Muhammad Saif Ullah Khan
E-Mail: | Muhammad_Saif_Ullah.Khan@dfki.de |
---|---|
Position: | Researcher |
Saif Khan holds a Bachelor’s degree in Software Engineering from NUST, Pakistan, and a Master’s in Computer Science from the University of Kaiserslautern, where he wrote his thesis on 3D reconstruction of transparent and low-texture surfaces. He joined the AV group in November 2021 and has worked on projects including INFINITY, LUMINOUS, and SHARESPACE. Currently pursuing his Ph.D. at RPTU Kaiserslautern, his research focuses on real-time, markerless motion tracking and multimodal approaches to make human motion understanding more accessible on everyday devices.
Classroom-Inspired Multi-Mentor Distillation with Adaptive Learning Strategies
In: Intelligent Systems and Applications. Intelligent Systems Conference (IntelliSys-2025), 11th Intelligent Systems Conference 2025, Amsterdam, Netherlands, Springer Nature Switzerland, 8/2025.
Details
| Link 1
Towards Unconstrained 2D Pose Estimation of the Human Spine
In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops. International Workshop on Computer Vision in Sports (CVsports-2025), 11th International Workshop, located at CVPR 2025, June 11-15, Nashville, TN, USA, IEEE/CVF, 6/2025.
Details
| Link 1
SituationalLLM: Proactive Language Models with Scene Awareness for Dynamic, Contextual Task Guidance [version 1; peer review: awaiting peer review]
In: Open Research Europe, Vol. 5, No. 61, Pages 1-14, Open Research Europe, 3/2025.
Details
Shape2.5D: A Dataset of Texture-less Surfaces for Depth and Normals Estimation
In: IEEE Access (IEEE), Vol. 12, Pages 1-1, IEEE, 11/2024.
Details
Enhanced Bank Check Security: Introducing a Novel Dataset and Transformer-Based Approach for Detection and Verification
In: IAPR International Workshop on Document Analysis Systems. IAPR International Workshop on Document Analysis Systems (DAS-2024), August 29 - September 4, Greece, Springer, 8/2024.
Details
| Link 1
CICA: Content-Injected Contrastive Alignment for Zero-Shot Document Image Classification
In: ICDAR 2024 Main Conference Proceedings. International Conference on Document Analysis and Recognition (ICDAR-2024), 18th International Conference on Document Analysis and Recognition, located at International Conference on Document Analysis and Recognition, August 30 - September 4, Athens, Greece, Springer, 2024.
Details
| Link 1
3D Reconstruction from a Single RGB Image using Deep Learning: A Review
Journal of Imaging (MDPI J) 8 225 Seiten 1-23 MDPI 8/2022 .
Details
| Link 1