Heng Zhang

Orcid: 0000-0001-9448-4031

Affiliations:
  • Chinese Academy of Sciences, Institution of Automation, State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Beijing, China
  • Chinese Academy of Sciences, Institution of Automation, National Laboratory of Pattern Recognition (NLPR), Beijing, China (PhD 2013)


According to our database1, Heng Zhang authored at least 20 papers between 2010 and 2025.

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

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

Online presence:

On csauthors.net:

Bibliography

2025
CHSAM: Efficient Scene Text Segmentation via SAM with Convolutional Adapters and Hierarchical Decoding.
Proceedings of the Document Analysis and Recognition - ICDAR 2025, 2025

2024
An approach for handwritten Chinese text recognition unifying character segmentation and recognition.
Pattern Recognit., 2024

Deep Metric Learning with Cross-Writer Attention for Offline Signature Verification.
Proceedings of the Document Analysis and Recognition - ICDAR 2024 - 18th International Conference, Athens, Greece, August 30, 2024

Adaptive Scaling and Refined Pyramid Feature Fusion Network for Scene Text Segmentation.
Proceedings of the Document Analysis and Recognition - ICDAR 2024 - 18th International Conference, Athens, Greece, August 30, 2024

2022
An Efficient Prototype-Based Model for Handwritten Text Recognition with Multi-loss Fusion.
Proceedings of the Frontiers in Handwriting Recognition - 18th International Conference, 2022

2021
Regularizing CTC in Expectation-Maximization Framework with Application to Handwritten Text Recognition.
Proceedings of the International Joint Conference on Neural Networks, 2021

2020
Table detection and cell segmentation in online handwritten documents with graph attention networks.
Proceedings of the MMAsia 2020: ACM Multimedia Asia, 2020

2019
Oracle Character Recognition by Nearest Neighbor Classification with Deep Metric Learning.
Proceedings of the 2019 International Conference on Document Analysis and Recognition, 2019

2017
Keyword spotting in handwritten chinese documents using semi-markov conditional random fields.
Eng. Appl. Artif. Intell., 2017

2016
Improving short text classification by learning vector representations of both words and hidden topics.
Knowl. Based Syst., 2016

2015
Towards end-to-end speech recognition for Chinese Mandarin using long short-term memory recurrent neural networks.
Proceedings of the 16th Annual Conference of the International Speech Communication Association, 2015

Semantic Clustering and Convolutional Neural Network for Short Text Categorization.
Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, 2015

2014
Character confidence based on N-best list for keyword spotting in online Chinese handwritten documents.
Pattern Recognit., 2014

Short Text Feature Enrichment Using Link Analysis on Topic-Keyword Graph.
Proceedings of the Natural Language Processing and Chinese Computing, 2014

A robust framework for short text categorization based on topic model and integrated classifier.
Proceedings of the 2014 International Joint Conference on Neural Networks, 2014

Short Text Hashing Improved by Integrating Topic Features and Tags.
Proceedings of the Neural Information Processing - 21st International Conference, 2014

2013
Keyword Spotting from Online Chinese Handwritten Documents using One-versus-All Character Classification Model.
Int. J. Pattern Recognit. Artif. Intell., 2013

2012
A confidence-based method for keyword spotting in online Chinese handwritten documents.
Proceedings of the 21st International Conference on Pattern Recognition, 2012

An Effective Character Separation Method for Online Cursive Uyghur Handwriting.
Proceedings of the Pattern Recognition - Chinese Conference, 2012

2010
Keyword Spotting from Online Chinese Handwritten Documents Using One-vs-All Trained Character Classifier.
Proceedings of the International Conference on Frontiers in Handwriting Recognition, 2010


  Loading...