{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,24]],"date-time":"2026-10-24T06:33:45Z","timestamp":1792823625247,"version":"4.5.0"},"reference-count":68,"publisher":"Springer Science and Business Media LLC","issue":"9","license":[{"start":{"date-parts":[[2025,6,14]],"date-time":"2025-06-14T00:00:00Z","timestamp":1749859200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,6,14]],"date-time":"2025-06-14T00:00:00Z","timestamp":1749859200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2025,9]]},"DOI":"10.1007\/s11263-025-02495-3","type":"journal-article","created":{"date-parts":[[2025,6,14]],"date-time":"2025-06-14T09:02:35Z","timestamp":1749891755000},"page":"6456-6472","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["StimuVAR: Spatiotemporal Stimuli-Aware Video Affective Reasoning with Multimodal Large Language Models"],"prefix":"10.1007","volume":"133","author":[{"given":"Yuxiang","family":"Guo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Faizan","family":"Siddiqui","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rama","family":"Chellappa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shao-Yuan","family":"Lo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,6,14]]},"reference":[{"key":"2495_CR1","unstructured":"Achiam, J., Adler, S., Agarwal, S., Ahmad, L., Akkaya, I., Aleman, F. L., Almeida, D., et al. (2023). Gpt-4 technical report. arXiv preprint arXiv:2303.08774"},{"key":"2495_CR2","doi-asserted-by":"crossref","unstructured":"Achlioptas, P., Ovsjanikov, M., Guibas, L., & Tulyakov, S. (2023). Affection: Learning affective explanations for real-world visual data. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition","DOI":"10.1109\/CVPR52729.2023.00642"},{"key":"2495_CR3","doi-asserted-by":"crossref","unstructured":"Achlioptas, P., Ovsjanikov, M., Haydarov, K., Elhoseiny, M., & Guibas, L.J. (2021) Artemis: Affective language for visual art. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition","DOI":"10.1109\/CVPR46437.2021.01140"},{"key":"2495_CR4","unstructured":"Anthropic: Claude 3.5 sonnet model card addendum (2024)"},{"key":"2495_CR5","doi-asserted-by":"crossref","unstructured":"Bielozorov, A., Bezbradica, M., & Helfert, M. (2019). The role of user emotions for content personalization in e-commerce: literature review. In: International Conference on HCI in Business, Government and Organizations","DOI":"10.1007\/978-3-030-22335-9_12"},{"key":"2495_CR6","doi-asserted-by":"crossref","unstructured":"Brosch, T., Pourtois, G., & Sander, D. (2010). The perception and categorisation of emotional stimuli: A review. In: Cognition and Emotion","DOI":"10.1080\/02699930902975754"},{"key":"2495_CR7","unstructured":"Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J. D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020). Language models are few-shot learners. In: Conference on Neural Information Processing Systems"},{"key":"2495_CR8","unstructured":"Cheng, Z., Cheng, Z.-Q., He, J.-Y., Sun, J., Wang, K., Lin, Y., Lian, Z., et al. (2024). Emotion-llama: Multimodal emotion recognition and reasoning with instruction tuning. In: Conference on Neural Information Processing Systems"},{"key":"2495_CR9","doi-asserted-by":"crossref","unstructured":"Cordonnier, J.-B., Mahendran, A., Dosovitskiy, A., Weissenborn, D., Uszkoreit, J., & Unterthiner, T. (2021). Differentiable patch selection for image recognition. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition","DOI":"10.1109\/CVPR46437.2021.00238"},{"key":"2495_CR10","doi-asserted-by":"crossref","unstructured":"Cowen, A. S., & Keltner, D. (2017). Self-report captures 27 distinct categories of emotion bridged by continuous gradients. In: Proceedings of the National Academy of Sciences","DOI":"10.1073\/pnas.1702247114"},{"key":"2495_CR11","unstructured":"Dai, W., Li, J., Li, D., et al. (2023). Instructblip: Towards general-purpose vision-language models with instruction tuning. In: Conference on Neural Information Processing Systems"},{"key":"2495_CR12","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., et al. (2021). An image is worth 16x16 words: Transformers for image recognition at scale. In: International Conference on Learning Representations"},{"key":"2495_CR13","doi-asserted-by":"crossref","unstructured":"Dosovitskiy, A., Fischer, P., Ilg, E., Hausser, P., Hazirbas, C., Golkov, V., Van Der\u00a0Smagt, P., et al. (2015). Flownet: Learning optical flow with convolutional networks. In: IEEE\/CVF International Conference on Computer Vision","DOI":"10.1109\/ICCV.2015.316"},{"key":"2495_CR14","unstructured":"Dubey, A., Jauhri, A., Pandey, A., et al. (2024). The llama 3 herd of models. arXiv preprint arXiv:2407.21783"},{"key":"2495_CR15","doi-asserted-by":"crossref","unstructured":"Ekman, P., & Friesen, W. V. (1971). Constants across cultures in the face and emotion. In: Journal of Personality and Social Psychology","DOI":"10.1037\/h0030377"},{"key":"2495_CR16","doi-asserted-by":"crossref","unstructured":"Epstein, D., Chen, B., & Vondrick, C. (2020). Oops! predicting unintentional action in video. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition","DOI":"10.1109\/CVPR42600.2020.00100"},{"key":"2495_CR17","unstructured":"Frijda, N. H. (1986). The emotions. In: Cambridge University Press"},{"key":"2495_CR18","doi-asserted-by":"crossref","unstructured":"Hessel, J., Holtzman, A., Forbes, M., Bras, R. L., & Choi, Y. (2021). Clipscore: A reference-free evaluation metric for image captioning. In: Conference on Empirical Methods in Natural Language Processing","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"2495_CR19","unstructured":"Hu, E. J., Shen, Y., Wallis, P., et al. (2022). Lora: Low-rank adaptation of large language models. In: International Conference on Learning Representations"},{"key":"2495_CR20","doi-asserted-by":"crossref","unstructured":"Ilg, E., Mayer, N., Saikia, T., Keuper, M., Dosovitskiy, A., & Brox, T. (2017). Flownet 2.0: Evolution of optical flow estimation with deep networks. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition","DOI":"10.1109\/CVPR.2017.179"},{"key":"2495_CR21","doi-asserted-by":"crossref","unstructured":"Jiang, Y.-G., Xu, B., & Xue, X. (2014). Predicting emotions in user-generated videos. In: AAAI Conference on Artificial Intelligence","DOI":"10.1609\/aaai.v28i1.8724"},{"key":"2495_CR22","doi-asserted-by":"crossref","unstructured":"Jin, P., Takanobu, R., Zhang, W., Cao, X., & Yuan, L. (2024). Chat-univi: Unified visual representation empowers large language models with image and video understanding. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition","DOI":"10.1109\/CVPR52733.2024.01300"},{"key":"2495_CR23","doi-asserted-by":"crossref","unstructured":"Kosti, R., Alvarez, J. M., Recasens, A., & Lapedriza, A. (2019). Context based emotion recognition using emotic dataset. In: IEEE Transactions on Pattern Analysis and Machine Intelligence","DOI":"10.1109\/TPAMI.2019.2916866"},{"key":"2495_CR24","doi-asserted-by":"crossref","unstructured":"Lee, J., Kim, S., Kim, S., Park, J., & Sohn, K. (2019). Context-aware emotion recognition networks. In: IEEE\/CVF International Conference on Computer Vision","DOI":"10.1109\/ICCV.2019.01024"},{"key":"2495_CR25","unstructured":"Lee, D., Oh, K.-J., & Choi, H.-J. (2017). The chatbot feels you - a counseling service using emotional response generation. In: IEEE International Conference on Big Data and Smart Computing"},{"key":"2495_CR26","unstructured":"Li, J., Li, D., Savarese, S., & Hoi, S. (2023). Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. In: International Conference on Machine Learning"},{"key":"2495_CR27","doi-asserted-by":"crossref","unstructured":"Li, K., Wang, Y., He, Y., Li, Y., Wang, Y., Liu, Y., Wang, Z., Xu, J., Chen, G., Luo, P., et al. (2024). Mvbench: A comprehensive multi-modal video understanding benchmark. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition","DOI":"10.1109\/CVPR52733.2024.02095"},{"key":"2495_CR28","unstructured":"Lian, Z., Sun, L., Xu, M., et al. (2023). Explainable multimodal emotion reasoning. arXiv preprint arXiv:2306.15401"},{"key":"2495_CR29","doi-asserted-by":"crossref","unstructured":"Lin, B., Zhu, B., Ye, Y., et al. (2023). Video-llava: Learning united visual representation by alignment before projection. arXiv preprint arXiv:2311.10122","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"2495_CR30","unstructured":"Liu, H., Li, C., Wu, Q., & Lee, Y. J. (2023). Visual instruction tuning. In: Conference on Neural Information Processing Systems"},{"key":"2495_CR31","unstructured":"Loshchilov, I., & Hutter, F. (2019). Decoupled weight decay regularization. In: International Conference on Learning Representations"},{"key":"2495_CR32","unstructured":"Lucas, B. D., & Kanade, T. (1981). An iterative image registration technique with an application to stereo vision. In: Intl. Joint Conf. on Artificial Intelligence"},{"key":"2495_CR33","unstructured":"Luo, R., Zhao, Z., Yang, M., Dong, J., et al. (2023). Valley: Video assistant with large language model enhanced ability. arXiv preprint arXiv:2306.07207"},{"key":"2495_CR34","doi-asserted-by":"crossref","unstructured":"Maaz, M., Rasheed, H., Khan, S., & Khan, F. S. (2024). Video-chatgpt: Towards detailed video understanding via large vision and language models. In: Annual Meeting of the Association for Computational Linguistics","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"2495_CR35","doi-asserted-by":"crossref","unstructured":"Mao, C., Teotia, R., Sundar, A., Menon, S., Yang, J., Wang, X., & Vondrick, C. (2023). Doubly right object recognition: A why prompt for visual rationales. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition","DOI":"10.1109\/CVPR52729.2023.00267"},{"key":"2495_CR36","unstructured":"Mazeika, M., Tang, E., Zou, A., Basart, S., Chan, J. S., Song, D., Forsyth, D., et al. (2022) How would the viewer feel? estimating wellbeing from video scenarios. In: Conference on Neural Information Processing Systems"},{"key":"2495_CR37","unstructured":"Mehrabian, A., & Russell, J. A. (1974). An approach to environmental psychology. In: The MIT Press"},{"key":"2495_CR38","doi-asserted-by":"crossref","unstructured":"Mittal, H., Agarwal, N., Lo, S.-Y., et al. (2024). Can\u2019t make an omelette without breaking some eggs: Plausible action anticipation using large video-language models. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition","DOI":"10.1109\/CVPR52733.2024.01758"},{"key":"2495_CR39","doi-asserted-by":"crossref","unstructured":"Pantic, M., Sebe, N., Cohn, J.F., & Huang, T. (2005). Affective multimodal human-computer interaction. In: ACM International Conference on Multimedia","DOI":"10.1145\/1101149.1101299"},{"key":"2495_CR40","doi-asserted-by":"crossref","unstructured":"Peng, K.-C., Sadovnik, A., Gallagher, A., & Chen, T. (2016). Where do emotions come from? predicting the emotion stimuli map. In: IEEE International Conference on Image Processing","DOI":"10.1109\/ICIP.2016.7532430"},{"key":"2495_CR41","doi-asserted-by":"crossref","unstructured":"Plutchik, R. (1980). A general psychoevolutionary theory of emotion. In: Theories of Emotion","DOI":"10.1016\/B978-0-12-558701-3.50007-7"},{"key":"2495_CR42","doi-asserted-by":"crossref","unstructured":"Pu, H., Sun, Y., Song, R., Chen, X., Jiang, H., Liu, Y. & Cao, Z. (2023). Going beyond closed sets: A multimodal perspective for video emotion analysis. In: Chinese Conference on Pattern Recognition and Computer Vision","DOI":"10.1007\/978-981-99-8537-1_19"},{"key":"2495_CR43","unstructured":"Radford, A., Kim, J. W., et al. (2021). Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning"},{"key":"2495_CR44","unstructured":"Sharir, G., Noy, A., & Zelnik-Manor, L. (2021). An image is worth 16x16 words, what is a video worth? arXiv preprint arXiv:2103.13915"},{"key":"2495_CR45","doi-asserted-by":"crossref","unstructured":"Srivastava, D., Singh, A. K., & Tapaswi, M. (2023). How you feelin\u2019? learning emotions and mental states in movie scenes. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition","DOI":"10.1109\/CVPR52729.2023.00248"},{"key":"2495_CR46","doi-asserted-by":"crossref","unstructured":"Tang, X., Qiu, J., et al. (2025). Adaptive keyframe sampling for long video understanding. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition","DOI":"10.1109\/CVPR52734.2025.02711"},{"key":"2495_CR47","unstructured":"Tong, Z., Song, Y., Wang, J., & Wang, L. (2022). Videomae: Masked autoencoders are data-efficient learners for self-supervised video pre-training. In: Conference on Neural Information Processing Systems"},{"key":"2495_CR48","unstructured":"Touvron, H., Lavril, T., Izacard, G., Martinet, X., et al. (2023). Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971"},{"key":"2495_CR49","unstructured":"Touvron, H., Martin, L., Stone, K., Albert, P., et al. (2023). Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288"},{"key":"2495_CR50","doi-asserted-by":"crossref","unstructured":"Tran, D., Wang, H., Torresani, L., Ray, J., LeCun, Y., & Paluri, M. (2018). A closer look at spatiotemporal convolutions for action recognition. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition","DOI":"10.1109\/CVPR.2018.00675"},{"key":"2495_CR51","doi-asserted-by":"crossref","unstructured":"Turaga, P., Veeraraghavan, A., & Chellappa, R. (2007). From videos to verbs: Mining videos for activities using a cascade of dynamical systems. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition","DOI":"10.1109\/CVPR.2007.383170"},{"key":"2495_CR52","doi-asserted-by":"crossref","unstructured":"Turaga, P., Veeraraghavan, A., & Chellappa, R. (2009). Unsupervised view and rate invariant clustering of video sequences. In: Comp. Vision and Image Understanding","DOI":"10.1016\/j.cviu.2008.08.009"},{"key":"2495_CR53","doi-asserted-by":"crossref","unstructured":"Wang, Z., Jiao, R., & Jiang, H. (2020). Emotion recognition using wt-svm in human-computer interaction. Journal of New Media","DOI":"10.32604\/jnm.2020.010674"},{"key":"2495_CR54","unstructured":"Wang, W., Lv, Q., Yu, W., Hong, W., et al. (2023). Cogvlm: Visual expert for pretrained language models. arXiv preprint arXiv:2311.03079"},{"key":"2495_CR55","doi-asserted-by":"crossref","unstructured":"Wang, J., Yang, X., Li, H., et al. (2022). Efficient video transformers with spatial-temporal token selection. In: European Conference on Computer Vision","DOI":"10.1007\/978-3-031-19833-5_5"},{"key":"2495_CR56","doi-asserted-by":"crossref","unstructured":"Wang, S., Zhao, Q., Do, M. Q., Agarwal, N., et al. (2024). Vamos: Versatile action models for video understanding. In: European Conference on Computer Vision","DOI":"10.1007\/978-3-031-73254-6_9"},{"key":"2495_CR57","doi-asserted-by":"crossref","unstructured":"Weng, Y., Han, M., He, H., et al. (2024). Longvlm: Efficient long video understanding via large language models. In: European Conference on Computer Vision","DOI":"10.1007\/978-3-031-73414-4_26"},{"key":"2495_CR58","doi-asserted-by":"crossref","unstructured":"Xie, H., Peng, C.-J., Tseng, Y.-W., Chen, H.-J., Hsu, C.-F., Shuai, H.-H., & Cheng, W.-H. (2024). Emovit: Revolutionizing emotion insights with visual instruction tuning. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition","DOI":"10.1109\/CVPR52733.2024.02511"},{"key":"2495_CR59","unstructured":"Xu, B., Fu, Y., Jiang, Y.-G., Li, B., & Sigal, L. (2016). Heterogeneous knowledge transfer in video emotion recognition, attribution and summarization. In: IEEE Transactions on Affective Computing"},{"key":"2495_CR60","doi-asserted-by":"crossref","unstructured":"Yang, J., Huang, Q., Ding, T., Lischinski, D., Cohen-Or, D., & Huang, H. (2023). Emoset: A large-scale visual emotion dataset with rich attributes. In: IEEE\/CVF International Conference on Computer Vision","DOI":"10.1109\/ICCV51070.2023.01864"},{"key":"2495_CR61","doi-asserted-by":"crossref","unstructured":"Yang, Y., Lee, K., Dariush, B., Cao, Y., & Lo, S.-Y. (2024). Follow the rules: Reasoning for video anomaly detection with large language models. In: European Conference on Computer Vision","DOI":"10.1007\/978-3-031-73004-7_18"},{"key":"2495_CR62","doi-asserted-by":"crossref","unstructured":"Yang, J., Li, J., Wang, X., Ding, Y., & Gao, X. (2021). Stimuli-aware visual emotion analysis. In: IEEE Transactions on Image Processing","DOI":"10.1109\/TIP.2021.3106813"},{"key":"2495_CR63","doi-asserted-by":"crossref","unstructured":"Yang, D., Yang, K., Li, M., Wang, S., Wang, S., & Zhang, L. (2024). Robust emotion recognition in context debiasing. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition","DOI":"10.1109\/CVPR52733.2024.01183"},{"key":"2495_CR64","doi-asserted-by":"crossref","unstructured":"Ye, Q., Xu, H., Ye, J., et al. (2024). mplug-owl2: Revolutionizing multi-modal large language model with modality collaboration. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition","DOI":"10.1109\/CVPR52733.2024.01239"},{"key":"2495_CR65","doi-asserted-by":"crossref","unstructured":"Zhang, H., Li, X., & Bing, L. (2023). Video-llama: An instruction-tuned audio-visual language model for video understanding. In: Conference on Empirical Methods in Natural Language Processing","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"2495_CR66","doi-asserted-by":"crossref","unstructured":"Zhang, C., Lin, K., Yang, Z., Wang, J., Li, L., Lin, C.-C., Liu, Z., & Wang, L. (2024). Mm-narrator: Narrating long-form videos with multimodal in-context learning. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition","DOI":"10.1109\/CVPR52733.2024.01295"},{"key":"2495_CR67","unstructured":"Zheng, L., Chiang, W.-L., Sheng, Y., Zhuang, S., Wu, Z., Zhuang, Y., Lin, Z., Li, Z., Li, D., Xing, E., et al. (2023). Judging llm-as-a-judge with mt-bench and chatbot arena. In: Conference on Neural Information Processing Systems"},{"key":"2495_CR68","unstructured":"Zhu, D., Chen, J., Shen, X., Li, X., & Elhoseiny, M. (2024). Minigpt-4: Enhancing vision-language understanding with advanced large language models. In: International Conference on Learning Representations"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-025-02495-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-025-02495-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-025-02495-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T08:04:24Z","timestamp":1757405064000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-025-02495-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,14]]},"references-count":68,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2025,9]]}},"alternative-id":["2495"],"URL":"https:\/\/doi.org\/10.1007\/s11263-025-02495-3","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,14]]},"assertion":[{"value":"30 August 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 May 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 June 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}