Xudong Hong (PhD Student)

Personal Information

I am working in C7 2, 2.02 from Monday to Thursday. My another address is:

Department of Language Science and Technology | Saarland University | Germany
Saarland Informatics Campus C7.2 / room 2.02 D-66123 Saarbruecken
Tel.: +49 681 302 70020
Email: xhong@coli.uni-saarland.de

Research Interests

Natural Language Processing: event modeling; commonsense inference; pragmatics

Computer Vision: visual event recognition; multimodal representation

Machine Learning: transfer learning;

Publication

Google Scholar

Publications

2024

Conference paper

D2

N. Shvetsova, A. Kukleva, X. Hong, C. Rupprecht, B. Schiele, and H. Kuehne

“HowToCaption: Prompting LLMs to Transform Video Annotations at Scale,” in Computer Vision -- ECCV 2024, Milano, Italy.

more

BibTeX

@inproceedings{ShvetsovaECCV24,
TITLE = {{HowToCaption}: {P}rompting {LLM}s to Transform Video Annotations at Scale},
AUTHOR = {Shvetsova, Nina and Kukleva, Anna and Hong, Xudong and Rupprecht, Christian and Schiele, Bernt and Kuehne, Hilde},
LANGUAGE = {eng},
PUBLISHER = {Springer},
YEAR = {2024},
PUBLREMARK = {Accepted},
BOOKTITLE = {Computer Vision -- ECCV 2024},
SERIES = {Lecture Notes in Computer Science},
ADDRESS = {Milano, Italy},
}

Endnote

%0 Conference Proceedings
%A Shvetsova, Nina
%A Kukleva, Anna
%A Hong, Xudong
%A Rupprecht, Christian
%A Schiele, Bernt
%A Kuehne, Hilde
%+ Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
External Organizations
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
External Organizations
%T HowToCaption: Prompting LLMs to Transform Video Annotations at Scale : 
%G eng
%U http://hdl.handle.net/21.11116/0000-000F-D874-B
%D 2024
%B 18th European Conference on Computer Vision 
%Z date of event: 2024-09-29 - 2024-10-04
%C Milano, Italy
%B Computer Vision -- ECCV 2024
%I Springer
%B Lecture Notes in Computer Science

2023

Article

D2

X. Hong, A. Sayeed, K. Mehra, V. Demberg, and B. Schiele

“Visual Writing Prompts: Character-Grounded Story Generation with Curated Image Sequences,” Transactions of the Association for Computational Linguistics, vol. 11, 2023.

more

BibTeX

@article{hong2023visual,
TITLE = {Visual Writing Prompts: {C}haracter-Grounded Story Generation with Curated Image Sequences},
AUTHOR = {Hong, Xudong and Sayeed, Asad and Mehra, Khushboo and Demberg, Vera and Schiele, Bernt},
LANGUAGE = {eng},
ISSN = {2307-387X},
DOI = {10.1162/tacl_a_00553},
PUBLISHER = {MIT Press},
ADDRESS = {Cambridge, MA},
YEAR = {2023},
MARGINALMARK = {$\bullet$},
JOURNAL = {Transactions of the Association for Computational Linguistics},
VOLUME = {11},
PAGES = {565--581},
}

Endnote

%0 Journal Article
%A Hong, Xudong
%A Sayeed, Asad
%A Mehra, Khushboo
%A Demberg, Vera
%A Schiele, Bernt
%+ Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
External Organizations
External Organizations
External Organizations
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
%T Visual Writing Prompts: Character-Grounded Story Generation with Curated Image Sequences : 
%G eng
%U http://hdl.handle.net/21.11116/0000-000D-6330-D
%R 10.1162/tacl_a_00553
%7 2023
%D 2023
%J Transactions of the Association for Computational Linguistics
%V 11
%& 565
%P 565 - 581
%I MIT Press
%C Cambridge, MA
%@ false

2022

Article

D2

H. Cao, X. Hong, H. Tost, A. Meyer-Lindenberg, and E. Schwarz

“Advancing Translational Research in Neuroscience through Multi-task Learning,” Frontiers in Psychiatry, vol. 13, 2022.

more

BibTeX

@article{Cao22,
TITLE = {Advancing Translational Research in Neuroscience through Multi-task Learning},
AUTHOR = {Cao, Han and Hong, Xudong and Tost, Heike and Meyer-Lindenberg, Andreas and Schwarz, Emanuel},
LANGUAGE = {eng},
ISSN = {1664-0640},
DOI = {10.3389/fpsyt.2022.993289},
PUBLISHER = {Frontiers Research Foundation},
ADDRESS = {Lausanne, Switzerland},
YEAR = {2022},
MARGINALMARK = {$\bullet$},
JOURNAL = {Frontiers in Psychiatry},
VOLUME = {13},
EID = {993289},
}

Endnote

%0 Journal Article
%A Cao, Han
%A Hong, Xudong
%A Tost, Heike
%A Meyer-Lindenberg, Andreas
%A Schwarz, Emanuel
%+ External Organizations
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
External Organizations
External Organizations
External Organizations
%T Advancing Translational Research in Neuroscience through Multi-task Learning : 
%G eng
%U http://hdl.handle.net/21.11116/0000-000B-B59F-6
%R 10.3389/fpsyt.2022.993289
%2 PMC9714033
%7 2022
%D 2022
%J Frontiers in Psychiatry
%O Front Psychiatry
%V 13
%Z sequence number: 993289
%I Frontiers Research Foundation
%C Lausanne, Switzerland
%@ false

Conference paper

D2

D. Pu, X. Hong, P.-J. Lin, E. Chang, and V. Demberg

“Two-Stage Movie Script Summarization: An Efficient Method For Low-Resource Long Document Summarization,” in Proceedings of The Workshop on Automatic Summarization for Creative Writing (COLING 2022), Gyeongju, Republic of Korea, 2022.

more

BibTeX

@inproceedings{pu-etal-2022-two,
TITLE = {Two-Stage Movie Script Summarization: {A}n Efficient Method For Low-Resource Long Document Summarization},
AUTHOR = {Pu, Dongqi and Hong, Xudong and Lin, Pin-Jie and Chang, Ernie and Demberg, Vera},
LANGUAGE = {eng},
URL = {https://aclanthology.org/2022.creativesumm-1.9},
PUBLISHER = {ACL},
YEAR = {2022},
MARGINALMARK = {$\bullet$},
BOOKTITLE = {Proceedings of The Workshop on Automatic Summarization for Creative Writing (COLING 2022)},
EDITOR = {Mckeown, Kathleen},
PAGES = {57--66},
ADDRESS = {Gyeongju, Republic of Korea},
}

Endnote

%0 Conference Proceedings
%A Pu, Dongqi
%A Hong, Xudong
%A Lin, Pin-Jie
%A Chang, Ernie
%A Demberg, Vera
%+ External Organizations
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
External Organizations
External Organizations
External Organizations
%T Two-Stage Movie Script Summarization: An Efficient Method For Low-Resource Long Document Summarization : 
%G eng
%U http://hdl.handle.net/21.11116/0000-000D-6337-6
%U https://aclanthology.org/2022.creativesumm-1.9
%D 2022
%B Workshop on Automatic Summarization for Creative Writing
%Z date of event: 2022-10-17 - 2022-10-17
%C Gyeongju, Republic of Korea
%B Proceedings of The Workshop on Automatic Summarization for Creative Writing
%E Mckeown, Kathleen
%P 57 - 66
%I ACL

2020

Conference paper

D2

X. Hong, R. Shetty, A. Sayeed, K. Mehra, V. Demberg, and B. Schiele

“Diverse and Relevant Visual Storytelling with Scene Graph Embeddings,” in Proceedings of the 24th Conference on Computational Natural Language Learning (CoNLL 2020), Online, 2020.

more

BibTeX

@inproceedings{hong-etal-2020-diverse,
TITLE = {Diverse and Relevant Visual Storytelling with Scene Graph Embeddings},
AUTHOR = {Hong, Xudong and Shetty, Rakshith and Sayeed, Asad and Mehra, Khushboo and Demberg, Vera and Schiele, Bernt},
LANGUAGE = {eng},
ISBN = {978-1-952148-63-7},
DOI = {10.18653/v1/2020.conll-1.34},
PUBLISHER = {ACL},
YEAR = {2020},
BOOKTITLE = {Proceedings of the 24th Conference on Computational Natural Language Learning (CoNLL 2020)},
PAGES = {420--430},
ADDRESS = {Online},
}

Endnote

%0 Conference Proceedings
%A Hong, Xudong
%A Shetty, Rakshith
%A Sayeed, Asad
%A Mehra, Khushboo
%A Demberg, Vera
%A Schiele, Bernt
%+ Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
External Organizations
External Organizations
External Organizations
Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
%T Diverse and Relevant Visual Storytelling with Scene Graph Embeddings : 
%G eng
%U http://hdl.handle.net/21.11116/0000-0007-AE1B-8
%R 10.18653/v1/2020.conll-1.34
%D 2020
%B 24th Conference on Computational Natural Language Learning
%Z date of event: 2020-11-19 - 2020-11-20
%C Online
%B Proceedings of the 24th Conference on Computational Natural Language Learning
%P 420 - 430
%I ACL
%@  978-1-952148-63-7
%U https://www.aclweb.org/anthology/2020.conll-1.34.pdf

2019

Conference paper

D2

X. Hong, E. Chang, and V. Demberg

“Improving Language Generation from Feature-Rich Tree-Structured Data with Relational Graph Convolutional Encoders,” in Multilingual Surface Realisation (MSR 2019), Hong Kong, China, 2019.

more

BibTeX

@inproceedings{hong2019improving,
TITLE = {Improving Language Generation from Feature-Rich Tree-Structured Data with Relational Graph Convolutional Encoders},
AUTHOR = {Hong, Xudong and Chang, Ernie and Demberg, Vera},
LANGUAGE = {eng},
ISBN = {978-1-950737-76-5},
DOI = {10.18653/v1/D19-6310},
PUBLISHER = {ACL},
YEAR = {2019},
BOOKTITLE = {Multilingual Surface Realisation (MSR 2019)},
EDITOR = {Mille, Simon and Belz, Anja and Bohnet, Bernd and Graham, Yvette and Wanner, Leo},
PAGES = {75--80},
ADDRESS = {Hong Kong, China},
}

Endnote

%0 Conference Proceedings
%A Hong, Xudong
%A Chang, Ernie
%A Demberg, Vera
%+ Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society
External Organizations
External Organizations
%T Improving Language Generation from Feature-Rich Tree-Structured Data with Relational Graph Convolutional Encoders : 
%G eng
%U http://hdl.handle.net/21.11116/0000-0008-3265-E
%R 10.18653/v1/D19-6310
%D 2019
%B 2nd Workshop on Multilingual Surface Realisation
%Z date of event: 2019-11-03 - 2019-11-03
%C Hong Kong, China
%B Multilingual Surface Realisation
%E Mille, Simon; Belz, Anja; Bohnet, Bernd; Graham, Yvette; Wanner, Leo
%P 75 - 80
%I ACL
%@ 978-1-950737-76-5
%U https://www.aclweb.org/anthology/D19-6310