{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T20:06:53Z","timestamp":1765310813921,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":55,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022ZD0160501"],"award-info":[{"award-number":["2022ZD0160501"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Foundation of Fujian Province of China","award":["2024J011001"],"award-info":[{"award-number":["2024J011001"]}]},{"name":"the Public Technology Service Platform Project of Xiamen","award":["3502Z20231043"],"award-info":[{"award-number":["3502Z20231043"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755100","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:30:51Z","timestamp":1761377451000},"page":"3507-3516","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["EditEval: Towards Comprehensive and Automatic Evaluation for Text-guided Video Editing"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3630-7499","authenticated-orcid":false,"given":"Bingshuai","family":"Liu","sequence":"first","affiliation":[{"name":"School of Informatics, Xiamen University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8438-554X","authenticated-orcid":false,"given":"Ante","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Informatics, Xiamen University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8016-3069","authenticated-orcid":false,"given":"Zijun","family":"Min","sequence":"additional","affiliation":[{"name":"School of Informatics, Xiamen University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6733-5879","authenticated-orcid":false,"given":"Chenyang","family":"Lyu","sequence":"additional","affiliation":[{"name":"Alibaba International Digital Commerce, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9062-6183","authenticated-orcid":false,"given":"Longyue","family":"Wang","sequence":"additional","affiliation":[{"name":"Alibaba International Digital Commerce, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7497-6467","authenticated-orcid":false,"given":"Zhihao","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Informatics, Xiamen University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4726-7621","authenticated-orcid":false,"given":"Xu","family":"Han","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1374-5979","authenticated-orcid":false,"given":"Peng","family":"Li","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5606-7122","authenticated-orcid":false,"given":"Jinsong","family":"Su","sequence":"additional","affiliation":[{"name":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, China and Shanghai Artificial Intelligence Laboratory, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Qwen-vl: A frontier large vision-language model with versatile abilities. arXiv preprint arXiv:2308.12966","author":"Bai Jinze","year":"2023","unstructured":"Jinze Bai, Shuai Bai, Shusheng Yang, Shijie Wang, Sinan Tan, Peng Wang, Junyang Lin, Chang Zhou, and Jingren Zhou. 2023. Qwen-vl: A frontier large vision-language model with versatile abilities. arXiv preprint arXiv:2308.12966 (2023)."},{"key":"e_1_3_2_1_2_1","first-page":"961","article-title":"Activitynet: A large-scale video benchmark for human activity understanding","author":"Heilbron Fabian Caba","year":"2015","unstructured":"Fabian Caba Heilbron, Victor Escorcia, Bernard Ghanem, and Juan Carlos Niebles. 2015. Activitynet: A large-scale video benchmark for human activity understanding. In CVPR. 961-970.","journal-title":"CVPR."},{"key":"e_1_3_2_1_3_1","volume-title":"Federico Perazzi, and Jordi Pont-Tuset.","author":"Caelles Sergi","year":"2018","unstructured":"Sergi Caelles, Alberto Montes, Kevis-Kokitsi Maninis, Yuhua Chen, Luc Van Gool, Federico Perazzi, and Jordi Pont-Tuset. 2018. The 2018 davis challenge on video object segmentation. arXiv preprint arXiv:1803.00557 (2018)."},{"key":"e_1_3_2_1_4_1","volume-title":"The 2019 davis challenge on vos: Unsupervised multi-object segmentation. arXiv preprint arXiv:1905.00737","author":"Caelles Sergi","year":"2019","unstructured":"Sergi Caelles, Jordi Pont-Tuset, Federico Perazzi, Alberto Montes, Kevis-Kokitsi Maninis, and Luc Van Gool. 2019. The 2019 davis challenge on vos: Unsupervised multi-object segmentation. arXiv preprint arXiv:1905.00737 (2019)."},{"key":"e_1_3_2_1_5_1","first-page":"23206","article-title":"Pix2video: Video editing using image diffusion","author":"Ceylan Duygu","year":"2023","unstructured":"Duygu Ceylan, Chun-Hao P Huang, and Niloy J Mitra. 2023. Pix2video: Video editing using image diffusion. In ICCV. 23206-23217.","journal-title":"ICCV."},{"key":"e_1_3_2_1_6_1","volume-title":"Chateval: Towards better llm-based evaluators through multi-agent debate. arXiv preprint arXiv:2308.07201","author":"Chan Chi-Min","year":"2023","unstructured":"Chi-Min Chan, Weize Chen, Yusheng Su, Jianxuan Yu, Wei Xue, Shanghang Zhang, Jie Fu, and Zhiyuan Liu. 2023. Chateval: Towards better llm-based evaluators through multi-agent debate. arXiv preprint arXiv:2308.07201 (2023)."},{"key":"e_1_3_2_1_7_1","unstructured":"Zesen Cheng Sicong Leng Hang Zhang Yifei Xin Xin Li Guanzheng Chen Yongxin Zhu Wenqi Zhang Ziyang Luo Deli Zhao et al. 2024. VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs. arXiv preprint arXiv:2406.07476 (2024)."},{"key":"e_1_3_2_1_8_1","volume-title":"Modality-aware integration with large language models for knowledge-based visual question answering. arXiv preprint arXiv:2402.12728","author":"Dong Junnan","year":"2024","unstructured":"Junnan Dong, Qinggang Zhang, Huachi Zhou, Daochen Zha, Pai Zheng, and Xiao Huang. 2024. Modality-aware integration with large language models for knowledge-based visual question answering. arXiv preprint arXiv:2402.12728 (2024)."},{"key":"e_1_3_2_1_9_1","volume-title":"Gptscore: Evaluate as you desire. arXiv preprint arXiv:2302.04166","author":"Fu Jinlan","year":"2023","unstructured":"Jinlan Fu, See-Kiong Ng, Zhengbao Jiang, and Pengfei Liu. 2023. Gptscore: Evaluate as you desire. arXiv preprint arXiv:2302.04166 (2023)."},{"key":"e_1_3_2_1_10_1","volume-title":"Tokenflow: Consistent diffusion features for consistent video editing. arXiv preprint arXiv:2307.10373","author":"Geyer Michal","year":"2023","unstructured":"Michal Geyer, Omer Bar-Tal, Shai Bagon, and Tali Dekel. 2023. Tokenflow: Consistent diffusion features for consistent video editing. arXiv preprint arXiv:2307.10373 (2023)."},{"key":"e_1_3_2_1_11_1","volume-title":"Ronan Le Bras, and Yejin Choi","author":"Hessel Jack","year":"2021","unstructured":"Jack Hessel, Ari Holtzman, Maxwell Forbes, Ronan Le Bras, and Yejin Choi. 2021. Clipscore: A reference-free evaluation metric for image captioning. arXiv preprint arXiv:2104.08718 (2021)."},{"key":"e_1_3_2_1_12_1","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. NeurIPS, Vol. 33 (2020), 6840-6851.","journal-title":"NeurIPS"},{"key":"e_1_3_2_1_13_1","volume-title":"Diffusion model-based image editing: A survey. arXiv preprint arXiv:2402.17525","author":"Huang Yi","year":"2024","unstructured":"Yi Huang, Jiancheng Huang, Yifan Liu, Mingfu Yan, Jiaxi Lv, Jianzhuang Liu, Wei Xiong, He Zhang, Shifeng Chen, and Liangliang Cao. 2024. Diffusion model-based image editing: A survey. arXiv preprint arXiv:2402.17525 (2024)."},{"key":"e_1_3_2_1_14_1","volume-title":"Can Multimodal LLMs do Visual Temporal Understanding and Reasoning? The answer is No! arXiv preprint arXiv:2501.10674","author":"Imam Mohamed Fazli","year":"2025","unstructured":"Mohamed Fazli Imam, Chenyang Lyu, and Alham Fikri Aji. 2025. Can Multimodal LLMs do Visual Temporal Understanding and Reasoning? The answer is No! arXiv preprint arXiv:2501.10674 (2025)."},{"key":"e_1_3_2_1_15_1","first-page":"6507","article-title":"Rave: Randomized noise shuffling for fast and consistent video editing with diffusion models","author":"Kara Ozgur","year":"2024","unstructured":"Ozgur Kara, Bariscan Kurtkaya, Hidir Yesiltepe, James M Rehg, and Pinar Yanardag. 2024. Rave: Randomized noise shuffling for fast and consistent video editing with diffusion models. In CVPR. 6507-6516.","journal-title":"CVPR."},{"key":"e_1_3_2_1_16_1","first-page":"15954","article-title":"Text2video-zero: Text-to-image diffusion models are zero-shot video generators","author":"Khachatryan Levon","year":"2023","unstructured":"Levon Khachatryan, Andranik Movsisyan, Vahram Tadevosyan, Roberto Henschel, Zhangyang Wang, Shant Navasardyan, and Humphrey Shi. 2023. Text2video-zero: Text-to-image diffusion models are zero-shot video generators. In ICCV. 15954-15964.","journal-title":"ICCV."},{"volume-title":"Content analysis: An introduction to its methodology","author":"Krippendorff Klaus","key":"e_1_3_2_1_17_1","unstructured":"Klaus Krippendorff. 2018. Content analysis: An introduction to its methodology. Sage publications."},{"key":"e_1_3_2_1_18_1","volume-title":"Avg-llava: A large multimodal model with adaptive visual granularity. arXiv preprint arXiv:2410.02745","author":"Lan Zhibin","year":"2024","unstructured":"Zhibin Lan, Liqiang Niu, Fandong Meng, Wenbo Li, Jie Zhou, and Jinsong Su. 2024. Avg-llava: A large multimodal model with adaptive visual granularity. arXiv preprint arXiv:2410.02745 (2024)."},{"key":"e_1_3_2_1_19_1","volume-title":"Llave: Large language and vision embedding models with hardness-weighted contrastive learning. arXiv preprint arXiv:2503.04812","author":"Lan Zhibin","year":"2025","unstructured":"Zhibin Lan, Liqiang Niu, Fandong Meng, Jie Zhou, and Jinsong Su. 2025. Llave: Large language and vision embedding models with hardness-weighted contrastive learning. arXiv preprint arXiv:2503.04812 (2025)."},{"key":"e_1_3_2_1_20_1","volume-title":"LLaVA-OneVision: Easy Visual Task Transfer. arXiv preprint arXiv:2408.03326","author":"Li Bo","year":"2024","unstructured":"Bo Li, Yuanhan Zhang, Dong Guo, Renrui Zhang, Feng Li, Hao Zhang, Kaichen Zhang, Yanwei Li, Ziwei Liu, and Chunyuan Li. 2024c. LLaVA-OneVision: Easy Visual Task Transfer. arXiv preprint arXiv:2408.03326 (2024)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.262"},{"key":"e_1_3_2_1_22_1","first-page":"7486","article-title":"VidToMe","author":"Li Xirui","year":"2024","unstructured":"Xirui Li, Chao Ma, Xiaokang Yang, and Ming-Hsuan Yang. 2024b. VidToMe: Video Token Merging for Zero-Shot Video Editing. In CVPR. 7486-7495.","journal-title":"Video Token Merging for Zero-Shot Video Editing. In CVPR."},{"key":"e_1_3_2_1_23_1","first-page":"26689","article-title":"Vila: On pre-training for visual language models","author":"Lin Ji","year":"2024","unstructured":"Ji Lin, Hongxu Yin, Wei Ping, Pavlo Molchanov, Mohammad Shoeybi, and Song Han. 2024. Vila: On pre-training for visual language models. In CVPR. 26689-26699.","journal-title":"CVPR."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"crossref","unstructured":"Yujie Lin Ante Wang Moye Chen Jingyao Liu Hao Liu Jinsong Su and Xinyan Xiao. 2025. Investigating Inference-time Scaling for Chain of Multi-modal Thought: A Preliminary Study. arXiv:2502.11514 [cs.CL] https:\/\/arxiv.org\/abs\/2502.11514","DOI":"10.18653\/v1\/2025.findings-acl.808"},{"key":"e_1_3_2_1_25_1","volume-title":"Retrieval-augmented multi-modal chain-of-thoughts reasoning for large language models. arXiv preprint arXiv:2312.01714","author":"Liu Bingshuai","year":"2023","unstructured":"Bingshuai Liu, Chenyang Lyu, Zijun Min, Zhanyu Wang, Jinsong Su, and Longyue Wang. 2023b. Retrieval-augmented multi-modal chain-of-thoughts reasoning for large language models. arXiv preprint arXiv:2312.01714 (2023)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.3233\/FAIA240581"},{"key":"e_1_3_2_1_27_1","volume-title":"Kangaroo: A Powerful Video-Language Model Supporting Long-context Video Input. arXiv preprint arXiv:2408.15542","author":"Liu Jiajun","year":"2024","unstructured":"Jiajun Liu, Yibing Wang, Hanghang Ma, Xiaoping Wu, Xiaoqi Ma, Xiaoming Wei, Jianbin Jiao, Enhua Wu, and Jie Hu. 2024b. Kangaroo: A Powerful Video-Language Model Supporting Long-context Video Input. arXiv preprint arXiv:2408.15542 (2024)."},{"key":"e_1_3_2_1_28_1","volume-title":"Levine (Eds.)","volume":"36","author":"Liu Yuanxin","year":"2023","unstructured":"Yuanxin Liu, Lei Li, Shuhuai Ren, Rundong Gao, Shicheng Li, Sishuo Chen, Xu Sun, and Lu Hou. 2023a. FETV: A Benchmark for Fine-Grained Evaluation of Open-Domain Text-to-Video Generation. In NeurIPS, A. Oh, T. Naumann, A. Globerson, K. Saenko, M. Hardt, and S. Levine (Eds.), Vol. 36. 62352-62387. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2023\/file\/c481049f7410f38e788f67c171c64ad5-Paper-Datasets_and_Benchmarks.pdf"},{"key":"e_1_3_2_1_29_1","volume-title":"Xin Eric Wang, and William Yang Wang","author":"Lu Yujie","year":"2023","unstructured":"Yujie Lu, Xianjun Yang, Xiujun Li, Xin Eric Wang, and William Yang Wang. 2023. LLMScore: Unveiling the Power of Large Language Models in Text-to-Image Synthesis Evaluation. In NeurIPS, A. Oh, T. Naumann, A. Globerson, K. Saenko, M. Hardt, and S. Levine (Eds.), Vol. 36. 23075-23093. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2023\/file\/47f30d67bce3e9824928267e9355420f-Paper-Conference.pdf"},{"key":"e_1_3_2_1_30_1","first-page":"11616","article-title":"Semantic Enrichment for Video Question Answering with Gated Graph Neural Networks. In ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"Lyu Chenyang","year":"2024","unstructured":"Chenyang Lyu, Wenxi Li, Tianbo Ji, Yi Yu, and Longyue Wang. 2024. Semantic Enrichment for Video Question Answering with Gated Graph Neural Networks. In ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 11616-11620.","journal-title":"IEEE"},{"key":"e_1_3_2_1_31_1","volume-title":"Yossi Matias, Yael Pritch, Yaniv Leviathan, and Yedid Hoshen.","author":"Molad Eyal","year":"2023","unstructured":"Eyal Molad, Eliahu Horwitz, Dani Valevski, Alex Rav Acha, Yossi Matias, Yael Pritch, Yaniv Leviathan, and Yedid Hoshen. 2023. Dreamix: Video diffusion models are general video editors. arXiv preprint arXiv:2302.01329 (2023)."},{"key":"e_1_3_2_1_32_1","unstructured":"OpenAI. 2024. GPT-4o System Card."},{"key":"e_1_3_2_1_33_1","first-page":"1","article-title":"Zero-shot image-to-image translation","author":"Parmar Gaurav","year":"2023","unstructured":"Gaurav Parmar, Krishna Kumar Singh, Richard Zhang, Yijun Li, Jingwan Lu, and Jun-Yan Zhu. 2023. Zero-shot image-to-image translation. In SIGGRAPH. 1-11.","journal-title":"SIGGRAPH."},{"key":"e_1_3_2_1_34_1","volume-title":"The 2017 davis challenge on video object segmentation. arXiv preprint arXiv:1704.00675","author":"Pont-Tuset Jordi","year":"2017","unstructured":"Jordi Pont-Tuset, Federico Perazzi, Sergi Caelles, Pablo Arbel\u00e1ez, Alex Sorkine-Hornung, and Luc Van Gool. 2017. The 2017 davis challenge on video object segmentation. arXiv preprint arXiv:1704.00675 (2017)."},{"key":"e_1_3_2_1_35_1","first-page":"15932","article-title":"Fatezero: Fusing attentions for zero-shot text-based video editing","author":"Qi Chenyang","year":"2023","unstructured":"Chenyang Qi, Xiaodong Cun, Yong Zhang, Chenyang Lei, Xintao Wang, Ying Shan, and Qifeng Chen. 2023. Fatezero: Fusing attentions for zero-shot text-based video editing. In ICCV. 15932-15942.","journal-title":"ICCV."},{"key":"e_1_3_2_1_36_1","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al., 2021. Learning transferable visual models from natural language supervision. In ICML. 8748-8763.","journal-title":"ICML."},{"key":"e_1_3_2_1_37_1","volume-title":"Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125","author":"Ramesh Aditya","year":"2022","unstructured":"Aditya Ramesh, Prafulla Dhariwal, Alex Nichol, Casey Chu, and Mark Chen. 2022. Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125, Vol. 1, 2 (2022), 3."},{"key":"e_1_3_2_1_38_1","first-page":"14313","article-title":"Timechat: A time-sensitive multimodal large language model for long video understanding","author":"Ren Shuhuai","year":"2024","unstructured":"Shuhuai Ren, Linli Yao, Shicheng Li, Xu Sun, and Lu Hou. 2024. Timechat: A time-sensitive multimodal large language model for long video understanding. In CVPR. 14313-14323.","journal-title":"CVPR."},{"key":"e_1_3_2_1_39_1","first-page":"10684","article-title":"High-resolution image synthesis with latent diffusion models","author":"Rombach Robin","year":"2022","unstructured":"Robin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser, and Bj\u00f6rn Ommer. 2022. High-resolution image synthesis with latent diffusion models. In CVPR. 10684-10695.","journal-title":"CVPR."},{"key":"e_1_3_2_1_40_1","first-page":"11479","article-title":". CVQA: Culturally-diverse Multilingual Visual Question Answering Benchmark","volume":"37","author":"Romero David","year":"2025","unstructured":"David Romero, Chenyang Lyu, Haryo Wibowo, Santiago G\u00f3ngora, Aishik Mandal, Sukannya Purkayastha, Jesus-German Ortiz-Barajas, Emilio Cueva, Jinheon Baek, Soyeong Jeong, et al., 2025. CVQA: Culturally-diverse Multilingual Visual Question Answering Benchmark. Advances in Neural Information Processing Systems, Vol. 37 (2025), 11479-11505.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_41_1","volume-title":"Oh (Eds.)","volume":"35","author":"Schuhmann Christoph","year":"2022","unstructured":"Christoph Schuhmann, Romain Beaumont, Richard Vencu, Cade Gordon, Ross Wightman, Mehdi Cherti, Theo Coombes, Aarush Katta, Clayton Mullis, Mitchell Wortsman, Patrick Schramowski, Srivatsa Kundurthy, Katherine Crowson, Ludwig Schmidt, Robert Kaczmarczyk, and Jenia Jitsev. 2022. LAION-5B: An open large-scale dataset for training next generation image-text models. In NeurIPS, S. Koyejo, S. Mohamed, A. Agarwal, D. Belgrave, K. Cho, and A. Oh (Eds.), Vol. 35. 25278-25294. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2022\/file\/a1859debfb3b59d094f3504d5ebb6c25-Paper-Datasets_and_Benchmarks.pdf"},{"key":"e_1_3_2_1_42_1","volume-title":"E-Bench: Subjective-Aligned Benchmark Suite for Text-Driven Video Editing Quality Assessment. arXiv preprint arXiv:2408.11481","author":"Sun Shangkun","year":"2024","unstructured":"Shangkun Sun, Xiaoyu Liang, Songlin Fan, Wenxu Gao, and Wei Gao. 2024. E-Bench: Subjective-Aligned Benchmark Suite for Text-Driven Video Editing Quality Assessment. arXiv preprint arXiv:2408.11481 (2024)."},{"key":"e_1_3_2_1_43_1","volume-title":"Ryan Burnell, Libin Bai, Anmol Gulati, Garrett Tanzer, Damien Vincent, Zhufeng Pan, Shibo Wang, et al.","author":"Team Gemini","year":"2024","unstructured":"Gemini Team, Petko Georgiev, Ving Ian Lei, Ryan Burnell, Libin Bai, Anmol Gulati, Garrett Tanzer, Damien Vincent, Zhufeng Pan, Shibo Wang, et al., 2024. Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context. arXiv preprint arXiv:2403.05530 (2024)."},{"key":"e_1_3_2_1_44_1","first-page":"9568","article-title":"Eyes wide shut? exploring the visual shortcomings of multimodal llms","author":"Tong Shengbang","year":"2024","unstructured":"Shengbang Tong, Zhuang Liu, Yuexiang Zhai, Yi Ma, Yann LeCun, and Saining Xie. 2024. Eyes wide shut? exploring the visual shortcomings of multimodal llms. In CVPR. 9568-9578.","journal-title":"CVPR."},{"key":"e_1_3_2_1_45_1","first-page":"1921","article-title":"Plug-and-play diffusion features for text-driven image-to-image translation","author":"Tumanyan Narek","year":"2023","unstructured":"Narek Tumanyan, Michal Geyer, Shai Bagon, and Tali Dekel. 2023. Plug-and-play diffusion features for text-driven image-to-image translation. In CVPR. 1921-1930.","journal-title":"CVPR."},{"key":"e_1_3_2_1_46_1","volume-title":"Zero-shot video editing using off-the-shelf image diffusion models. arXiv preprint arXiv:2303.17599","author":"Wang Wen","year":"2023","unstructured":"Wen Wang, Yan Jiang, Kangyang Xie, Zide Liu, Hao Chen, Yue Cao, Xinlong Wang, and Chunhua Shen. 2023. Zero-shot video editing using off-the-shelf image diffusion models. arXiv preprint arXiv:2303.17599 (2023)."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681464"},{"key":"e_1_3_2_1_48_1","first-page":"7623","article-title":"Tune-a-video: One-shot tuning of image diffusion models for text-to-video generation","author":"Wu Jay Zhangjie","year":"2023","unstructured":"Jay Zhangjie Wu, Yixiao Ge, Xintao Wang, Stan Weixian Lei, Yuchao Gu, Yufei Shi, Wynne Hsu, Ying Shan, Xiaohu Qie, and Mike Zheng Shou. 2023a. Tune-a-video: One-shot tuning of image diffusion models for text-to-video generation. In ICCV. 7623-7633.","journal-title":"ICCV."},{"key":"e_1_3_2_1_49_1","unstructured":"Jay Zhangjie Wu Xiuyu Li Difei Gao Zhen Dong Jinbin Bai Aishani Singh Xiaoyu Xiang Youzeng Li Zuwei Huang Yuanxi Sun et al. 2023b. Cvpr 2023 text guided video editing competition. arXiv preprint arXiv:2310.16003 (2023)."},{"key":"e_1_3_2_1_50_1","first-page":"9777","article-title":"Next-qa: Next phase of question-answering to explaining temporal actions","author":"Xiao Junbin","year":"2021","unstructured":"Junbin Xiao, Xindi Shang, Angela Yao, and Tat-Seng Chua. 2021. Next-qa: Next phase of question-answering to explaining temporal actions. In CVPR. 9777-9786.","journal-title":"CVPR."},{"key":"e_1_3_2_1_51_1","first-page":"1","article-title":"Rerender a video: Zero-shot text-guided video-to-video translation","author":"Yang Shuai","year":"2023","unstructured":"Shuai Yang, Yifan Zhou, Ziwei Liu, and Chen Change Loy. 2023. Rerender a video: Zero-shot text-guided video-to-video translation. In SIGGRAPH Asia. 1-11.","journal-title":"SIGGRAPH Asia."},{"key":"e_1_3_2_1_52_1","volume-title":"Video-llama: An instruction-tuned audio-visual language model for video understanding. arXiv preprint arXiv:2306.02858","author":"Zhang Hang","year":"2023","unstructured":"Hang Zhang, Xin Li, and Lidong Bing. 2023a. Video-llama: An instruction-tuned audio-visual language model for video understanding. arXiv preprint arXiv:2306.02858 (2023)."},{"key":"e_1_3_2_1_53_1","first-page":"3836","article-title":"Adding conditional control to text-to-image diffusion models","author":"Zhang Lvmin","year":"2023","unstructured":"Lvmin Zhang, Anyi Rao, and Maneesh Agrawala. 2023b. Adding conditional control to text-to-image diffusion models. In ICCV. 3836-3847.","journal-title":"ICCV."},{"key":"e_1_3_2_1_54_1","volume-title":"Yong jae Lee, Liangke Gui, Di Fu, Jiashi Feng, Ziwei Liu, and Chunyuan Li.","author":"Zhang Yuanhan","year":"2024","unstructured":"Yuanhan Zhang, Bo Li, haotian Liu, Yong jae Lee, Liangke Gui, Di Fu, Jiashi Feng, Ziwei Liu, and Chunyuan Li. 2024. LLaVA-NeXT: A Strong Zero-shot Video Understanding Model. https:\/\/llava-vl.github.io\/blog\/2024-04-30-llava-next-video\/"},{"key":"e_1_3_2_1_55_1","volume-title":"Corso","author":"Zhou Luowei","year":"2017","unstructured":"Luowei Zhou and Jason J. Corso. 2017. YouCookII Dataset. https:\/\/api.semanticscholar.org\/CorpusID:19774151"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755100","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T20:03:29Z","timestamp":1765310609000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755100"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":55,"alternative-id":["10.1145\/3746027.3755100","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755100","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}