Muhammad Zeshan Afzal

105 papers A* 7A 12B 10Journal 54Unranked 20

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	DreamCAD: Scaling Multi-modal CAD Generation using Differentiable Parametric Surfaces. CoRR Mohammad Sadil Khan, Muhammad Usama, Rolandos Alexandros Potamias, Didier Stricker, Muhammad Zeshan Afzal, Jiankang Deng, Ismail Elezi
2026	A*	`conf`	NURBGen: High-Fidelity Text-to-CAD Generation Through LLM-Driven NURBS Modeling. AAAI Muhammad Usama, Mohammad Sadil Khan, Didier Stricker, Muhammad Zeshan Afzal
2025	A	`conf`	Beyond Boxes: Mask-Guided Spatio-Temporal Feature Aggregation for Video Object Detection. WACV Khurram Azeem Hashmi, Talha Uddin Sheikh, Didier Stricker, Muhammad Zeshan Afzal
2025	—	`conf`	DocSemi: Efficient Document Layout Analysis with Guided Queries. ICCVW Tahira Shehzadi, Ifza, Didier Stricker, Muhammad Zeshan Afzal
2025	—	`conf`	Efficient Additive Attention for Transformer-Based Semi-Supervised Document Layout Analysis. ICCVW Tahira Shehzadi, Ifza, Didier Stricker, Muhammad Zeshan Afzal
2025	—	`conf`	FD-SSD: Semi-supervised Detection of Bone Fenestration and Dehiscence in Intraoral Images. MIUA (2) Tahira Shehzadi, Ifza, Didier Stricker, Muhammad Zeshan Afzal
2025	A*	`conf`	MARVEL-40M+: Multi-Level Visual Elaboration for High-Fidelity Text-to-3D Content Creation. CVPR Sankalp Sinha, Mohammad Sadil Khan, Muhammad Usama, Shino Sam, Didier Stricker, Sk Aziz Ali, Muhammad Zeshan Afzal
2025	J	`jnl`	NURBGen: High-Fidelity Text-to-CAD Generation through LLM-Driven NURBS Modeling. CoRR Muhammad Usama, Mohammad Sadil Khan, Didier Stricker, Muhammad Zeshan Afzal
2025	J	`jnl`	Next Generation XR Systems - Large Language Models Meet Augmented and Virtual Reality. IEEE Computer Graphics and Applications Muhammad Zeshan Afzal, Sk Aziz Ali, Didier Stricker, Peter Eisert, Anna Hilsmann, Daniel Pérez-Marcos, Marco Bianchi, Sonia Crottaz-Herbette, Roberto De Ioris, Eleni E. Mangina, Mirco Sanguineti, Ander Salaberria, Oier Lopez de Lacalle, Aitor García-Pablos, Montse Cuadros
2025	—	`conf`	SemiTabDETR: End-to-End Semi-supervised Table Detection with Transformer-Based Enhanced Query Approach. ICDAR (1) Tahira Shehzadi, Didier Stricker, Muhammad Zeshan Afzal
2025	—	`conf`	ZOD: Zero-Shot and Out-of-Distribution Detection Dataset for Document Images. ICCVW Talha Uddin Sheikh, Sankalp Sinha, Shino Sam, Didier Stricker, Muhammad Zeshan Afzal
2024	—	`conf`	A Hybrid Approach for Document Layout Analysis in Document Images. ICDAR (4) Tahira Shehzadi, Didier Stricker, Muhammad Zeshan Afzal
2024	J	`jnl`	A Hybrid Approach for Document Layout Analysis in Document images. CoRR Tahira Shehzadi, Didier Stricker, Muhammad Zeshan Afzal
2024	J	`jnl`	Beyond Boxes: Mask-Guided Spatio-Temporal Feature Aggregation for Video Object Detection. CoRR Khurram Azeem Hashmi, Talha Uddin Sheikh, Didier Stricker, Muhammad Zeshan Afzal
2024	—	`conf`	CICA: Content-Injected Contrastive Alignment for Zero-Shot Document Image Classification. ICDAR (4) Sankalp Sinha, Muhammad Saif Ullah Khan, Talha Uddin Sheikh, Didier Stricker, Muhammad Zeshan Afzal
2024	J	`jnl`	CICA: Content-Injected Contrastive Alignment for Zero-Shot Document Image Classification. CoRR Sankalp Sinha, Muhammad Saif Ullah Khan, Talha Uddin Sheikh, Didier Stricker, Muhammad Zeshan Afzal
2024	J	`jnl`	Classroom-Inspired Multi-Mentor Distillation with Adaptive Learning Strategies. CoRR Shalini Sarode, Muhammad Saif Ullah Khan, Tahira Shehzadi, Didier Stricker, Muhammad Zeshan Afzal
2024	J	`jnl`	Continual Human Pose Estimation for Incremental Integration of Keypoints and Pose Variations. CoRR Muhammad Saif Ullah Khan, Muhammad Ahmed Ullah Khan, Muhammad Zeshan Afzal, Didier Stricker
2024	J	`jnl`	End-to-End Semi-Supervised approach with Modulated Object Queries for Table Detection in Documents. CoRR Iqraa Ehsan, Tahira Shehzadi, Didier Stricker, Muhammad Zeshan Afzal
2024	J	`jnl`	End-to-end semi-supervised approach with modulated object queries for table detection in documents. Int. J. Document Anal. Recognit. Iqraa Ehsan, Tahira Shehzadi, Didier Stricker, Muhammad Zeshan Afzal
2024	B	`conf`	Enhanced Bank Check Security: Introducing a Novel Dataset and Transformer-Based Approach for Detection and Verification. DAS Muhammad Saif Ullah Khan, Tahira Shehzadi, Rabeya Noor, Didier Stricker, Muhammad Zeshan Afzal
2024	J	`jnl`	Enhanced Bank Check Security: Introducing a Novel Dataset and Transformer-Based Approach for Detection and Verification. CoRR Muhammad Saif Ullah Khan, Tahira Shehzadi, Rabeya Noor, Didier Stricker, Muhammad Zeshan Afzal
2024	J	`jnl`	Estimating Human Poses Across Datasets: A Unified Skeleton and Multi-Teacher Distillation Approach. CoRR Muhammad Saif Ullah Khan, Dhavalkumar Limbachiya, Didier Stricker, Muhammad Zeshan Afzal
2024	J	`jnl`	FocusCLIP: Multimodal Subject-Level Guidance for Zero-Shot Transfer in Human-Centric Tasks. CoRR Muhammad Saif Ullah Khan, Muhammad Ferjad Naeem, Federico Tombari, Luc Van Gool, Didier Stricker, Muhammad Zeshan Afzal
2024	J	`jnl`	MARVEL-40M+: Multi-Level Visual Elaboration for High-Fidelity Text-to-3D Content Creation. CoRR Sankalp Sinha, Mohammad Sadil Khan, Muhammad Usama, Shino Sam, Didier Stricker, Sk Aziz Ali, Muhammad Zeshan Afzal
2024	J	`jnl`	Semi-Supervised Object Detection: A Survey on Progress from CNN to Transformer. CoRR Tahira Shehzadi, Ifza, Didier Stricker, Muhammad Zeshan Afzal
2024	J	`jnl`	Shape2.5D: A Dataset of Texture-Less Surfaces for Depth and Normals Estimation. IEEE Access Muhammad Saif Ullah Khan, Sankalp Sinha, Didier Stricker, Marcus Liwicki, Muhammad Zeshan Afzal
2024	J	`jnl`	Shape2.5D: A Dataset of Texture-less Surfaces for Depth and Normals Estimation. CoRR Muhammad Saif Ullah Khan, Muhammad Zeshan Afzal, Didier Stricker
2024	J	`jnl`	Situational Instructions Database: Task Guidance in Dynamic Environments. CoRR Muhammad Saif Ullah Khan, Sankalp Sinha, Didier Stricker, Muhammad Zeshan Afzal
2024	A*	`conf`	Sparse Semi-DETR: Sparse Learnable Queries for Semi-Supervised Object Detection. CVPR Tahira Shehzadi, Khurram Azeem Hashmi, Didier Stricker, Muhammad Zeshan Afzal
2024	J	`jnl`	Sparse Semi-DETR: Sparse Learnable Queries for Semi-Supervised Object Detection. CoRR Tahira Shehzadi, Khurram Azeem Hashmi, Didier Stricker, Muhammad Zeshan Afzal
2024	A*	`conf`	Text2CAD: Generating Sequential CAD Designs from Beginner-to-Expert Level Text Prompts. NeurIPS Mohammad Sadil Khan, Sankalp Sinha, Talha Uddin Sheikh, Didier Stricker, Sk Aziz Ali, Muhammad Zeshan Afzal
2024	J	`jnl`	Text2CAD: Generating Sequential CAD Models from Beginner-to-Expert Level Text Prompts. CoRR Mohammad Sadil Khan, Sankalp Sinha, Talha Uddin Sheikh, Didier Stricker, Sk Aziz Ali, Muhammad Zeshan Afzal
2024	J	`jnl`	Towards End-to-End Semi-Supervised Table Detection with Semantic Aligned Matching Transformer. CoRR Tahira Shehzadi, Shalini Sarode, Didier Stricker, Muhammad Zeshan Afzal
2024	—	`conf`	Towards End-to-End Semi-supervised Table Detection with Semantic Aligned Matching Transformer. ICDAR (5) Tahira Shehzadi, Shalini Sarode, Didier Stricker, Muhammad Zeshan Afzal
2024	B	`conf`	UnSupDLA: Towards Unsupervised Document Layout Analysis. DAS Talha Uddin Sheikh, Tahira Shehzadi, Khurram Azeem Hashmi, Didier Stricker, Muhammad Zeshan Afzal
2024	J	`jnl`	UnSupDLA: Towards Unsupervised Document Layout Analysis. CoRR Talha Uddin Sheikh, Tahira Shehzadi, Khurram Azeem Hashmi, Didier Stricker, Muhammad Zeshan Afzal
2023	A	`conf`	BoxMask: Revisiting Bounding Box Supervision for Video Object Detection. WACV Khurram Azeem Hashmi, Alain Pagani, Didier Stricker, Muhammad Zeshan Afzal
2023	J	`jnl`	Bridging the Performance Gap between DETR and R-CNN for Graphical Object Detection in Document Images. CoRR Tahira Shehzadi, Khurram Azeem Hashmi, Didier Stricker, Marcus Liwicki, Muhammad Zeshan Afzal
2023	A*	`conf`	FeatEnHancer: Enhancing Hierarchical Features for Object Detection and Beyond Under Low-Light Vision. ICCV Khurram Azeem Hashmi, Goutham Kallempudi, Didier Stricker, Muhammad Zeshan Afzal
2023	J	`jnl`	FeatEnHancer: Enhancing Hierarchical Features for Object Detection and Beyond Under Low-Light Vision. CoRR Khurram Azeem Hashmi, Goutham Kallempudi, Didier Stricker, Muhammad Zeshan Afzal
2023	A*	`conf`	I2MVFormer: Large Language Model Generated Multi-View Document Supervision for Zero-Shot Image Classification. CVPR Muhammad Ferjad Naeem, Muhammad Gul Zain Ali Khan, Yongqin Xian, Muhammad Zeshan Afzal, Didier Stricker, Luc Van Gool, Federico Tombari
2023	A*	`conf`	Introducing Language Guidance in Prompt-based Continual Learning. ICCV Muhammad Gul Zain Ali Khan, Muhammad Ferjad Naeem, Luc Van Gool, Didier Stricker, Federico Tombari, Muhammad Zeshan Afzal
2023	J	`jnl`	Introducing Language Guidance in Prompt-based Continual Learning. CoRR Muhammad Gul Zain Ali Khan, Muhammad Ferjad Naeem, Luc Van Gool, Didier Stricker, Federico Tombari, Muhammad Zeshan Afzal
2023	A	`conf`	Learning Attention Propagation for Compositional Zero-Shot Learning. WACV Muhammad Gul Zain Ali Khan, Muhammad Ferjad Naeem, Luc Van Gool, Alain Pagani, Didier Stricker, Muhammad Zeshan Afzal
2023	J	`jnl`	Object Detection with Transformers: A Review. CoRR Tahira Shehzadi, Khurram Azeem Hashmi, Didier Stricker, Muhammad Zeshan Afzal
2023	J	`jnl`	Robust and Fast Vehicle Detection using Augmented Confidence Map. CoRR Hamam Mokayed, Palaiahnakote Shivakumara, Lama Alkhaled, Rajkumar Saini, Muhammad Zeshan Afzal, Yan Chai Hum, Marcus Liwicki
2023	—	`conf`	Towards End-to-End Semi-Supervised Table Detection with Deformable Transformer. ICDAR (2) Tahira Shehzadi, Khurram Azeem Hashmi, Didier Stricker, Marcus Liwicki, Muhammad Zeshan Afzal
2023	J	`jnl`	Towards End-to-End Semi-Supervised Table Detection with Deformable Transformer. CoRR Tahira Shehzadi, Khurram Azeem Hashmi, Didier Stricker, Marcus Liwicki, Muhammad Zeshan Afzal
2022	J	`jnl`	A Comprehensive Survey of Depth Completion Approaches. Sensors Muhammad Ahmed Ullah Khan, Danish Nazir, Alain Pagani, Hamam Mokayed, Marcus Liwicki, Didier Stricker, Muhammad Zeshan Afzal
2022	J	`jnl`	Attention-Guided Disentangled Feature Aggregation for Video Object Detection. Sensors Shishir Muralidhara, Khurram Azeem Hashmi, Alain Pagani, Marcus Liwicki, Didier Stricker, Muhammad Zeshan Afzal
2022	J	`jnl`	BoxMask: Revisiting Bounding Box Supervision for Video Object Detection. CoRR Khurram Azeem Hashmi, Alain Pagani, Didier Stricker, Muhammad Zeshan Afzal
2022	J	`jnl`	Exploiting Concepts of Instance Segmentation to Boost Detection in Challenging Environments. Sensors Khurram Azeem Hashmi, Alain Pagani, Marcus Liwicki, Didier Stricker, Muhammad Zeshan Afzal
2022	J	`jnl`	I2MVFormer: Large Language Model Generated Multi-View Document Supervision for Zero-Shot Image Classification. CoRR Muhammad Ferjad Naeem, Muhammad Gul Zain Ali Khan, Yongqin Xian, Muhammad Zeshan Afzal, Didier Stricker, Luc Van Gool, Federico Tombari
2022	J	`jnl`	Learning Attention Propagation for Compositional Zero-Shot Learning. CoRR Muhammad Gul Zain Ali Khan, Muhammad Ferjad Naeem, Luc Van Gool, Alain Pagani, Didier Stricker, Muhammad Zeshan Afzal
2022	J	`jnl`	SemAttNet: Toward Attention-Based Semantic Aware Guided Depth Completion. IEEE Access Danish Nazir, Alain Pagani, Marcus Liwicki, Didier Stricker, Muhammad Zeshan Afzal
2022	J	`jnl`	SemAttNet: Towards Attention-based Semantic Aware Guided Depth Completion. CoRR Danish Nazir, Marcus Liwicki, Didier Stricker, Muhammad Zeshan Afzal
2022	A	`conf`	Spatio-Temporal Learnable Proposals for End-to-End Video Object Detection. BMVC Khurram Azeem Hashmi, Didier Stricker, Muhammad Zeshan Afzal
2022	J	`jnl`	Spatio-Temporal Learnable Proposals for End-to-End Video Object Detection. CoRR Khurram Azeem Hashmi, Didier Stricker, Muhammad Zeshan Afzal
2022	J	`jnl`	Three-Dimensional Reconstruction from a Single RGB Image Using Deep Learning: A Review. J. Imaging Muhammad Saif Ullah Khan, Alain Pagani, Marcus Liwicki, Didier Stricker, Muhammad Zeshan Afzal
2022	J	`jnl`	Toward Semi-Supervised Graphical Object Detection in Document Images. Future Internet Goutham Kallempudi, Khurram Azeem Hashmi, Alain Pagani, Marcus Liwicki, Didier Stricker, Muhammad Zeshan Afzal
2021	J	`jnl`	CasTabDetectoRS: Cascade Network for Table Detection in Document Images with Recursive Feature Pyramid and Switchable Atrous Convolution. J. Imaging Khurram Azeem Hashmi, Alain Pagani, Marcus Liwicki, Didier Stricker, Muhammad Zeshan Afzal
2021	J	`jnl`	Contrastive Learning for 3D Point Clouds Classification and Shape Completion. Sensors Danish Nazir, Muhammad Zeshan Afzal, Alain Pagani, Marcus Liwicki, Didier Stricker
2021	J	`jnl`	Current Status and Performance Analysis of Table Recognition in Document Images With Deep Neural Networks. IEEE Access Khurram Azeem Hashmi, Marcus Liwicki, Didier Stricker, Muhammad Adnan Afzal, Muhammad Ahtsham Afzal, Muhammad Zeshan Afzal
2021	J	`jnl`	Current Status and Performance Analysis of Table Recognition in Document Images with Deep Neural Networks. CoRR Khurram Azeem Hashmi, Marcus Liwicki, Didier Stricker, Muhammad Adnan Afzal, Muhammad Ahtsham Afzal, Muhammad Zeshan Afzal
2021	J	`jnl`	Guided Table Structure Recognition Through Anchor Optimization. IEEE Access Khurram Azeem Hashmi, Didier Stricker, Marcus Liwicki, Muhammad Noman Afzal, Muhammad Zeshan Afzal
2021	J	`jnl`	Guided Table Structure Recognition through Anchor Optimization. CoRR Khurram Azeem Hashmi, Didier Stricker, Marcus Liwicki, Muhammad Noman Afzal, Muhammad Zeshan Afzal
2021	J	`jnl`	Survey and Performance Analysis of Deep Learning Based Object Detection in Challenging Environments. Sensors Muhammad Ahmed, Khurram Azeem Hashmi, Alain Pagani, Marcus Liwicki, Didier Stricker, Muhammad Zeshan Afzal
2020	J	`jnl`	A deep learning based arabic script recognition system: benchmark on KHAT. Int. Arab J. Inf. Technol. Riaz Ahmad, Saeeda Naz, Muhammad Zeshan Afzal, Sheikh Faisal Rashid, Marcus Liwicki
2018	B	`conf`	Recognizing Challenging Handwritten Annotations with Fully Convolutional Networks. ICFHR Andreas Kölsch, Ashutosh Mishra, Saurabh Varshneya, Muhammad Zeshan Afzal, Marcus Liwicki
2018	—	`conf`	Space Anomalies in OCRs for Arabic Like Scripts. ASAR Riaz Ahmad, Muhammad Zeshan Afzal, Sheikh Faisal Rashid, Marcus Liwicki, Andreas Dengel
2017	A	`conf`	AirScript - Creating Documents in Air. ICDAR Ayushman Dash, Amit Sahu, Rajveer Shringi, John Cristian Borges Gamboa, Muhammad Zeshan Afzal, Muhammad Imran Malik, Andreas Dengel, Sheraz Ahmed
2017	J	`jnl`	AirScript - Creating Documents in Air. CoRR Ayushman Dash, Amit Sahu, Rajveer Shringi, John Cristian Borges Gamboa, Muhammad Zeshan Afzal, Muhammad Imran Malik, Sheraz Ahmed, Andreas Dengel
2017	A	`conf`	Cutting the Error by Half: Investigation of Very Deep CNN and Advanced Training Strategies for Document Image Classification. ICDAR Muhammad Zeshan Afzal, Andreas Kölsch, Sheraz Ahmed, Marcus Liwicki
2017	J	`jnl`	Cutting the Error by Half: Investigation of Very Deep CNN and Advanced Training Strategies for Document Image Classification. CoRR Muhammad Zeshan Afzal, Andreas Kölsch, Sheraz Ahmed, Marcus Liwicki
2017	A	`conf`	D-StaR: A Generic Method for Stamp Segmentation from Document Images. ICDAR Junaid Younas, Muhammad Zeshan Afzal, Muhammad Imran Malik, Faisal Shafait, Paul Lukowicz, Sheraz Ahmed
2017	—	`conf`	Deep Convolutional Neural Networks for Image Resolution Detection. HIP@ICDAR Felix Trier, Muhammad Zeshan Afzal, Markus Ebbecke, Marcus Liwicki
2017	—	`—`	Deep learning in space and time for document image processing. Muhammad Zeshan Afzal
2017	—	`conf`	Exploiting State-of-the-Art Deep Learning Methods for Document Image Analysis. WML@ICDAR Vinaychandran Pondenkandath, Mathias Seuret, Rolf Ingold, Muhammad Zeshan Afzal, Marcus Liwicki
2017	—	`conf`	KHATT: A Deep Learning Benchmark on Arabic Script. MOCR@ICDAR Riaz Ahmad, Saeeda Naz, Muhammad Zeshan Afzal, Sheikh Faisal Rashid, Marcus Liwicki, Andreas Dengel
2017	—	`conf`	Multilevel Context Representation for Improving Object Recognition. WML@ICDAR Andreas Kölsch, Muhammad Zeshan Afzal, Marcus Liwicki
2017	J	`jnl`	Multilevel Context Representation for Improving Object Recognition. CoRR Andreas Kölsch, Muhammad Zeshan Afzal, Marcus Liwicki
2017	A	`conf`	Real-Time Document Image Classification Using Deep CNN and Extreme Learning Machines. ICDAR Andreas Kölsch, Muhammad Zeshan Afzal, Markus Ebbecke, Marcus Liwicki
2017	J	`jnl`	Real-Time Document Image Classification using Deep CNN and Extreme Learning Machines. CoRR Andreas Kölsch, Muhammad Zeshan Afzal, Markus Ebbecke, Marcus Liwicki
2017	J	`jnl`	TAC-GAN - Text Conditioned Auxiliary Classifier Generative Adversarial Network. CoRR Ayushman Dash, John Cristian Borges Gamboa, Sheraz Ahmed, Marcus Liwicki, Muhammad Zeshan Afzal
2017	—	`conf`	Text-line segmentation of large titles and headings in Arabic like script. ASAR Riaz Ahmad, Muhammad Zeshan Afzal, Sheikh Faisal Rashid, Marcus Liwicki, Andreas Dengel
2017	—	`conf`	The Impact of Visual Similarities of Arabic-Like Scripts Regarding Learning in an OCR System. MOCR@ICDAR Riaz Ahmad, Saeeda Naz, Muhammad Zeshan Afzal, Sheikh Faisal Rashid, Marcus Liwicki, Andreas Dengel
2016	J	`jnl`	A Generic Method for Automatic Ground Truth Generation of Camera-captured Documents. CoRR Sheraz Ahmed, Muhammad Imran Malik, Muhammad Zeshan Afzal, Koichi Kise, Masakazu Iwamura, Andreas Dengel, Marcus Liwicki
2016	B	`conf`	Complete System for Text Line Extraction Using Convolutional Neural Networks and Watershed Transform. DAS Joan Pastor-Pellicer, Muhammad Zeshan Afzal, Marcus Liwicki, María José Castro Bleda
2016	B	`conf`	KPTI: Katib's Pashto Text Imagebase and Deep Learning Benchmark. ICFHR Riaz Ahmad, Muhammad Zeshan Afzal, Sheikh Faisal Rashid, Marcus Liwicki, Thomas M. Breuel, Andreas Dengel
2016	—	`ch.`	Latest Developments of LSTM Neural Networks with Applications of Document Image Analysis. Handbook of Pattern Recognition and Computer Vision Marcus Liwicki, Volkmar Frinken, Muhammad Zeshan Afzal
2015	A	`conf`	A sequence learning approach for multiple script identification. ICDAR Adnan Ul-Hasan, Muhammad Zeshan Afzal, Faisal Shafait, Marcus Liwicki, Thomas M. Breuel
2015	J	`jnl`	DeXpression: Deep Convolutional Neural Network for Expression Recognition. CoRR Peter Burkert, Felix Trier, Muhammad Zeshan Afzal, Andreas Dengel, Marcus Liwicki
2015	A	`conf`	Deepdocclassifier: Document classification with deep Convolutional Neural Network. ICDAR Muhammad Zeshan Afzal, Samuele Capobianco, Muhammad Imran Malik, Simone Marinai, Thomas M. Breuel, Andreas Dengel, Marcus Liwicki
2015	—	`conf`	Document Image Binarization using LSTM: A Sequence Learning Approach. HIP@ICDAR Muhammad Zeshan Afzal, Joan Pastor-Pellicer, Faisal Shafait, Thomas M. Breuel, Andreas Dengel, Marcus Liwicki
2015	—	`conf`	Insights on the Use of Convolutional Neural Networks for Document Image Binarization. IWANN (2) Joan Pastor-Pellicer, Salvador España Boquera, Francisco Zamora-Martínez, Muhammad Zeshan Afzal, María José Castro Bleda
2015	A	`conf`	Recognizable units in Pashto language for OCR. ICDAR Riaz Ahmad, Muhammad Zeshan Afzal, Sheikh Faisal Rashid, Marcus Liwicki, Andreas Dengel, Thomas M. Breuel
2015	A	`conf`	Scale and rotation invariant OCR for Pashto cursive script using MDLSTM network. ICDAR Riaz Ahmad, Muhammad Zeshan Afzal, Sheikh Faisal Rashid, Marcus Liwicki, Thomas M. Breuel
2014	B	`conf`	Using recurrent networks for non-temporal classification tasks. IJCNN Saurav Biswas, Muhammad Zeshan Afzal, Thomas M. Breuel
2013	—	`conf`	Normalizing historical orthography for OCR historical documents using LSTM. HIP@ICDAR Mayce Ibrahim Ali Al Azawi, Muhammad Zeshan Afzal, Thomas M. Breuel
2013	—	`conf`	Robust Binarization of Stereo and Monocular Document Images Using Percentile Filter. CBDAR Muhammad Zeshan Afzal, Martin Krämer, Syed Saqib Bukhari, Mohammad Reza Yousefi, Faisal Shafait, Thomas M. Breuel
2012	B	`conf`	Improvements to Uncalibrated Feature-Based Stereo Matching for Document Images by Using Text-Line Segmentation. Document Analysis Systems Muhammad Zeshan Afzal, Martin Krämer, Syed Saqib Bukhari, Faisal Shafait, Thomas M. Breuel
2012	B	`conf`	Learning feature weights of symbols, with application to symbol spotting. ICPR Nibal Nayef, Muhammad Zeshan Afzal, Thomas M. Breuel
2012	B	`conf`	Robust stereo correspondence for documents by matching connected components of text-lines with dynamic programming. ICPR Martin Krämer, Muhammad Zeshan Afzal, Syed Saqib Bukhari, Faisal Shafait, Thomas M. Breuel
2012	B	`conf`	Robust stereo matching for document images using parameter selection of text-line extraction. ICPR Muhammad Zeshan Afzal, Syed Saqib Bukhari, Martin Krämer, Faisal Shafait, Thomas M. Breuel