{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,15]],"date-time":"2025-10-15T10:38:19Z","timestamp":1760524699801,"version":"3.40.3"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031781827"},{"type":"electronic","value":"9783031781834"}],"license":[{"start":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T00:00:00Z","timestamp":1733270400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T00:00:00Z","timestamp":1733270400000},"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":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-78183-4_29","type":"book-chapter","created":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T12:01:23Z","timestamp":1733227283000},"page":"455-473","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Temporal Insight Enhancement: Mitigating Temporal Hallucination in Video Understanding by Multimodal Large Language Models"],"prefix":"10.1007","author":[{"given":"Li","family":"Sun","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liuan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takayuki","family":"Okatani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,4]]},"reference":[{"key":"29_CR1","doi-asserted-by":"publisher","unstructured":"Amaro, I., Barra, P., Della\u00a0Greca, A., Francese, R., Tucci, C.: Believe in artificial intelligence? a user study on the chatgpt\u2019s fake information impact. IEEE Transactions on Computational Social Systems pp. 1\u201310 (2023). https:\/\/doi.org\/10.1109\/TCSS.2023.3291539","DOI":"10.1109\/TCSS.2023.3291539"},{"key":"29_CR2","doi-asserted-by":"crossref","unstructured":"Amaro, I., Della\u00a0Greca, A., Francese, R., Tortora, G., Tucci, C.: Ai unreliable answers: A case study on chatgpt. In: International Conference on Human-Computer Interaction. pp. 23\u201340. Springer (2023)","DOI":"10.1007\/978-3-031-35894-4_2"},{"key":"29_CR3","doi-asserted-by":"crossref","unstructured":"Bao, W., Yu, Q., Kong, Y.: Uncertainty-based traffic accident anticipation with spatio-temporal relational learning. In: ACM Multimedia Conference (May 2020)","DOI":"10.1145\/3394171.3413827"},{"key":"29_CR4","unstructured":"Brown, T., Mann, B., Ryder, N., et\u00a0al.: Language models are few-shot learners. In: Annual Conference on Neural Information Processing Systems, NeurIPS. pp. 1877\u20131901 (2020)"},{"key":"29_CR5","unstructured":"Chen, J., Zhu, D., Shen, X., et\u00a0al.: Minigpt-v2: Large language model as a unified interface for vision-language multi-task learning. arXiv preprint arXiv:2310.09478 (2023)"},{"key":"29_CR6","unstructured":"Chern, I., Chern, S., Chen, S., et\u00a0al.: Factool: Factuality detection in generative ai\u2013a tool augmented framework for multi-task and multi-domain scenarios. arXiv preprint arXiv:2307.13528 (2023)"},{"key":"29_CR7","unstructured":"Chiang, W.L., Li, Z., Lin, Z., et\u00a0al.: Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality. See https:\/\/vicuna. lmsys. org (accessed 14 April 2023) (2023), accessed 14 April 2023"},{"key":"29_CR8","doi-asserted-by":"crossref","unstructured":"Dhuliawala, S., Komeili, M., Xu, J., et\u00a0al.: Chain-of-verification reduces hallucination in large language models. arXiv preprint arXiv:2309.11495 (2023)","DOI":"10.18653\/v1\/2024.findings-acl.212"},{"key":"29_CR9","doi-asserted-by":"crossref","unstructured":"Fabian Caba\u00a0Heilbron, Victor\u00a0Escorcia, B.G., Niebles, J.C.: Activitynet: A large-scale video benchmark for human activity understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 961\u2013970 (2015)","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"29_CR10","doi-asserted-by":"crossref","unstructured":"Gao, J., Sun, C., Yang, Z., et\u00a0al.: Tall: Temporal activity localization via language query. In: Proceedings of the IEEE international conference on computer vision, ICCV. pp. 5267\u20135275 (2017)","DOI":"10.1109\/ICCV.2017.563"},{"key":"29_CR11","doi-asserted-by":"crossref","unstructured":"Huang, Q., Dong, X., Zhang, P., Wang, B., He, C., Wang, J., Lin, D., Zhang, W., Yu, N.: Opera: Alleviating hallucination in multi-modal large language models via over-trust penalty and retrospection-allocation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 13418\u201313427 (2024)","DOI":"10.1109\/CVPR52733.2024.01274"},{"key":"29_CR12","doi-asserted-by":"crossref","unstructured":"Leng, S., Zhang, H., Chen, G., Li, X., Lu, S., Miao, C., Bing, L.: Mitigating object hallucinations in large vision-language models through visual contrastive decoding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 13872\u201313882 (2024)","DOI":"10.1109\/CVPR52733.2024.01316"},{"key":"29_CR13","unstructured":"Li, J., Li, D., Savarese, S., et\u00a0al.: BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. In: Proceedings of the International Conference on Machine Learning. pp. 19730\u201319742 (2023)"},{"key":"29_CR14","unstructured":"Li, J., Li, D., Xiong, C., et\u00a0al.: BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In: Proceedings of the International Conference on Machine Learning. pp. 12888\u201312900. PMLR (2022)"},{"key":"29_CR15","doi-asserted-by":"crossref","unstructured":"Li, Y., Du, Y., Zhou, K., et\u00a0al.: Evaluating object hallucination in large vision-language models. arXiv preprint arXiv:2305.10355 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"29_CR16","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Li, Y., et\u00a0al.: Improved baselines with visual instruction tuning. arXiv preprint arXiv:2310.03744 (2023)","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"29_CR17","unstructured":"Liu, H., Li, C., Wu, Q., et\u00a0al.: Visual instruction tuning. arXiv preprint arXiv:2304.08485 (2023)"},{"key":"29_CR18","unstructured":"Ouyang, L., Wu, J., Jiang, X., et\u00a0al.: Training language models to follow instructions with human feedback. In: Annual Conference on Neural Information Processing Systems, NeurIPS. pp. 27730\u201327744 (2022)"},{"key":"29_CR19","unstructured":"Radford, A., Kim, J.W., Hallacy, C., et\u00a0al.: Learning transferable visual models from natural language supervision. In: Proceedings of the International Conference on Machine Learning. pp. 8748\u20138763 (2021)"},{"key":"29_CR20","doi-asserted-by":"crossref","unstructured":"Ram, O., Levine, Y., Dalmedigos, I., et\u00a0al.: In-context retrieval-augmented language models. arXiv preprint arXiv:2302.00083 (2023)","DOI":"10.1162\/tacl_a_00605"},{"key":"29_CR21","unstructured":"Rawte, V., Sheth, A., Das, A.: A survey of hallucination in large foundation models. arXiv preprint arXiv:2309.05922 (2023)"},{"key":"29_CR22","doi-asserted-by":"publisher","unstructured":"Shuster, K., Poff, S., Chen, M., Kiela, D., Weston, J.: Retrieval augmentation reduces hallucination in conversation. In: Findings of the Association for Computational Linguistics: EMNLP. pp. 3784\u20133803 (2021). https:\/\/doi.org\/10.18653\/V1\/2021.FINDINGS-EMNLP.320","DOI":"10.18653\/V1\/2021.FINDINGS-EMNLP.320"},{"key":"29_CR23","unstructured":"Touvron, H., Lavril, T., Izacard, G., et\u00a0al.: Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"29_CR24","unstructured":"Touvron, H., Martin, L., Stone, K., et\u00a0al.: Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)"},{"key":"29_CR25","doi-asserted-by":"crossref","unstructured":"Yang, Z., Ping, W., Liu, Z., et\u00a0al.: Re-vilm: Retrieval-augmented visual language model for zero and few-shot image captioning. arXiv preprint arXiv:2302.04858 (2023)","DOI":"10.18653\/v1\/2023.findings-emnlp.793"},{"key":"29_CR26","unstructured":"Yin, S., Fu, C., Zhao, S., et\u00a0al.: A survey on multimodal large language models. arXiv preprint arXiv:2306.13549 (2023)"},{"key":"29_CR27","unstructured":"Yin, S., Fu, C., Zhao, S., et\u00a0al.: Woodpecker: Hallucination correction for multimodal large language models. arXiv preprint arXiv:2310.16045 (2023)"},{"key":"29_CR28","doi-asserted-by":"crossref","unstructured":"Zhang, H., Li, X., Bing, L.: Video-llama: An instruction-tuned audio-visual language model for video understanding. arXiv preprint arXiv:2306.02858 (2023)","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"29_CR29","unstructured":"Zhang, Y., Li, Y., Cui, L., et\u00a0al.: Siren\u2019s song in the ai ocean: A survey on hallucination in large language models. arXiv preprint arXiv:2309.01219 (2023)"},{"key":"29_CR30","doi-asserted-by":"crossref","unstructured":"Zhao, R., Li, X., Joty, S., et\u00a0al.: Verify-and-edit: A knowledge-enhanced chain-of-thought framework. arXiv preprint arXiv:2305.03268 (2023)","DOI":"10.18653\/v1\/2023.acl-long.320"},{"key":"29_CR31","unstructured":"Zhou, Y., Ren, J., Li, F., et\u00a0al.: Test-time distribution normalization for contrastively learned visual-language models. In: Annual Conference on Neural Information Processing Systems, NeurIPS (2023)"},{"key":"29_CR32","unstructured":"Zhu, D., Chen, J., Shen, X., et\u00a0al.: Minigpt-4: Enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592 (2023)"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78183-4_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T12:14:17Z","timestamp":1733228057000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78183-4_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,4]]},"ISBN":["9783031781827","9783031781834"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78183-4_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,12,4]]},"assertion":[{"value":"4 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kolkata","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}