2026

Fu, Junchen, Deng, Wenhao, Zheng, Kaiwen, Arapakis, Ioannis, Ye, Yu, Ni, Yongxin, Jose, Joemon M. ORCID: https://orcid.org/0000-0001-9228-1759 and Ge, Xuri (2026) Benchmarking Multimodal Large Language Models for missing modality completion in product catalogues. Pattern Recognition, 180(A), 114020. (doi: 10.1016/j.patcog.2026.114020)

Zheng, Kaiwen, Fu, Junchen, XU, Songpei, He, Yaoqin, Jose, Joemon M. ORCID: https://orcid.org/0000-0001-9228-1759, Han, Hu and Ge, Xuri ORCID: https://orcid.org/0000-0002-3925-4951 (2026) Focal-RegionFace: Generating Fine-Grained Multi-attribute Descriptions for Arbitrarily Selected Face Focal Regions. In: 16th ACM International Conference on Multimedia Retrieval (ICMR 2026), Amsterdam, The Netherlands, 16-19 June 2026, pp. 2656-2665. ISBN 9798400726170 (doi: 10.1145/3805622.3810710)

Ye, Yu, Fu, Junchen, Song, Yu, Zheng, Kaiwen and Jose, Joemon M. ORCID: https://orcid.org/0000-0001-9228-1759 (2026) A reproducibility study of multimodal embeddings for recommender systems. International Journal of Multimedia Information Retrieval, 15(2), 14. (doi: 10.1007/s13735-026-00408-9)

Fu, Junchen, Ge, Xuri, Zheng, Kaiwen, Karatzoglou, Alexandros, Arapakis, Ioannis, Xin, Xin, Ni, Yongxin and Jose, Joemon M. ORCID: https://orcid.org/0000-0001-9228-1759 (2026) LLMpopcorn: exploring LLMs as assistants for popular micro-video generation. In: IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2026), Barcelona, Spain, 04-08 May 2026, pp. 12007-12011. ISBN 9798331567026 (doi: 10.1109/ICASSP55912.2026.11463708)

Ge, Xuri, Zhang, Tianshuo, Li, Ruihan, Ye, Hui, Zheng, Kaiwen, Fu, Junchen, Huo, Da, Jose, Joemon M. ORCID: https://orcid.org/0000-0001-9228-1759 and Han, Hu (2026) A Comprehensive Review of Multimodal Facial State Analysis: Tasks, Methods, and Resources. In: IEEE International Conference on Multimedia and Expo (ICME 2026), Bangkok, Thailand, 05-09 July 2026, (Accepted for Publication)

Ye, Yu, Fu, Junchen, Song, Yu, Zheng, Kaiwen and Jose, Joemon ORCID: https://orcid.org/0000-0001-9228-1759 (2026) Are Multimodal Embeddings Truly Beneficial for Recommendation? A Deep Dive into Whole vs. Individual Modalities. In: 48th European Conference on Information Retrieval (ECIR 2026), Delft, The Netherlands, 30 March - 1 April 2026, pp. 66-81. ISBN 9783032213235 (doi: 10.1007/978-3-032-21324-2_5)

2025

Zheng, Kaiwen, Ge, Xuri ORCID: https://orcid.org/0000-0002-3925-4951, Fu, Junchen, Peng, Jun and Jose, Joemon ORCID: https://orcid.org/0000-0001-9228-1759 (2025) Multimodal Representation Learning Techniques for Comprehensive Facial State Analysis. In: 2025 IEEE International Conference on Multimedia and Expo (ICME), Nantes, France, 30 Jun - 04 Jul 2025, ISBN 9798331594954 (doi: 10.1109/ICME59968.2025.11208908)

Parker, Deven ORCID: https://orcid.org/0000-0003-0467-5294, Zheng, Kaiwen, Gamer, Michael and Jose, Joemon M. ORCID: https://orcid.org/0000-0001-9228-1759 (2025) Unlocking 18th- and 19th-century playbills with AI: an experiment in qualitative data categorization. Umanistica Digitale, 9(21), pp. 33-83. (doi: 10.60923/issn.2532-8816/21718)

Fu, Junchen, Ge, Xuri, Xin, Xin, Karatzoglou, Alexandros, Arapakis, Ioannis, Zheng, Kaiwen, Ni, Yongxin and Jose, Joemon M. ORCID: https://orcid.org/0000-0001-9228-1759 (2025) Efficient and effective adaptation of multimodal foundation models in sequential recommendation. IEEE Transactions on Knowledge and Data Engineering, (doi: 10.1109/TKDE.2025.3608071) (Early Online Publication)

He, Yaoqin, Fu, Junchen, Zheng, Kaiwen, Xu, Songpei, Chen, Fuhai, Li, Jie, Jose, Joemon M. ORCID: https://orcid.org/0000-0001-9228-1759 and Ge, Xuri (2025) Double-Filter: Efficient Fine-tuning of Pre-trained Vision-Language Models via Patch&Layer Filtering. In: ICML 2025, Vancouver, Canada, 13-19 July 2025,

Ge, Xuri, Li, Linqing, Xu, Songpei, Zheng, Kaiwen, He, Yaoqin, Fu, Junchen and Jose, Joemon M. ORCID: https://orcid.org/0000-0001-9228-1759 (2025) The DenseCap-Guided Attention Network For Image-Text Matching. In: ACM Web Conference 2025, Sydney, Australia, 28 April - 2 May 2025, pp. 2153-2160. ISBN 9798400713316 (doi: 10.1145/3701716.3717564)

Liu, Zhiyu, Fu, Junchen, Zheng, Kaiwen and Jose, Joemon M. ORCID: https://orcid.org/0000-0001-9228-1759 (2025) Exploring Multimodal Pre-trained Models for Speech Emotion Recognition. In: ACM Web Conference 2025, Sydney, Australia, 28 April - 2 May 2025, pp. 2176-2180. ISBN 9798400713316 (doi: 10.1145/3701716.3717561)

Articles

Fu, Junchen, Deng, Wenhao, Zheng, Kaiwen, Arapakis, Ioannis, Ye, Yu, Ni, Yongxin, Jose, Joemon M. ORCID: https://orcid.org/0000-0001-9228-1759 and Ge, Xuri (2026) Benchmarking Multimodal Large Language Models for missing modality completion in product catalogues. Pattern Recognition, 180(A), 114020. (doi: 10.1016/j.patcog.2026.114020)

Ye, Yu, Fu, Junchen, Song, Yu, Zheng, Kaiwen and Jose, Joemon M. ORCID: https://orcid.org/0000-0001-9228-1759 (2026) A reproducibility study of multimodal embeddings for recommender systems. International Journal of Multimedia Information Retrieval, 15(2), 14. (doi: 10.1007/s13735-026-00408-9)

Parker, Deven ORCID: https://orcid.org/0000-0003-0467-5294, Zheng, Kaiwen, Gamer, Michael and Jose, Joemon M. ORCID: https://orcid.org/0000-0001-9228-1759 (2025) Unlocking 18th- and 19th-century playbills with AI: an experiment in qualitative data categorization. Umanistica Digitale, 9(21), pp. 33-83. (doi: 10.60923/issn.2532-8816/21718)

Fu, Junchen, Ge, Xuri, Xin, Xin, Karatzoglou, Alexandros, Arapakis, Ioannis, Zheng, Kaiwen, Ni, Yongxin and Jose, Joemon M. ORCID: https://orcid.org/0000-0001-9228-1759 (2025) Efficient and effective adaptation of multimodal foundation models in sequential recommendation. IEEE Transactions on Knowledge and Data Engineering, (doi: 10.1109/TKDE.2025.3608071) (Early Online Publication)

Conference Proceedings

Zheng, Kaiwen, Fu, Junchen, XU, Songpei, He, Yaoqin, Jose, Joemon M. ORCID: https://orcid.org/0000-0001-9228-1759, Han, Hu and Ge, Xuri ORCID: https://orcid.org/0000-0002-3925-4951 (2026) Focal-RegionFace: Generating Fine-Grained Multi-attribute Descriptions for Arbitrarily Selected Face Focal Regions. In: 16th ACM International Conference on Multimedia Retrieval (ICMR 2026), Amsterdam, The Netherlands, 16-19 June 2026, pp. 2656-2665. ISBN 9798400726170 (doi: 10.1145/3805622.3810710)

Fu, Junchen, Ge, Xuri, Zheng, Kaiwen, Karatzoglou, Alexandros, Arapakis, Ioannis, Xin, Xin, Ni, Yongxin and Jose, Joemon M. ORCID: https://orcid.org/0000-0001-9228-1759 (2026) LLMpopcorn: exploring LLMs as assistants for popular micro-video generation. In: IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2026), Barcelona, Spain, 04-08 May 2026, pp. 12007-12011. ISBN 9798331567026 (doi: 10.1109/ICASSP55912.2026.11463708)

Ge, Xuri, Zhang, Tianshuo, Li, Ruihan, Ye, Hui, Zheng, Kaiwen, Fu, Junchen, Huo, Da, Jose, Joemon M. ORCID: https://orcid.org/0000-0001-9228-1759 and Han, Hu (2026) A Comprehensive Review of Multimodal Facial State Analysis: Tasks, Methods, and Resources. In: IEEE International Conference on Multimedia and Expo (ICME 2026), Bangkok, Thailand, 05-09 July 2026, (Accepted for Publication)

Ye, Yu, Fu, Junchen, Song, Yu, Zheng, Kaiwen and Jose, Joemon ORCID: https://orcid.org/0000-0001-9228-1759 (2026) Are Multimodal Embeddings Truly Beneficial for Recommendation? A Deep Dive into Whole vs. Individual Modalities. In: 48th European Conference on Information Retrieval (ECIR 2026), Delft, The Netherlands, 30 March - 1 April 2026, pp. 66-81. ISBN 9783032213235 (doi: 10.1007/978-3-032-21324-2_5)

Zheng, Kaiwen, Ge, Xuri ORCID: https://orcid.org/0000-0002-3925-4951, Fu, Junchen, Peng, Jun and Jose, Joemon ORCID: https://orcid.org/0000-0001-9228-1759 (2025) Multimodal Representation Learning Techniques for Comprehensive Facial State Analysis. In: 2025 IEEE International Conference on Multimedia and Expo (ICME), Nantes, France, 30 Jun - 04 Jul 2025, ISBN 9798331594954 (doi: 10.1109/ICME59968.2025.11208908)

He, Yaoqin, Fu, Junchen, Zheng, Kaiwen, Xu, Songpei, Chen, Fuhai, Li, Jie, Jose, Joemon M. ORCID: https://orcid.org/0000-0001-9228-1759 and Ge, Xuri (2025) Double-Filter: Efficient Fine-tuning of Pre-trained Vision-Language Models via Patch&Layer Filtering. In: ICML 2025, Vancouver, Canada, 13-19 July 2025,

Ge, Xuri, Li, Linqing, Xu, Songpei, Zheng, Kaiwen, He, Yaoqin, Fu, Junchen and Jose, Joemon M. ORCID: https://orcid.org/0000-0001-9228-1759 (2025) The DenseCap-Guided Attention Network For Image-Text Matching. In: ACM Web Conference 2025, Sydney, Australia, 28 April - 2 May 2025, pp. 2153-2160. ISBN 9798400713316 (doi: 10.1145/3701716.3717564)

Liu, Zhiyu, Fu, Junchen, Zheng, Kaiwen and Jose, Joemon M. ORCID: https://orcid.org/0000-0001-9228-1759 (2025) Exploring Multimodal Pre-trained Models for Speech Emotion Recognition. In: ACM Web Conference 2025, Sydney, Australia, 28 April - 2 May 2025, pp. 2176-2180. ISBN 9798400713316 (doi: 10.1145/3701716.3717561)