference36 citations Open access
Semantic Scholar
Detailed Annotations of Chest X-Rays via CT Projection for Report Understanding
C. Seibold, Simon Reiß, M. Sarfraz, Matthias A. Fink +6 more
2022British Machine Vision Conference33 citations Open access
Semantic Scholar
Referring Atomic Video Action Recognition
Kun-Yu Peng, Jian-Yang Fu, Kailun Yang, Di Wen +7 more
2024European Conference on Computer Vision28 citations
Semantic Scholar
A Multimodal Assistive System for Helping Visually Impaired in Social Interactions
M. Sarfraz, A. Constantinescu, Melanie Zuzej, R. Stiefelhagen
2017Informatik-Spektrum24 citations Open access
Semantic Scholar
Domain Adaptive Object Detection via Balancing Between Self-Training and Adversarial Learning
Muhammad Akhtar Munir, M. H. Khan, M. Sarfraz, Mohsen Ali
2023IEEE Transactions on Pattern Analysis and Machine Intelligence22 citations Open access
Semantic Scholar
Content and Colour Distillation for Learning Image Translations with the Spatial Profile Loss
M. Sarfraz, C. Seibold, Haroon Khalid, R. Stiefelhagen
2019British Machine Vision Conference22 citations
Semantic Scholar
Advancing Open-Set Domain Generalization Using Evidential Bi-Level Hardest Domain Scheduler
Kun-Yu Peng, Di Wen, Kailun Yang, Ao Luo +5 more
2024Neural Information Processing Systems20 citations
Semantic Scholar
A Simple and Effective Technique for Face Clustering in TV Series
Vivek Sharma, M. Sarfraz, R. Stiefelhagen
201720 citations
Semantic Scholar
Recognizing affective states from the expressive behavior of tennis players using convolutional neural networks
D. Jekauc, Diana Burkart, J. Fritsch, M. Hesenius +3 more
2024Knowledge-Based Systems19 citations Open access
Semantic Scholar
An efficient front-end facial pose estimation system for face recognition
M. Sarfraz, O. Hellwich
2008Pattern Recognition and Image Analysis19 citations
Semantic Scholar
Pose-based Contrastive Learning for Domain Agnostic Activity Representations
David Schneider, M. Sarfraz, Alina Roitberg, R. Stiefelhagen
20222022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)16 citations
Semantic Scholar
Vision-Based Mouth Motion Analysis in Epilepsy: A 3D Perspective
David Ahmedt-Aristizabal, Kien Nguyen, Simon Denman, M. Sarfraz +3 more
2019Annual International Conference of the IEEE Engineering in Medicine and Biology Society16 citations Open access
Semantic Scholar
Feature Extraction and Representation for Face Recognition
M. Sarfraz, O. Hellwich, Zahid Riaz
201016 citations Open access
Semantic Scholar
Fourier Prompt Tuning for Modality-Incomplete Scene Segmentation
Rui-Ping Liu, Jiaming Zhang, Kun-Yu Peng, Yu-Fan Chen +5 more
20242024 IEEE Intelligent Vehicles Symposium (IV)14 citations Open access
Semantic Scholar
Unsupervised Meta-Domain Adaptation for Fashion Retrieval
Vivek Sharma, Naila Murray, Diane Larlus, M. Sarfraz +2 more
2021IEEE Workshop/Winter Conference on Applications of Computer Vision12 citations
Semantic Scholar
Video Face Clustering With Self-Supervised Representation Learning
Vivek Sharma, Makarand Tapaswi, M. Sarfraz, R. Stiefelhagen
2020IEEE Transactions on Biometrics Behavior and Identity Science12 citations
Semantic Scholar
On Head Pose Estimation in Face Recognition
M. Sarfraz, O. Hellwich
2008VISIGRAPP11 citations
Semantic Scholar
Muscles in Time: Learning to Understand Human Motion In-Depth by Simulating Muscle Activations
David Schneider, Simon Reiß, Marco Kugler, Alexander Jaus +5 more
2024Neural Information Processing Systems10 citations
Semantic Scholar
Motion Signatures for the Analysis of Seizure Evolution in Epilepsy
David Ahmedt-Aristizabal, M. Sarfraz, Simon Denman, Kien Nguyen +3 more
2019Annual International Conference of the IEEE Engineering in Medicine and Biology Society10 citations Open access
Semantic Scholar
Mitigating Label Noise using Prompt-Based Hyperbolic Meta-Learning in Open-Set Domain Generalization
Kun-Yu Peng, Di Wen, M. Sarfraz, Yu-Fan Chen +6 more
2024International Journal of Computer Vision7 citations Open access
Semantic Scholar
Muscles in Time: Learning to Understand Human Motion by Simulating Muscle Activations
David Schneider, Simon Reiß, Marco Kugler, Alexander Jaus +5 more
2024arXiv.org7 citations
Semantic Scholar
AltChart: Enhancing VLM-based Chart Summarization Through Multi-Pretext Tasks
Omar Moured, Jiaming Zhang, M. Sarfraz, Rainer Stiefelhagen
2024IEEE International Conference on Document Analysis and Recognition7 citations
Semantic Scholar
Statistical appearance models for automatic pose invariant face recognition
M. Sarfraz, O. Hellwich
2008IEEE International Conference on Automatic Face & Gesture Recognition6 citations
Semantic Scholar
Exploring Few-Shot Adaptation for Activity Recognition on Diverse Domains
Kun-Yu Peng, Di Wen, David Schneider, Jiaming Zhang +4 more
20235 citations
Semantic Scholar
Multi-feature fusion in advanced robotics applications
Zahid Riaz, C. Mayer, M. Beetz, B. Radig +1 more
2009International Conference on Frontiers of Information Technology4 citations
Semantic Scholar
Go Beyond Earth: Understanding Human Actions and Scenes in Microgravity Environments
Di Wen, Lei Qi, Kun-Yu Peng, Kailun Yang +8 more
2025arXiv.org3 citations
Semantic Scholar
Is Visual in-Context Learning for Compositional Medical Tasks Within Reach?
Simon Reiß, Zdravko Marinov, Alexander Jaus, C. Seibold +3 more
2025IEEE International Conference on Computer Vision3 citations Open access
Semantic Scholar
OmniFall: From Staged Through Synthetic to Wild, A Unified Multi-Domain Dataset for Robust Fall Detection
David Schneider, Zdravko Marinov, Moritz Mistol, Zeyun Zhong +5 more
20252 citations
Semantic Scholar
Muscles in Time: Learning to Understand Human Motion In-Depth by Simulating Muscle Activations
Alexander Jaus, Marco Kugler, Sven Matthiesen, Kun-Yu Peng +5 more
2024Advances in Neural Information Processing Systems 372 citations
Semantic Scholar
MuscleMap: Towards Video-based Activated Muscle Group Estimation
Kun-Yu Peng, David Schneider, Alina Roitberg, Kailun Yang +3 more
2023arXiv.org2 citations Open access
Semantic Scholar
EReLiFM: Evidential Reliability-Aware Residual Flow Meta-Learning for Open-Set Domain Generalization under Noisy Labels
Kun-Yu Peng, Di Wen, Kailun Yang, Jian-Yang Fu +8 more
2025arXiv.org1 citations
Semantic Scholar
Integrating Multimodal Recognition for Smart Load Management and Spoof Detection in Residential Environments
Kanak Gautam, Anant Agarwal, K. Ahmad, Ahraz Shamim +4 more
2024International Conference on Computing Communication and Networking Technologies1 citations
Semantic Scholar
Perturbing Dominant Feature Modes for Single Domain-Generalized Object Detection
M. S. Danish, Javed Iqbal, Mohsen Ali, M. Sarfraz +2 more
2024International Conference on Digital Image Computing: Techniques and Applications1 citations
Semantic Scholar
FeatFSDA: Towards Few-shot Domain Adaptation for Video-based Activity Recognition
Kun-Yu Peng, Di Wen, David Schneider, Jiaming Zhang +4 more
2023arXiv.org1 citations Open access
Semantic Scholar
Learning Probabilistic Models for Recognizing Faces under Pose Variations
M. Sarfraz, O. Hellwich
20181 citations Open access
Semantic Scholar