Muhammad Zeshan Afzal

Orcid: 0000-0002-0536-6867

Affiliations:
  • German Research Center for Artificial Intelligence (DFKI), Kaiserslautern, Germany
  • University of Kaiserslautern, Department of Computer Science, Kaiserslautern, Germany


According to our database1, Muhammad Zeshan Afzal authored at least 57 papers between 2012 and 2024.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2024
FocusCLIP: Multimodal Subject-Level Guidance for Zero-Shot Transfer in Human-Centric Tasks.
CoRR, 2024

2023
Bridging the Performance Gap between DETR and R-CNN for Graphical Object Detection in Document Images.
CoRR, 2023

Object Detection with Transformers: A Review.
CoRR, 2023

Robust and Fast Vehicle Detection using Augmented Confidence Map.
CoRR, 2023

Learning Attention Propagation for Compositional Zero-Shot Learning.
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2023

BoxMask: Revisiting Bounding Box Supervision for Video Object Detection.
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision, 2023

Towards End-to-End Semi-Supervised Table Detection with Deformable Transformer.
Proceedings of the Document Analysis and Recognition - ICDAR 2023, 2023

Introducing Language Guidance in Prompt-based Continual Learning.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

FeatEnHancer: Enhancing Hierarchical Features for Object Detection and Beyond Under Low-Light Vision.
Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

I2MVFormer: Large Language Model Generated Multi-View Document Supervision for Zero-Shot Image Classification.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

2022
Attention-Guided Disentangled Feature Aggregation for Video Object Detection.
Sensors, 2022

A Comprehensive Survey of Depth Completion Approaches.
Sensors, 2022

Exploiting Concepts of Instance Segmentation to Boost Detection in Challenging Environments.
Sensors, 2022

Three-Dimensional Reconstruction from a Single RGB Image Using Deep Learning: A Review.
J. Imaging, 2022

Toward Semi-Supervised Graphical Object Detection in Document Images.
Future Internet, 2022

SemAttNet: Towards Attention-based Semantic Aware Guided Depth Completion.
CoRR, 2022

SemAttNet: Toward Attention-Based Semantic Aware Guided Depth Completion.
IEEE Access, 2022

Spatio-Temporal Learnable Proposals for End-to-End Video Object Detection.
Proceedings of the 33rd British Machine Vision Conference 2022, 2022

2021
Contrastive Learning for 3D Point Clouds Classification and Shape Completion.
Sensors, 2021

Survey and Performance Analysis of Deep Learning Based Object Detection in Challenging Environments.
Sensors, 2021

CasTabDetectoRS: Cascade Network for Table Detection in Document Images with Recursive Feature Pyramid and Switchable Atrous Convolution.
J. Imaging, 2021

Guided Table Structure Recognition Through Anchor Optimization.
IEEE Access, 2021

Current Status and Performance Analysis of Table Recognition in Document Images With Deep Neural Networks.
IEEE Access, 2021

2020
A deep learning based arabic script recognition system: benchmark on KHAT.
Int. Arab J. Inf. Technol., 2020

2018
Recognizing Challenging Handwritten Annotations with Fully Convolutional Networks.
Proceedings of the 16th International Conference on Frontiers in Handwriting Recognition, 2018

Space Anomalies in OCRs for Arabic Like Scripts.
Proceedings of the IEEE 2nd International Workshop on Arabic and Derived Script Analysis and Recognition, 2018

2017
Deep learning in space and time for document image processing.
PhD thesis, 2017

TAC-GAN - Text Conditioned Auxiliary Classifier Generative Adversarial Network.
CoRR, 2017

D-StaR: A Generic Method for Stamp Segmentation from Document Images.
Proceedings of the 14th IAPR International Conference on Document Analysis and Recognition, 2017

Deep Convolutional Neural Networks for Image Resolution Detection.
Proceedings of the 4th International Workshop on Historical Document Imaging and Processing, 2017

Exploiting State-of-the-Art Deep Learning Methods for Document Image Analysis.
Proceedings of the First Workshop of Machine Learning, 2017

Multilevel Context Representation for Improving Object Recognition.
Proceedings of the First Workshop of Machine Learning, 2017

Real-Time Document Image Classification Using Deep CNN and Extreme Learning Machines.
Proceedings of the 14th IAPR International Conference on Document Analysis and Recognition, 2017

AirScript - Creating Documents in Air.
Proceedings of the 14th IAPR International Conference on Document Analysis and Recognition, 2017

The Impact of Visual Similarities of Arabic-Like Scripts Regarding Learning in an OCR System.
Proceedings of the 6th International Workshop on Multilingual OCR, 2017

KHATT: A Deep Learning Benchmark on Arabic Script.
Proceedings of the 6th International Workshop on Multilingual OCR, 2017

Cutting the Error by Half: Investigation of Very Deep CNN and Advanced Training Strategies for Document Image Classification.
Proceedings of the 14th IAPR International Conference on Document Analysis and Recognition, 2017

Text-line segmentation of large titles and headings in Arabic like script.
Proceedings of the 1st International Workshop on Arabic Script Analysis and Recognition, 2017

2016
Evaluation of cursive and non-cursive scripts using recurrent neural networks.
Neural Comput. Appl., 2016

A Generic Method for Automatic Ground Truth Generation of Camera-captured Documents.
CoRR, 2016

KPTI: Katib's Pashto Text Imagebase and Deep Learning Benchmark.
Proceedings of the 15th International Conference on Frontiers in Handwriting Recognition, 2016

Complete System for Text Line Extraction Using Convolutional Neural Networks and Watershed Transform.
Proceedings of the 12th IAPR Workshop on Document Analysis Systems, 2016

Latest Developments of LSTM Neural Networks with Applications of Document Image Analysis.
Proceedings of the Handbook of Pattern Recognition and Computer Vision, 5th Ed., 2016

2015
DeXpression: Deep Convolutional Neural Network for Expression Recognition.
CoRR, 2015

Insights on the Use of Convolutional Neural Networks for Document Image Binarization.
Proceedings of the Advances in Computational Intelligence, 2015

A sequence learning approach for multiple script identification.
Proceedings of the 13th International Conference on Document Analysis and Recognition, 2015

Recognizable units in Pashto language for OCR.
Proceedings of the 13th International Conference on Document Analysis and Recognition, 2015

Scale and rotation invariant OCR for Pashto cursive script using MDLSTM network.
Proceedings of the 13th International Conference on Document Analysis and Recognition, 2015

Document Image Binarization using LSTM: A Sequence Learning Approach.
Proceedings of the 3rd International Workshop on Historical Document Imaging and Processing, 2015

Deepdocclassifier: Document classification with deep Convolutional Neural Network.
Proceedings of the 13th International Conference on Document Analysis and Recognition, 2015

2014
Using recurrent networks for non-temporal classification tasks.
Proceedings of the 2014 International Joint Conference on Neural Networks, 2014

2013
Normalizing historical orthography for OCR historical documents using LSTM.
Proceedings of the 2nd International Workshop on Historical Document Imaging and Processing, 2013

Robust Binarization of Stereo and Monocular Document Images Using Percentile Filter.
Proceedings of the Camera-Based Document Analysis and Recognition, 2013

2012
Learning feature weights of symbols, with application to symbol spotting.
Proceedings of the 21st International Conference on Pattern Recognition, 2012

Robust stereo correspondence for documents by matching connected components of text-lines with dynamic programming.
Proceedings of the 21st International Conference on Pattern Recognition, 2012

Robust stereo matching for document images using parameter selection of text-line extraction.
Proceedings of the 21st International Conference on Pattern Recognition, 2012

Improvements to Uncalibrated Feature-Based Stereo Matching for Document Images by Using Text-Line Segmentation.
Proceedings of the 10th IAPR International Workshop on Document Analysis Systems, 2012


  Loading...