{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T18:17:08Z","timestamp":1783189028784,"version":"3.54.6"},"reference-count":48,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Expert Systems with Applications"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.eswa.2026.133174","type":"journal-article","created":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T16:32:09Z","timestamp":1781022729000},"page":"133174","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PA","title":["NEXPRO: Multimodal negative expression prompting for open-set video-based facial expression recognition"],"prefix":"10.1016","volume":"331","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3199-2631","authenticated-orcid":false,"given":"Qintai","family":"Hu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yifei","family":"Su","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1679-3394","authenticated-orcid":false,"given":"Fan","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6084-1851","authenticated-orcid":false,"given":"Xiaodi","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5041-6093","authenticated-orcid":false,"given":"Qionghao","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1371-2608","authenticated-orcid":false,"given":"Changqin","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.eswa.2026.133174_bib0001","unstructured":"Achiam, J., Adler, S., Agarwal, S., Ahmad, L., Akkaya, I., Aleman, F. L., Almeida, D., Altenschmidt, J., Altman, S., Anadkat, S. et al. (2023). GPT-4 technical report. arXiv: 2303.08774."},{"key":"10.1016\/j.eswa.2026.133174_bib0002","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"13349","article-title":"Evidential deep learning for open set action recognition","author":"Bao","year":"2021"},{"issue":"11","key":"10.1016\/j.eswa.2026.133174_bib0003","first-page":"8065","article-title":"Adversarial reciprocal points learning for open set recognition","volume":"44","author":"Chen","year":"2021","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.eswa.2026.133174_bib0004","series-title":"Computer vision\u2013ECCV 2020: 16th European conference, Glasgow, UK, August 23\u201328, 2020, proceedings, Part III 16","first-page":"507","article-title":"Learning open set network with discriminative reciprocal points","author":"Chen","year":"2020"},{"key":"10.1016\/j.eswa.2026.133174_bib0005","series-title":"Proceedings of the 32nd ACM international conference on multimedia","first-page":"2301","article-title":"FineCLIPER: Multi-modal fine-grained CLIP for dynamic facial expression recognition with adapters","author":"Chen","year":"2024"},{"key":"10.1016\/j.eswa.2026.133174_bib0006","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"4673","article-title":"MMA-DFER: Multimodal adaptation of unimodal models for dynamic facial expression recognition in-the-wild","author":"Chumachenko","year":"2024"},{"key":"10.1016\/j.eswa.2026.133174_bib0007","series-title":"Proceedings of the 33rd ACM international conference on multimedia","first-page":"5587","article-title":"Learning from heterogeneity: Generalizing dynamic facial expression recognition via distributionally robust optimization","author":"Cui","year":"2025"},{"key":"10.1016\/j.eswa.2026.133174_bib0008","series-title":"Proceedings of the 2015\u202fACM on international conference on multimodal interaction","first-page":"423","article-title":"Video and image based emotion recognition challenges in the wild: Emotiw 2015","author":"Dhall","year":"2015"},{"key":"10.1016\/j.eswa.2026.133174_bib0009","doi-asserted-by":"crossref","first-page":"9464","DOI":"10.1109\/TMM.2023.3252275","article-title":"Spatial-temporal exclusive capsule network for open set action recognition","volume":"25","author":"Feng","year":"2023","journal-title":"IEEE Transactions on Multimedia"},{"key":"10.1016\/j.eswa.2026.133174_bib0010","series-title":"2024\u202fIEEE 18th international conference on automatic face and gesture recognition (FG)","first-page":"1","article-title":"EmoCLIP: A vision-language method for zero-shot video facial expression recognition","author":"Foteinopoulou","year":"2024"},{"issue":"2","key":"10.1016\/j.eswa.2026.133174_bib0011","doi-asserted-by":"crossref","first-page":"581","DOI":"10.1007\/s11263-023-01891-x","article-title":"CLIP-adapter: Better vision-language models with feature adapters","volume":"132","author":"Gao","year":"2024","journal-title":"International Journal of Computer Vision"},{"issue":"3","key":"10.1016\/j.eswa.2026.133174_bib0012","doi-asserted-by":"crossref","first-page":"1675","DOI":"10.1109\/TAFFC.2025.3530973","article-title":"Modeling fine-grained relations in dynamic space-time graphs for video-based facial expression recognition","volume":"16","author":"Huang","year":"2025","journal-title":"IEEE Transactions on Affective Computing"},{"issue":"4","key":"10.1016\/j.eswa.2026.133174_bib0013","first-page":"4214","article-title":"Class-specific semantic reconstruction for open set recognition","volume":"45","author":"Huang","year":"2022","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.eswa.2026.133174_bib0014","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2026.114329","article-title":"Prompting multimodal vision-language models for automated student engagement prediction","volume":"172","author":"Jiang","year":"2026","journal-title":"Engineering Applications of Artificial Intelligence"},{"issue":"7","key":"10.1016\/j.eswa.2026.133174_bib0015","doi-asserted-by":"crossref","first-page":"4366","DOI":"10.1007\/s11263-025-02384-9","article-title":"Unknown support prototype set for open set recognition","volume":"133","author":"Jiang","year":"2025","journal-title":"International Journal of Computer Vision"},{"key":"10.1016\/j.eswa.2026.133174_bib0016","series-title":"Proceedings of the 28th ACM international conference on multimedia","first-page":"2881","article-title":"Dfew: A large-scale database for recognizing dynamic facial expressions in the wild","author":"Jiang","year":"2020"},{"key":"10.1016\/j.eswa.2026.133174_bib0017","series-title":"Advances in neural information processing systems","first-page":"18661","article-title":"Supervised contrastive learning","volume":"33","author":"Khosla","year":"2020"},{"key":"10.1016\/j.eswa.2026.133174_bib0018","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"13446","article-title":"All beings are equal in open set recognition","volume":"vol. 38","author":"Li","year":"2024"},{"key":"10.1016\/j.eswa.2026.133174_bib0019","series-title":"2024\u202fIEEE International conference on multimedia and expo (ICME)","first-page":"1","article-title":"CLIPER: A unified vision-language framework for in-the-wild facial expression recognition","author":"Li","year":"2024"},{"key":"10.1016\/j.eswa.2026.133174_bib0020","series-title":"International conference on machine learning","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","author":"Li","year":"2022"},{"key":"10.1016\/j.eswa.2026.133174_bib0021","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1109\/TIP.2024.3504298","article-title":"PTH-Net: Dynamic facial expression recognition without face detection and alignment","volume":"34","author":"Li","year":"2024","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.1016\/j.eswa.2026.133174_bib0022","series-title":"Proceedings of the 30th ACM international conference on multimedia","first-page":"24","article-title":"MAFW: A large-scale, multi-modal, compound affective database for dynamic facial expression recognition in the wild","author":"Liu","year":"2022"},{"key":"10.1016\/j.eswa.2026.133174_bib0023","series-title":"Proceedings of the 32nd ACM international conference on multimedia","first-page":"5722","article-title":"Open-set video-based facial expression recognition with human expression-sensitive prompting","author":"Liu","year":"2024"},{"key":"10.1016\/j.eswa.2026.133174_bib0024","series-title":"Proceedings of the IEEE\/CVF winter conference on applications of computer vision","first-page":"3570","article-title":"Class anchor clustering: A loss for distance-based open set recognition","author":"Miller","year":"2021"},{"key":"10.1016\/j.eswa.2026.133174_bib0025","series-title":"European conference on computer vision","first-page":"365","article-title":"Difficulty-aware simulator for open set recognition","author":"Moon","year":"2022"},{"key":"10.1016\/j.eswa.2026.133174_bib0026","series-title":"Proceedings of the European conference on computer vision (ECCV)","first-page":"613","article-title":"Open set learning with counterfactual images","author":"Neal","year":"2018"},{"issue":"6","key":"10.1016\/j.eswa.2026.133174_bib0027","doi-asserted-by":"crossref","first-page":"9946","DOI":"10.1109\/TNNLS.2025.3548669","article-title":"Learning sequential variation information for dynamic facial expression recognition","volume":"36","author":"Pan","year":"2025","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.1016\/j.eswa.2026.133174_bib0028","series-title":"International conference on machine learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.eswa.2026.133174_bib0029","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"28578","article-title":"Argue: Attribute-guided prompt tuning for vision-language models","author":"Tian","year":"2024"},{"key":"10.1016\/j.eswa.2026.133174_bib0030","series-title":"International conference on learning representations","article-title":"Open-set recognition: A good closed-set classifier is all you need","author":"Vaze","year":"2021"},{"key":"10.1016\/j.eswa.2026.133174_bib0031","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"20694","article-title":"Fix-CLIP: Dual-branch hierarchical contrastive learning via synthetic captions for better understanding of long text","author":"Wang","year":"2025"},{"key":"10.1016\/j.eswa.2026.133174_bib0032","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"17958","article-title":"Rethinking the learning paradigm for dynamic facial expression recognition","author":"Wang","year":"2023"},{"key":"10.1016\/j.eswa.2026.133174_bib0033","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision","first-page":"1802","article-title":"Clipn for zero-shot ood detection: Teaching CLIP to say no","author":"Wang","year":"2023"},{"key":"10.1016\/j.eswa.2026.133174_bib0034","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"23034","article-title":"Vita-CLIP: Video and text adaptive CLIP via multimodal prompting","author":"Wasim","year":"2023"},{"issue":"7","key":"10.1016\/j.eswa.2026.133174_bib0035","doi-asserted-by":"crossref","first-page":"4747","DOI":"10.1109\/TPAMI.2024.3357503","article-title":"Building an open-vocabulary video CLIP model with better architectures, optimization and data","volume":"46","author":"Wu","year":"2024","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.eswa.2026.133174_bib0036","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.129332","article-title":"Mul-FES: A multimodal facial expression spotting method that integrates textual information","volume":"304","author":"Yang","year":"2026","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.133174_bib0037","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"6757","article-title":"Visual-language prompt tuning with knowledge-guided context optimization","author":"Yao","year":"2023"},{"key":"10.1016\/j.eswa.2026.133174_bib0038","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"4016","article-title":"Classification-reconstruction learning for open-set recognition","author":"Yoshihashi","year":"2019"},{"key":"10.1016\/j.eswa.2026.133174_bib0039","series-title":"European conference on computer vision","first-page":"310","article-title":"Long-CLIP: Unlocking the long-text capability of CLIP","author":"Zhang","year":"2024"},{"key":"10.1016\/j.eswa.2026.133174_bib0040","unstructured":"Zhang, R., Fang, R., Zhang, W., Gao, P., Li, K., Dai, J., Qiao, Y., & Li, H. (2021). Tip-adapter: Training-free CLIP-adapter for better vision-language modeling. arXiv: 2111.03930."},{"key":"10.1016\/j.eswa.2026.133174_bib0041","unstructured":"Zhang, Y., Fan, H., & Yang, Y. (2024b). Prompt-aware adapter: Towards learning adaptive visual tokens for multimodal large language models. arXiv: 2405.15684."},{"key":"10.1016\/j.eswa.2026.133174_bib0042","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"646","article-title":"Open-set facial expression recognition","volume":"vol. 38","author":"Zhang","year":"2024"},{"key":"10.1016\/j.eswa.2026.133174_bib0043","unstructured":"Zhao, Z., & Patras, I. (2023). Prompting visual-language models for dynamic facial expression recognition. arXiv: 2308.13382."},{"key":"10.1016\/j.eswa.2026.133174_bib0044","article-title":"VLCA: Vision-language feature enhancement with cross-attention learning for facial expression recognition","volume":"299","author":"Zheng","year":"2025","journal-title":"Expert Systems with Applications"},{"key":"10.1016\/j.eswa.2026.133174_bib0045","series-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","first-page":"2921","article-title":"Learning deep features for discriminative localization","author":"Zhou","year":"2016"},{"key":"10.1016\/j.eswa.2026.133174_bib0046","series-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","first-page":"16816","article-title":"Conditional prompt learning for vision-language models","author":"Zhou","year":"2022"},{"issue":"9","key":"10.1016\/j.eswa.2026.133174_bib0047","doi-asserted-by":"crossref","first-page":"2337","DOI":"10.1007\/s11263-022-01653-1","article-title":"Learning to prompt for vision-language models","volume":"130","author":"Zhou","year":"2022","journal-title":"International Journal of Computer Vision"},{"key":"10.1016\/j.eswa.2026.133174_bib0048","series-title":"Proceedings of the 31st ACM international conference on multimedia","first-page":"862","article-title":"Variance-aware bi-attention expression transformer for open-set facial expression recognition in the wild","author":"Zhu","year":"2023"}],"container-title":["Expert Systems with Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S095741742602083X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S095741742602083X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T17:20:40Z","timestamp":1783185640000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S095741742602083X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":48,"alternative-id":["S095741742602083X"],"URL":"https:\/\/doi.org\/10.1016\/j.eswa.2026.133174","relation":{},"ISSN":["0957-4174"],"issn-type":[{"value":"0957-4174","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"NEXPRO: Multimodal negative expression prompting for open-set video-based facial expression recognition","name":"articletitle","label":"Article Title"},{"value":"Expert Systems with Applications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.eswa.2026.133174","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"133174"}}