Stop the war!Остановите войну!
for scientists:
default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDMuhammad Zeshan Afzal
Muhammad Zeeshan Afzal
Person information
- affiliation: German Research Center for Artificial Intelligence (DFKI), Kaiserslautern, Germany
- affiliation: University of Kaiserslautern, Department of Computer Science, Kaiserslautern, Germany
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
showing all ?? records
2020 – today
- 2024
[i21]Muhammad Saif Ullah Khan, Muhammad Ferjad Naeem, Federico Tombari, Luc Van Gool, Didier Stricker, Muhammad Zeshan Afzal:
FocusCLIP: Multimodal Subject-Level Guidance for Zero-Shot Transfer in Human-Centric Tasks. CoRR abs/2403.06904 (2024)- 2023
- [c34]Muhammad Ferjad Naeem, Muhammad Gul Zain Ali Khan, Yongqin Xian, Muhammad Zeshan Afzal, Didier Stricker, Luc Van Gool, Federico Tombari:
I2MVFormer: Large Language Model Generated Multi-View Document Supervision for Zero-Shot Image Classification. CVPR 2023: 15169-15179 - [c33]Khurram Azeem Hashmi, Goutham Kallempudi, Didier Stricker, Muhammad Zeshan Afzal:
FeatEnHancer: Enhancing Hierarchical Features for Object Detection and Beyond Under Low-Light Vision. ICCV 2023: 6702-6712 - [c32]Muhammad Gul Zain Ali Khan, Muhammad Ferjad Naeem, Luc Van Gool, Didier Stricker, Federico Tombari, Muhammad Zeshan Afzal:
Introducing Language Guidance in Prompt-based Continual Learning. ICCV 2023: 11429-11439 - [c31]Tahira Shehzadi
, Khurram Azeem Hashmi, Didier Stricker, Marcus Liwicki, Muhammad Zeshan Afzal:
Towards End-to-End Semi-Supervised Table Detection with Deformable Transformer. ICDAR (2) 2023: 51-76 - [c30]Khurram Azeem Hashmi, Alain Pagani, Didier Stricker, Muhammad Zeshan Afzal:
BoxMask: Revisiting Bounding Box Supervision for Video Object Detection. WACV 2023: 2029-2039 - [c29]Muhammad Gul Zain Ali Khan, Muhammad Ferjad Naeem, Luc Van Gool, Alain Pagani, Didier Stricker, Muhammad Zeshan Afzal:
Learning Attention Propagation for Compositional Zero-Shot Learning. WACV 2023: 3817-3826 - [i20]Hamam Mokayed, Palaiahnakote Shivakumara, Lama Alkhaled, Rajkumar Saini, Muhammad Zeshan Afzal, Yan Chai Hum, Marcus Liwicki:
Robust and Fast Vehicle Detection using Augmented Confidence Map. CoRR abs/2304.14462 (2023) - [i19]Tahira Shehzadi, Khurram Azeem Hashmi, Didier Stricker, Marcus Liwicki, Muhammad Zeshan Afzal:
Towards End-to-End Semi-Supervised Table Detection with Deformable Transformer. CoRR abs/2305.02769 (2023) - [i18]Tahira Shehzadi, Khurram Azeem Hashmi, Didier Stricker, Muhammad Zeshan Afzal:
Object Detection with Transformers: A Review. CoRR abs/2306.04670 (2023) - [i17]Tahira Shehzadi, Khurram Azeem Hashmi, Didier Stricker, Marcus Liwicki, Muhammad Zeshan Afzal:
Bridging the Performance Gap between DETR and R-CNN for Graphical Object Detection in Document Images. CoRR abs/2306.13526 (2023) - [i16]Khurram Azeem Hashmi, Goutham Kallempudi, Didier Stricker, Muhammad Zeshan Afzal:
FeatEnHancer: Enhancing Hierarchical Features for Object Detection and Beyond Under Low-Light Vision. CoRR abs/2308.03594 (2023) - [i15]Muhammad Gul Zain Ali Khan, Muhammad Ferjad Naeem, Luc Van Gool, Didier Stricker, Federico Tombari, Muhammad Zeshan Afzal:
Introducing Language Guidance in Prompt-based Continual Learning. CoRR abs/2308.15827 (2023) - 2022
- [j13]Danish Nazir, Alain Pagani, Marcus Liwicki, Didier Stricker, Muhammad Zeshan Afzal:
SemAttNet: Toward Attention-Based Semantic Aware Guided Depth Completion. IEEE Access 10: 120781-120791 (2022) - [j12]Goutham Kallempudi, Khurram Azeem Hashmi, Alain Pagani, Marcus Liwicki, Didier Stricker, Muhammad Zeshan Afzal:
Toward Semi-Supervised Graphical Object Detection in Document Images. Future Internet 14(6): 176 (2022) - [j11]Muhammad Saif Ullah Khan, Alain Pagani, Marcus Liwicki, Didier Stricker, Muhammad Zeshan Afzal:
Three-Dimensional Reconstruction from a Single RGB Image Using Deep Learning: A Review. J. Imaging 8(9): 225 (2022) - [j10]Khurram Azeem Hashmi, Alain Pagani, Marcus Liwicki, Didier Stricker, Muhammad Zeshan Afzal:
Exploiting Concepts of Instance Segmentation to Boost Detection in Challenging Environments. Sensors 22(10): 3703 (2022) - [j9]Muhammad Ahmed Ullah Khan, Danish Nazir, Alain Pagani, Hamam Mokayed, Marcus Liwicki, Didier Stricker, Muhammad Zeshan Afzal:
A Comprehensive Survey of Depth Completion Approaches. Sensors 22(18): 6969 (2022) - [j8]Shishir Muralidhara, Khurram Azeem Hashmi, Alain Pagani, Marcus Liwicki, Didier Stricker, Muhammad Zeshan Afzal:
Attention-Guided Disentangled Feature Aggregation for Video Object Detection. Sensors 22(21): 8583 (2022) - [c28]Khurram Azeem Hashmi, Didier Stricker, Muhammad Zeshan Afzal:
Spatio-Temporal Learnable Proposals for End-to-End Video Object Detection. BMVC 2022: 18 - [i14]Danish Nazir, Marcus Liwicki, Didier Stricker, Muhammad Zeshan Afzal:
SemAttNet: Towards Attention-based Semantic Aware Guided Depth Completion. CoRR abs/2204.13635 (2022) - [i13]Khurram Azeem Hashmi, Didier Stricker, Muhammad Zeshan Afzal:
Spatio-Temporal Learnable Proposals for End-to-End Video Object Detection. CoRR abs/2210.02368 (2022) - [i12]Khurram Azeem Hashmi, Alain Pagani, Didier Stricker, Muhammad Zeshan Afzal:
BoxMask: Revisiting Bounding Box Supervision for Video Object Detection. CoRR abs/2210.06008 (2022) - [i11]Muhammad Gul Zain Ali Khan, Muhammad Ferjad Naeem, Luc Van Gool, Alain Pagani, Didier Stricker, Muhammad Zeshan Afzal:
Learning Attention Propagation for Compositional Zero-Shot Learning. CoRR abs/2210.11557 (2022) - [i10]Muhammad Ferjad Naeem, Muhammad Gul Zain Ali Khan, Yongqin Xian, Muhammad Zeshan Afzal, Didier Stricker, Luc Van Gool, Federico Tombari:
I2MVFormer: Large Language Model Generated Multi-View Document Supervision for Zero-Shot Image Classification. CoRR abs/2212.02291 (2022) - 2021
- [j7]Khurram Azeem Hashmi, Marcus Liwicki, Didier Stricker, Muhammad Adnan Afzal, Muhammad Ahtsham Afzal, Muhammad Zeshan Afzal:
Current Status and Performance Analysis of Table Recognition in Document Images With Deep Neural Networks. IEEE Access 9: 87663-87685 (2021) - [j6]Khurram Azeem Hashmi, Didier Stricker, Marcus Liwicki, Muhammad Noman Afzal, Muhammad Zeshan Afzal:
Guided Table Structure Recognition Through Anchor Optimization. IEEE Access 9: 113521-113534 (2021) - [j5]Khurram Azeem Hashmi, Alain Pagani, Marcus Liwicki, Didier Stricker, Muhammad Zeshan Afzal:
CasTabDetectoRS: Cascade Network for Table Detection in Document Images with Recursive Feature Pyramid and Switchable Atrous Convolution. J. Imaging 7(10): 214 (2021) - [j4]Muhammad Ahmed, Khurram Azeem Hashmi, Alain Pagani, Marcus Liwicki, Didier Stricker, Muhammad Zeshan Afzal:
Survey and Performance Analysis of Deep Learning Based Object Detection in Challenging Environments. Sensors 21(15): 5116 (2021) - [j3]Danish Nazir, Muhammad Zeshan Afzal, Alain Pagani, Marcus Liwicki, Didier Stricker:
Contrastive Learning for 3D Point Clouds Classification and Shape Completion. Sensors 21(21): 7392 (2021) - [i9]Khurram Azeem Hashmi, Didier Stricker, Marcus Liwicki, Muhammad Noman Afzal, Muhammad Zeshan Afzal:
Guided Table Structure Recognition through Anchor Optimization. CoRR abs/2104.10538 (2021) - [i8]Khurram Azeem Hashmi, Marcus Liwicki, Didier Stricker, Muhammad Adnan Afzal, Muhammad Ahtsham Afzal, Muhammad Zeshan Afzal:
Current Status and Performance Analysis of Table Recognition in Document Images with Deep Neural Networks. CoRR abs/2104.14272 (2021) - 2020
- [j2]Riaz Ahmad, Saeeda Naz, Muhammad Zeshan Afzal, Sheikh Faisal Rashid, Marcus Liwicki:
A deep learning based arabic script recognition system: benchmark on KHAT. Int. Arab J. Inf. Technol. 17(3): 299-305 (2020)
2010 – 2019
- 2018
- [c27]Riaz Ahmad, Muhammad Zeshan Afzal, Sheikh Faisal Rashid, Marcus Liwicki, Andreas Dengel:
Space Anomalies in OCRs for Arabic Like Scripts. ASAR 2018: 67-71 - [c26]Andreas Kölsch, Ashutosh Mishra, Saurabh Varshneya, Muhammad Zeshan Afzal, Marcus Liwicki:
Recognizing Challenging Handwritten Annotations with Fully Convolutional Networks. ICFHR 2018: 25-31 - 2017
- [b1]Muhammad Zeshan Afzal:
Deep learning in space and time for document image processing. Kaiserslautern University of Technology, Germany, 2017, ISBN 978-3-95974-058-6, pp. 1-204 - [c25]Riaz Ahmad, Muhammad Zeshan Afzal, Sheikh Faisal Rashid, Marcus Liwicki, Andreas Dengel:
Text-line segmentation of large titles and headings in Arabic like script. ASAR 2017: 168-172 - [c24]Riaz Ahmad, Saeeda Naz, Muhammad Zeshan Afzal, Sheikh Faisal Rashid, Marcus Liwicki, Andreas Dengel:
KHATT: A Deep Learning Benchmark on Arabic Script. MOCR@ICDAR 2017: 10-14 - [c23]Andreas Kölsch, Muhammad Zeshan Afzal, Marcus Liwicki:
Multilevel Context Representation for Improving Object Recognition. WML@ICDAR 2017: 10-15 - [c22]Riaz Ahmad, Saeeda Naz, Muhammad Zeshan Afzal, Sheikh Faisal Rashid, Marcus Liwicki, Andreas Dengel:
The Impact of Visual Similarities of Arabic-Like Scripts Regarding Learning in an OCR System. MOCR@ICDAR 2017: 15-19 - [c21]Vinaychandran Pondenkandath, Mathias Seuret, Rolf Ingold, Muhammad Zeshan Afzal, Marcus Liwicki:
Exploiting State-of-the-Art Deep Learning Methods for Document Image Analysis. WML@ICDAR 2017: 30-35 - [c20]Felix Trier, Muhammad Zeshan Afzal, Markus Ebbecke, Marcus Liwicki:
Deep Convolutional Neural Networks for Image Resolution Detection. HIP@ICDAR 2017: 77-82 - [c19]Junaid Younas, Muhammad Zeshan Afzal, Muhammad Imran Malik, Faisal Shafait, Paul Lukowicz, Sheraz Ahmed:
D-StaR: A Generic Method for Stamp Segmentation from Document Images. ICDAR 2017: 248-253 - [c18]Muhammad Zeshan Afzal, Andreas Kölsch, Sheraz Ahmed, Marcus Liwicki:
Cutting the Error by Half: Investigation of Very Deep CNN and Advanced Training Strategies for Document Image Classification. ICDAR 2017: 883-888 - [c17]Ayushman Dash, Amit Sahu, Rajveer Shringi, John Cristian Borges Gamboa, Muhammad Zeshan Afzal, Muhammad Imran Malik, Andreas Dengel, Sheraz Ahmed:
AirScript - Creating Documents in Air. ICDAR 2017: 908-913 - [c16]Andreas Kölsch, Muhammad Zeshan Afzal, Markus Ebbecke, Marcus Liwicki:
Real-Time Document Image Classification Using Deep CNN and Extreme Learning Machines. ICDAR 2017: 1318-1323 - [i7]Andreas Kölsch, Muhammad Zeshan Afzal, Marcus Liwicki:
Multilevel Context Representation for Improving Object Recognition. CoRR abs/1703.06408 (2017) - [i6]Ayushman Dash, John Cristian Borges Gamboa, Sheraz Ahmed, Marcus Liwicki, Muhammad Zeshan Afzal:
TAC-GAN - Text Conditioned Auxiliary Classifier Generative Adversarial Network. CoRR abs/1703.06412 (2017) - [i5]Muhammad Zeshan Afzal, Andreas Kölsch, Sheraz Ahmed, Marcus Liwicki:
Cutting the Error by Half: Investigation of Very Deep CNN and Advanced Training Strategies for Document Image Classification. CoRR abs/1704.03557 (2017) - [i4]Ayushman Dash, Amit Sahu, Rajveer Shringi, John Cristian Borges Gamboa, Muhammad Zeshan Afzal, Muhammad Imran Malik, Sheraz Ahmed, Andreas Dengel:
AirScript - Creating Documents in Air. CoRR abs/1705.11181 (2017) - [i3]Andreas Kölsch, Muhammad Zeshan Afzal, Markus Ebbecke, Marcus Liwicki:
Real-Time Document Image Classification using Deep CNN and Extreme Learning Machines. CoRR abs/1711.05862 (2017) - 2016
- [j1]Saad Bin Ahmed, Saeeda Naz, Muhammad Imran Razzak, Shiekh Faisal Rashid, Muhammad Zeeshan Afzal, Thomas M. Breuel:
Evaluation of cursive and non-cursive scripts using recurrent neural networks. Neural Comput. Appl. 27(3): 603-613 (2016) - [c15]Joan Pastor-Pellicer, Muhammad Zeshan Afzal, Marcus Liwicki, María José Castro Bleda:
Complete System for Text Line Extraction Using Convolutional Neural Networks and Watershed Transform. DAS 2016: 30-35 - [c14]Riaz Ahmad, Muhammad Zeshan Afzal, Sheikh Faisal Rashid, Marcus Liwicki, Thomas M. Breuel, Andreas Dengel:
KPTI: Katib's Pashto Text Imagebase and Deep Learning Benchmark. ICFHR 2016: 453-458 - [p1]Marcus Liwicki, Volkmar Frinken, Muhammad Zeshan Afzal:
Latest Developments of LSTM Neural Networks with Applications of Document Image Analysis. Handbook of Pattern Recognition and Computer Vision 2016: 293-311 - [i2]Sheraz Ahmed, Muhammad Imran Malik, Muhammad Zeshan Afzal, Koichi Kise, Masakazu Iwamura, Andreas Dengel, Marcus Liwicki:
A Generic Method for Automatic Ground Truth Generation of Camera-captured Documents. CoRR abs/1605.01189 (2016) - 2015
- [c13]Muhammad Zeshan Afzal, Joan Pastor-Pellicer, Faisal Shafait, Thomas M. Breuel, Andreas Dengel, Marcus Liwicki:
Document Image Binarization using LSTM: A Sequence Learning Approach. HIP@ICDAR 2015: 79-84 - [c12]Adnan Ul-Hasan, Muhammad Zeshan Afzal, Faisal Shafait, Marcus Liwicki, Thomas M. Breuel:
A sequence learning approach for multiple script identification. ICDAR 2015: 1046-1050 - [c11]Riaz Ahmad, Muhammad Zeshan Afzal, Sheikh Faisal Rashid, Marcus Liwicki, Thomas M. Breuel:
Scale and rotation invariant OCR for Pashto cursive script using MDLSTM network. ICDAR 2015: 1101-1105 - [c10]Muhammad Zeshan Afzal, Samuele Capobianco, Muhammad Imran Malik, Simone Marinai, Thomas M. Breuel, Andreas Dengel, Marcus Liwicki:
Deepdocclassifier: Document classification with deep Convolutional Neural Network. ICDAR 2015: 1111-1115 - [c9]Riaz Ahmad, Muhammad Zeshan Afzal, Sheikh Faisal Rashid, Marcus Liwicki, Andreas Dengel, Thomas M. Breuel:
Recognizable units in Pashto language for OCR. ICDAR 2015: 1246-1250 - [c8]Joan Pastor-Pellicer, Salvador España Boquera, Francisco Zamora-Martínez, Muhammad Zeshan Afzal, María José Castro Bleda:
Insights on the Use of Convolutional Neural Networks for Document Image Binarization. IWANN (2) 2015: 115-126 - [i1]Peter Burkert, Felix Trier, Muhammad Zeshan Afzal, Andreas Dengel, Marcus Liwicki:
DeXpression: Deep Convolutional Neural Network for Expression Recognition. CoRR abs/1509.05371 (2015) - 2014
- [c7]Saurav Biswas, Muhammad Zeshan Afzal, Thomas M. Breuel:
Using recurrent networks for non-temporal classification tasks. IJCNN 2014: 135-140 - 2013
- [c6]Muhammad Zeshan Afzal, Martin Krämer, Syed Saqib Bukhari, Mohammad Reza Yousefi, Faisal Shafait, Thomas M. Breuel:
Robust Binarization of Stereo and Monocular Document Images Using Percentile Filter. CBDAR 2013: 139-149 - [c5]Mayce Ibrahim Ali Al Azawi, Muhammad Zeshan Afzal, Thomas M. Breuel:
Normalizing historical orthography for OCR historical documents using LSTM. HIP@ICDAR 2013: 80-85 - 2012
- [c4]Muhammad Zeshan Afzal, Martin Krämer, Syed Saqib Bukhari, Faisal Shafait, Thomas M. Breuel:
Improvements to Uncalibrated Feature-Based Stereo Matching for Document Images by Using Text-Line Segmentation. Document Analysis Systems 2012: 394-398 - [c3]Muhammad Zeshan Afzal, Syed Saqib Bukhari, Martin Krämer, Faisal Shafait, Thomas M. Breuel:
Robust stereo matching for document images using parameter selection of text-line extraction. ICPR 2012: 331-334 - [c2]Martin Krämer, Muhammad Zeshan Afzal, Syed Saqib Bukhari, Faisal Shafait, Thomas M. Breuel:
Robust stereo correspondence for documents by matching connected components of text-lines with dynamic programming. ICPR 2012: 734-737 - [c1]Nibal Nayef, Muhammad Zeshan Afzal, Thomas M. Breuel:
Learning feature weights of symbols, with application to symbol spotting. ICPR 2012: 2371-2374
Coauthor Index
a service of 
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
Unpaywalled article links
Add open access links from 
to the list of external document links (if available).
Privacy notice: By enabling the option above, your browser will contact the API of unpaywall.org to load hyperlinks to open access articles. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Unpaywall privacy policy.
Archived links via Wayback Machine
For web page which are no longer available, try to retrieve content from the 
of the Internet Archive (if available).
Privacy notice: By enabling the option above, your browser will contact the API of archive.org to check for archived content of web pages that are no longer available. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Internet Archive privacy policy.
Reference lists
Add a list of references from 
, 
, and 
to record detail pages.
load references from crossref.org and opencitations.net
Privacy notice: By enabling the option above, your browser will contact the APIs of crossref.org, opencitations.net, and semanticscholar.org to load article reference information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Crossref privacy policy and the OpenCitations privacy policy, as well as the AI2 Privacy Policy covering Semantic Scholar.
Citation data
Add a list of citing articles from and to record detail pages.
load citations from opencitations.net
Privacy notice: By enabling the option above, your browser will contact the API of opencitations.net and semanticscholar.org to load citation information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the OpenCitations privacy policy as well as the AI2 Privacy Policy covering Semantic Scholar.
OpenAlex data
Load additional information about publications from 
.
Privacy notice: By enabling the option above, your browser will contact the API of openalex.org to load additional information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the information given by OpenAlex.
last updated on 2024-04-07 22:27 CEST by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by:
