Clément Chatelain
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Clément Chatelain has a total of 96 co-authors. Here are the top co-authors by number of shared publications:
Thierry Paquet
Normandie Univ, UNIROUEN, UNIHAVRE, INSA Rouen, LITIS
20 shared publications- Thierry Paquet
LITIS EA4108, University of Rouen Normandy
15 shared publications T. Paquet
Universite de Rouen & INSA de Rouen, LITIS EA 4108, BP12, 76801 Saint Etienne du Rouvray, France
8 shared publicationsLuc Mioulet
Laboratoire LITIS - EA 4108, Universite de Rouen, FRANCE 76800
7 shared publications- Denis Coquenet
Univ. Rennes, CNRS, Inria, IRISA - UMR 6074
6 shared publications Laurent Heutte
Université de Rouen
6 shared publications
Latest Publications
- 26 August 2026
- Published by Springer Nature
- p. 663-680
A Benchmark of State-Space Models vs. Transformers and BiLSTM-Based Models for Historical Newspaper OCR
- 26 August 2026
- Published by Springer Nature
- p. 663-680
A Benchmark of State-Space Models vs. Transformers and BiLSTM-Based Models for Historical Newspaper OCR
- 23 August 2026
- Published by Springer Nature
- p. 608-625
Few-Shot Writer Adaptation via Multimodal In-Context Learning
- 23 August 2026
- Published by Springer Nature
- p. 608-625
Few-Shot Writer Adaptation via Multimodal In-Context Learning
- 16 September 2025
- Published by Springer Nature
- p. 224-243
Classifying the Unknown: In-Context Learning for Open-Vocabulary Text and Symbol Recognition
- 16 September 2025
- Published by Springer Nature
- p. 224-243
Classifying the Unknown: In-Context Learning for Open-Vocabulary Text and Symbol Recognition
- Open Access
Classifying the Unknown: In-Context Learning for Open-Vocabulary Text and Symbol Recognition
We introduce Rosetta, a multimodal model that leverages Multimodal In-Context Learning (MICL) to classify sequences of novel script patterns in documents by leveraging minimal examples, thus eliminating the need for explicit retraining. To enhance contextual learning, we designed a dataset generation process that ensures varying degrees of contextual informativeness, improving the model's adaptability in leveraging context across different scenarios. A key strength of our method is the use of a Context-Aware Tokenizer (CAT), which enables open-vocabulary classification. This allows the model to classify text and symbol patterns across an unlimited range of classes, extending its classification capabilities beyond the scope of its training alphabet of patterns. As a result, it unlocks applications such as the recognition of new alphabets and languages. Experiments on synthetic datasets demonstrate the potential of Rosetta to successfully classify Out-Of-Distribution visual patterns and diverse sets of alphabets and scripts, including but not limited to Chinese, Greek, Russian, French, Spanish, and Japanese.
Open AccessClassifying the Unknown: In-Context Learning for Open-Vocabulary Text and Symbol Recognition
We introduce Rosetta, a multimodal model that leverages Multimodal In-Context Learning (MICL) to classify sequences of novel script patterns in documents by leveraging minimal examples, thus eliminating the need for explicit retraining. To enhance contextual learning, we designed a dataset generation process that ensures varying degrees of contextual informativeness, improving the model's adaptability in leveraging context across different scenarios. A key strength of our method is the use of a Context-Aware Tokenizer (CAT), which enables open-vocabulary classification. This allows the model to classify text and symbol patterns across an unlimited range of classes, extending its classification capabilities beyond the scope of its training alphabet of patterns. As a result, it unlocks applications such as the recognition of new alphabets and languages. Experiments on synthetic datasets demonstrate the potential of Rosetta to successfully classify Out-Of-Distribution visual patterns and diverse sets of alphabets and scripts, including but not limited to Chinese, Greek, Russian, French, Spanish, and Japanese.
- Open Access
Temporal receptive field in dynamic graph learning: A comprehensive analysis
Dynamic link prediction is a critical task in the analysis of evolving networks, with applications ranging from recommender systems to economic exchanges. However, the concept of the temporal receptive field, which refers to the temporal context that models use for making predictions, has been largely overlooked and insufficiently analyzed in existing research. In this study, we present a comprehensive analysis of the temporal receptive field in dynamic graph learning. By examining multiple datasets and models, we formalize the role of temporal receptive field and highlight their crucial influence on predictive accuracy. Our results demonstrate that appropriately chosen temporal receptive field can significantly enhance model performance, while for some models, overly large windows may introduce noise and reduce accuracy. We conduct extensive benchmarking to validate our findings, ensuring that all experiments are fully reproducible. Code is available at https://github.com/ykrmm/BenchmarkTW .
Open AccessTemporal receptive field in dynamic graph learning: A comprehensive analysis
Dynamic link prediction is a critical task in the analysis of evolving networks, with applications ranging from recommender systems to economic exchanges. However, the concept of the temporal receptive field, which refers to the temporal context that models use for making predictions, has been largely overlooked and insufficiently analyzed in existing research. In this study, we present a comprehensive analysis of the temporal receptive field in dynamic graph learning. By examining multiple datasets and models, we formalize the role of temporal receptive field and highlight their crucial influence on predictive accuracy. Our results demonstrate that appropriately chosen temporal receptive field can significantly enhance model performance, while for some models, overly large windows may introduce noise and reduce accuracy. We conduct extensive benchmarking to validate our findings, ensuring that all experiments are fully reproducible. Code is available at https://github.com/ykrmm/BenchmarkTW .
- Top Cited PapersOpen Access
- 18 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 43460-43484
Dynamic Graph Representation Learning With Neural Networks: A Survey
In recent years, Dynamic Graph (DG) representations have been increasingly used for modeling dynamic systems due to their ability to integrate both topological and temporal information in a compact representation. Dynamic graphs efficiently handle applications such as social network prediction, recommender systems, traffic forecasting, or electroencephalography analysis, which cannot be addressed using standard numerical representations. As a direct consequence, dynamic graph learning has emerged as a new machine learning problem, combining challenges from both sequential/temporal data processing and static graph learning. In this research area, the Dynamic Graph Neural Network (DGNN) has become the state-of-the-art approach and a plethora of models have been proposed in the very recent years. This paper aims to provide a review of the problems and models related to dynamic graph learning. The various dynamic graph supervised learning settings are analyzed and discussed. We identify the similarities and differences between existing models concerning the way time information is modeled. Finally, we provide guidelines for DGNN design and optimization, and review public datasets for evaluating model performance on various tasks, along with the corresponding publications.
- 18 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 43460-43484
Top Cited PapersOpen AccessDynamic Graph Representation Learning With Neural Networks: A Survey
In recent years, Dynamic Graph (DG) representations have been increasingly used for modeling dynamic systems due to their ability to integrate both topological and temporal information in a compact representation. Dynamic graphs efficiently handle applications such as social network prediction, recommender systems, traffic forecasting, or electroencephalography analysis, which cannot be addressed using standard numerical representations. As a direct consequence, dynamic graph learning has emerged as a new machine learning problem, combining challenges from both sequential/temporal data processing and static graph learning. In this research area, the Dynamic Graph Neural Network (DGNN) has become the state-of-the-art approach and a plethora of models have been proposed in the very recent years. This paper aims to provide a review of the problems and models related to dynamic graph learning. The various dynamic graph supervised learning settings are analyzed and discussed. We identify the similarities and differences between existing models concerning the way time information is modeled. Finally, we provide guidelines for DGNN design and optimization, and review public datasets for evaluating model performance on various tasks, along with the corresponding publications.
- 1 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 25 (8) , 8949-8959
End-to-End Traffic Flow Rate Estimation From MPEG4 part-2 Compressed Video Streams
Automatic traffic surveillance usually relies on the estimation of traffic flow parameters through either dedicated sensors or the processing of road surveillance cameras. However, dedicated sensors are expensive to deploy and maintain. Moreover, available video processing algorithms usually require a complex multi-step pipeline, unsuited for large scale deployment. Herein, we address the problem of automatically estimating the flow rate (number of vehicles/unit of time) from surveillance cameras at low computation cost. To do so, we rely on end-to-end deep architectures applied to compressed MPEG4 part-2 video streams issued from road surveillance cameras. By leveraging the approximate flow representation induced by the compression, we heavily reduce the computation and memory requirements. We propose three end-to-end deep architectures using this coarse pixel flow representation as input. We also release two datasets, one based on synthetic videos and one collected on industrial tunnel cameras. By training the deep models on the newly introduced datasets, we evidence the effectiveness of predicting the flow rate directly from MPEG4 part-2 compressed video streams. We demonstrate an improved accuracy in comparison with a more classical RGB-based architecture and show an impressive speed up of $\times 2065$ at prediction time.
- 1 March 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 25 (8) , 8949-8959
End-to-End Traffic Flow Rate Estimation From MPEG4 part-2 Compressed Video Streams
Automatic traffic surveillance usually relies on the estimation of traffic flow parameters through either dedicated sensors or the processing of road surveillance cameras. However, dedicated sensors are expensive to deploy and maintain. Moreover, available video processing algorithms usually require a complex multi-step pipeline, unsuited for large scale deployment. Herein, we address the problem of automatically estimating the flow rate (number of vehicles/unit of time) from surveillance cameras at low computation cost. To do so, we rely on end-to-end deep architectures applied to compressed MPEG4 part-2 video streams issued from road surveillance cameras. By leveraging the approximate flow representation induced by the compression, we heavily reduce the computation and memory requirements. We propose three end-to-end deep architectures using this coarse pixel flow representation as input. We also release two datasets, one based on synthetic videos and one collected on industrial tunnel cameras. By training the deep models on the newly introduced datasets, we evidence the effectiveness of predicting the flow rate directly from MPEG4 part-2 compressed video streams. We demonstrate an improved accuracy in comparison with a more classical RGB-based architecture and show an impressive speed up of $\times 2065$ at prediction time.
- Open Access
- 15 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 15902-15916
Pseudo-Labeling With Large Language Models for Multi-Label Emotion Classification of French Tweets
This study proposes a novel semi-supervised multi-label emotion classification approach for French tweets based on pseudo-labeling. Human subjectivity in emotional expression makes it difficult for a machine to learn. Therefore, it necessitates training supervised learning models on large datasets annotated by multiple annotators. However, creating such datasets can be costly and time-consuming. Moreover, aggregating annotations from multiple annotators to capture their collective emotional state adds complexity to the task. Semi-supervised learning techniques have shown effectiveness with limited datasets. Furthermore, Large language Models (LLMs), particularly Chat-GPT, have demonstrated superior annotation accuracy compared to annotations obtained from crowdsourcing platforms, when both are evaluated against expert-annotated data. This work introduces a novel approach for multi-label emotion classification of French tweets by leveraging pseudo-labels generated through Chat-GPT, a robust large language model. Using zero-shot, one-shot, and few-shot learning techniques, Chat-GPT annotates the unlabelled part of our dataset. These Chat-GPT-annotated pseudo-labels are then merged with manual annotations, facilitating the training of a multi-label emotion classification model via semi-supervised learning. Furthermore, within the context of our research, we present a new French tweet dataset, containing testimonials from people affected by an urban industrial incident. This dataset features 2,350 tweets, each manually annotated by three human annotators based on 8 pre-identified emotions. Benchmark results are presented for multi-label emotion classification models employing both fully supervised and semi-supervised approaches with pseudo-labeling. Our findings demonstrate the superiority of our approach for multi-label emotion classification over standard pseudo-labeling and an established baseline.
- 15 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 15902-15916
Open AccessPseudo-Labeling With Large Language Models for Multi-Label Emotion Classification of French Tweets
This study proposes a novel semi-supervised multi-label emotion classification approach for French tweets based on pseudo-labeling. Human subjectivity in emotional expression makes it difficult for a machine to learn. Therefore, it necessitates training supervised learning models on large datasets annotated by multiple annotators. However, creating such datasets can be costly and time-consuming. Moreover, aggregating annotations from multiple annotators to capture their collective emotional state adds complexity to the task. Semi-supervised learning techniques have shown effectiveness with limited datasets. Furthermore, Large language Models (LLMs), particularly Chat-GPT, have demonstrated superior annotation accuracy compared to annotations obtained from crowdsourcing platforms, when both are evaluated against expert-annotated data. This work introduces a novel approach for multi-label emotion classification of French tweets by leveraging pseudo-labels generated through Chat-GPT, a robust large language model. Using zero-shot, one-shot, and few-shot learning techniques, Chat-GPT annotates the unlabelled part of our dataset. These Chat-GPT-annotated pseudo-labels are then merged with manual annotations, facilitating the training of a multi-label emotion classification model via semi-supervised learning. Furthermore, within the context of our research, we present a new French tweet dataset, containing testimonials from people affected by an urban industrial incident. This dataset features 2,350 tweets, each manually annotated by three human annotators based on 8 pre-identified emotions. Benchmark results are presented for multi-label emotion classification models employing both fully supervised and semi-supervised approaches with pseudo-labeling. Our findings demonstrate the superiority of our approach for multi-label emotion classification over standard pseudo-labeling and an established baseline.
- 19 August 2023
- Published by Springer Nature
- p. 182-199
Faster DAN: Multi-target Queries with Document Positional Encoding for End-to-End Handwritten Document Recognition
- 19 August 2023
- Published by Springer Nature
- p. 182-199
Faster DAN: Multi-target Queries with Document Positional Encoding for End-to-End Handwritten Document Recognition
- Top Cited Papers
- 10 January 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 45 (7) , 8227-8243
DAN: A Segmentation-Free Document Attention Network for Handwritten Document Recognition
Unconstrained handwritten text recognition is a challenging computer vision task. It is traditionally handled by a two-step approach, combining line segmentation followed by text line recognition. For the first time, we propose an end-to-end segmentation-free architecture for the task of handwritten document recognition: the Document Attention Network. In addition to text recognition, the model is trained to label text parts using begin and end tags in an XML-like fashion. This model is made up of an FCN encoder for feature extraction and a stack of transformer decoder layers for a recurrent token-by-token prediction process. It takes whole text documents as input and sequentially outputs characters, as well as logical layout tokens. Contrary to the existing segmentation-based approaches, the model is trained without using any segmentation label. We achieve competitive results on the READ 2016 dataset at page level, as well as double-page level with a CER of 3.43% and 3.70%, respectively. We also provide results for the RIMES 2009 dataset at page level, reaching 4.54% of CER. We provide all source code and pre-trained model weights at https://github.com/FactoDeepLearning/DAN
- 10 January 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 45 (7) , 8227-8243
Top Cited PapersDAN: A Segmentation-Free Document Attention Network for Handwritten Document Recognition
Unconstrained handwritten text recognition is a challenging computer vision task. It is traditionally handled by a two-step approach, combining line segmentation followed by text line recognition. For the first time, we propose an end-to-end segmentation-free architecture for the task of handwritten document recognition: the Document Attention Network. In addition to text recognition, the model is trained to label text parts using begin and end tags in an XML-like fashion. This model is made up of an FCN encoder for feature extraction and a stack of transformer decoder layers for a recurrent token-by-token prediction process. It takes whole text documents as input and sequentially outputs characters, as well as logical layout tokens. Contrary to the existing segmentation-based approaches, the model is trained without using any segmentation label. We achieve competitive results on the READ 2016 dataset at page level, as well as double-page level with a CER of 3.43% and 3.70%, respectively. We also provide results for the RIMES 2009 dataset at page level, reaching 4.54% of CER. We provide all source code and pre-trained model weights at https://github.com/FactoDeepLearning/DAN