{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T14:51:49Z","timestamp":1784904709487,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":75,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3680686","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:27Z","timestamp":1729925967000},"page":"8498-8507","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["MoS<sup>2<\/sup>: Mixture of Scale and Shift Experts for Text-Only Video Captioning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8062-9455","authenticated-orcid":false,"given":"Heng","family":"Jia","sequence":"first","affiliation":[{"name":"ReLER, CCAI, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2940-4805","authenticated-orcid":false,"given":"Yunqiu","family":"Xu","sequence":"additional","affiliation":[{"name":"ReLER, CCAI, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4093-7557","authenticated-orcid":false,"given":"Linchao","family":"Zhu","sequence":"additional","affiliation":[{"name":"The State Key Lab of Brain-Machine Intelligence, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1487-8044","authenticated-orcid":false,"given":"Guang","family":"Chen","sequence":"additional","affiliation":[{"name":"ByteDance Inc., San Jose, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4407-4948","authenticated-orcid":false,"given":"Yufei","family":"Wang","sequence":"additional","affiliation":[{"name":"character.ai, Menlo Park, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0512-880X","authenticated-orcid":false,"given":"Yi","family":"Yang","sequence":"additional","affiliation":[{"name":"ReLER, CCAI, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al.","author":"Achiam Josh","year":"2023","unstructured":"Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al. 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)."},{"key":"e_1_3_2_1_2_1","first-page":"23716","article-title":"Flamingo: a visual language model for few-shot learning","volume":"35","author":"Alayrac Jean-Baptiste","year":"2022","unstructured":"Jean-Baptiste Alayrac, Jeff Donahue, Pauline Luc, Antoine Miech, Iain Barr, Yana Hasson, Karel Lenc, Arthur Mensch, Katherine Millican, Malcolm Reynolds, et al. 2022. Flamingo: a visual language model for few-shot learning. Advances in Neural Information Processing Systems, Vol. 35 (2022), 23716--23736.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_3_1","volume-title":"Openflamingo: An open-source framework for training large autoregressive vision-language models. arXiv preprint arXiv:2308.01390","author":"Awadalla Anas","year":"2023","unstructured":"Anas Awadalla, Irena Gao, Josh Gardner, Jack Hessel, Yusuf Hanafy, Wanrong Zhu, Kalyani Marathe, Yonatan Bitton, Samir Gadre, Shiori Sagawa, et al. 2023. Openflamingo: An open-source framework for training large autoregressive vision-language models. arXiv preprint arXiv:2308.01390 (2023)."},{"key":"e_1_3_2_1_4_1","volume-title":"Proceedings of the acl workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization. 65--72","author":"Banerjee Satanjeev","year":"2005","unstructured":"Satanjeev Banerjee and Alon Lavie. 2005. METEOR: An automatic metric for MT evaluation with improved correlation with human judgments. In Proceedings of the acl workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization. 65--72."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.5555\/2002472.2002497"},{"key":"e_1_3_2_1_6_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Chen Sihan","year":"2024","unstructured":"Sihan Chen, Handong Li, Qunbo Wang, Zijia Zhao, Mingzhen Sun, Xinxin Zhu, and Jing Liu. 2024. Vast: A vision-audio-subtitle-text omni-modality foundation model and dataset. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_7_1","unstructured":"Xi Chen Xiao Wang Lucas Beyer Alexander Kolesnikov Jialin Wu Paul Voigtlaender Basil Mustafa Sebastian Goodman Ibrahim Alabdulmohsin Piotr Padlewski et al. 2023. Pali-3 vision language models: Smaller faster stronger. arXiv preprint arXiv:2310.09199 (2023)."},{"key":"e_1_3_2_1_8_1","volume-title":"Universal Captioner: Inducing Content-Style Separation in Vision-and-Language Model Training. arXiv preprint arXiv:2111.12727","author":"Cornia Marcella","year":"2021","unstructured":"Marcella Cornia, Lorenzo Baraldi, Giuseppe Fiameni, and Rita Cucchiara. 2021. Universal Captioner: Inducing Content-Style Separation in Vision-and-Language Model Training. arXiv preprint arXiv:2111.12727 (2021)."},{"key":"e_1_3_2_1_9_1","volume-title":"Eva: Exploring the limits of masked visual representation learning at scale. arXiv preprint arXiv:2211.07636","author":"Fang Yuxin","year":"2022","unstructured":"Yuxin Fang, Wen Wang, Binhui Xie, Quan Sun, Ledell Wu, Xinggang Wang, Tiejun Huang, Xinlong Wang, and Yue Cao. 2022. Eva: Exploring the limits of masked visual representation learning at scale. arXiv preprint arXiv:2211.07636 (2022)."},{"key":"e_1_3_2_1_10_1","volume-title":"I Can't Believe There's No Images! Learning Visual Tasks Using only Language Supervision. arXiv preprint arXiv:2211.09778","author":"Gu Sophia","year":"2022","unstructured":"Sophia Gu, Christopher Clark, and Aniruddha Kembhavi. 2022. I Can't Believe There's No Images! Learning Visual Tasks Using only Language Supervision. arXiv preprint arXiv:2211.09778 (2022)."},{"key":"e_1_3_2_1_11_1","volume-title":"Benchmarking Micro-action Recognition: Dataset, Method, and Application","author":"Guo Dan","year":"2024","unstructured":"Dan Guo, Kun Li, Bin Hu, Yan Zhang, and Meng Wang. 2024. Benchmarking Micro-action Recognition: Dataset, Method, and Application. IEEE Transactions on Circuits and Systems for Video Technology (2024)."},{"key":"e_1_3_2_1_12_1","volume-title":"Onellm: One framework to align all modalities with language. arXiv preprint arXiv:2312.03700","author":"Han Jiaming","year":"2023","unstructured":"Jiaming Han, Kaixiong Gong, Yiyuan Zhang, Jiaqi Wang, Kaipeng Zhang, Dahua Lin, Yu Qiao, Peng Gao, and Xiangyu Yue. 2023. Onellm: One framework to align all modalities with language. arXiv preprint arXiv:2312.03700 (2023)."},{"key":"e_1_3_2_1_13_1","volume-title":"Vlab: Enhancing video language pre-training by feature adapting and blending. arXiv preprint arXiv:2305.13167","author":"He Xingjian","year":"2023","unstructured":"Xingjian He, Sihan Chen, Fan Ma, Zhicheng Huang, Xiaojie Jin, Zikang Liu, Dongmei Fu, Yi Yang, Jing Liu, and Jiashi Feng. 2023. Vlab: Enhancing video language pre-training by feature adapting and blending. arXiv preprint arXiv:2305.13167 (2023)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1"},{"key":"e_1_3_2_1_15_1","volume-title":"International Conference on Machine Learning. PMLR, 2790--2799","author":"Houlsby Neil","year":"2019","unstructured":"Neil Houlsby, Andrei Giurgiu, Stanislaw Jastrzebski, Bruna Morrone, Quentin De Laroussilhe, Andrea Gesmundo, Mona Attariyan, and Sylvain Gelly. 2019. Parameter-efficient transfer learning for NLP. In International Conference on Machine Learning. PMLR, 2790--2799."},{"key":"e_1_3_2_1_16_1","volume-title":"Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685","author":"Hu Edward J","year":"2021","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2021. Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)."},{"key":"e_1_3_2_1_17_1","volume-title":"Llm-adapters: An adapter family for parameter-efficient fine-tuning of large language models. arXiv preprint arXiv:2304.01933","author":"Hu Zhiqiang","year":"2023","unstructured":"Zhiqiang Hu, Lei Wang, Yihuai Lan, Wanyu Xu, Ee-Peng Lim, Lidong Bing, Xing Xu, Soujanya Poria, and Roy Ka-Wei Lee. 2023. Llm-adapters: An adapter family for parameter-efficient fine-tuning of large language models. arXiv preprint arXiv:2304.01933 (2023)."},{"key":"e_1_3_2_1_18_1","volume-title":"International conference on machine learning. PMLR, 4651--4664","author":"Jaegle Andrew","year":"2021","unstructured":"Andrew Jaegle, Felix Gimeno, Andy Brock, Oriol Vinyals, Andrew Zisserman, and Joao Carreira. 2021. Perceiver: General perception with iterative attention. In International conference on machine learning. PMLR, 4651--4664."},{"key":"e_1_3_2_1_19_1","volume-title":"Categorical reparameterization with gumbel-softmax. arXiv preprint arXiv:1611.01144","author":"Jang Eric","year":"2016","unstructured":"Eric Jang, Shixiang Gu, and Ben Poole. 2016. Categorical reparameterization with gumbel-softmax. arXiv preprint arXiv:1611.01144 (2016)."},{"key":"e_1_3_2_1_20_1","volume-title":"Diego de las Casas, Emma Bou Hanna, Florian Bressand, et al.","author":"Jiang Albert Q","year":"2024","unstructured":"Albert Q Jiang, Alexandre Sablayrolles, Antoine Roux, Arthur Mensch, Blanche Savary, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Emma Bou Hanna, Florian Bressand, et al. 2024. Mixtral of experts. arXiv preprint arXiv:2401.04088 (2024)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01744"},{"key":"e_1_3_2_1_22_1","volume-title":"Gshard: Scaling giant models with conditional computation and automatic sharding. arXiv preprint arXiv:2006.16668","author":"Lepikhin Dmitry","year":"2020","unstructured":"Dmitry Lepikhin, HyoukJoong Lee, Yuanzhong Xu, Dehao Chen, Orhan Firat, Yanping Huang, Maxim Krikun, Noam Shazeer, and Zhifeng Chen. 2020. Gshard: Scaling giant models with conditional computation and automatic sharding. arXiv preprint arXiv:2006.16668 (2020)."},{"key":"e_1_3_2_1_23_1","volume-title":"The power of scale for parameter-efficient prompt tuning. arXiv preprint arXiv:2104.08691","author":"Lester Brian","year":"2021","unstructured":"Brian Lester, Rami Al-Rfou, and Noah Constant. 2021. The power of scale for parameter-efficient prompt tuning. arXiv preprint arXiv:2104.08691 (2021)."},{"key":"e_1_3_2_1_24_1","volume-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023. Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597 (2023)."},{"key":"e_1_3_2_1_25_1","volume-title":"International Conference on Machine Learning. PMLR, 12888--12900","author":"Li Junnan","year":"2022","unstructured":"Junnan Li, Dongxu Li, Caiming Xiong, and Steven Hoi. 2022. Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In International Conference on Machine Learning. PMLR, 12888--12900."},{"key":"e_1_3_2_1_26_1","volume-title":"DeCap: Decoding CLIP Latents for Zero-Shot Captioning via Text-Only Training. arXiv preprint arXiv:2303.03032","author":"Li Wei","year":"2023","unstructured":"Wei Li, Linchao Zhu, Longyin Wen, and Yi Yang. 2023. DeCap: Decoding CLIP Latents for Zero-Shot Captioning via Text-Only Training. arXiv preprint arXiv:2303.03032 (2023)."},{"key":"e_1_3_2_1_27_1","volume-title":"Prefix-tuning: Optimizing continuous prompts for generation. arXiv preprint arXiv:2101.00190","author":"Li Xiang Lisa","year":"2021","unstructured":"Xiang Lisa Li and Percy Liang. 2021. Prefix-tuning: Optimizing continuous prompts for generation. arXiv preprint arXiv:2101.00190 (2021)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00256"},{"key":"e_1_3_2_1_29_1","first-page":"109","article-title":"Scaling & shifting your features: A new baseline for efficient model tuning","volume":"35","author":"Lian Dongze","year":"2022","unstructured":"Dongze Lian, Daquan Zhou, Jiashi Feng, and Xinchao Wang. 2022. Scaling & shifting your features: A new baseline for efficient model tuning. Advances in Neural Information Processing Systems, Vol. 35 (2022), 109--123.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.3115\/1218955.1219032"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01742"},{"key":"e_1_3_2_1_32_1","volume-title":"Visual instruction tuning. Advances in neural information processing systems","author":"Liu Haotian","year":"2024","unstructured":"Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2024. Visual instruction tuning. Advances in neural information processing systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_33_1","first-page":"4404","article-title":"Self-reinforcing unsupervised matching","volume":"44","author":"Lu Jiang","year":"2021","unstructured":"Jiang Lu, Lei Li, and Changshui Zhang. 2021. Self-reinforcing unsupervised matching. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 44, 8 (2021), 4404--4418.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3365249"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28202"},{"key":"e_1_3_2_1_36_1","volume-title":"Text-Only Training for Image Captioning using Noise-Injected CLIP. arXiv preprint arXiv:2211.00575","author":"Nukrai David","year":"2022","unstructured":"David Nukrai, Ron Mokady, and Amir Globerson. 2022. Text-Only Training for Image Captioning using Noise-Injected CLIP. arXiv preprint arXiv:2211.00575 (2022)."},{"key":"e_1_3_2_1_37_1","first-page":"26462","article-title":"ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learning","volume":"35","author":"Pan Junting","year":"2022","unstructured":"Junting Pan, Ziyi Lin, Xiatian Zhu, Jing Shao, and Hongsheng Li. 2022. ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learning. Advances in Neural Information Processing Systems, Vol. 35 (2022), 26462--26477.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_38_1","volume-title":"A Simple Recipe for Contrastively Pre-training Video-First Encoders Beyond 16 Frames. arXiv preprint arXiv:2312.07395","author":"Papalampidi Pinelopi","year":"2023","unstructured":"Pinelopi Papalampidi, Skanda Koppula, Shreya Pathak, Justin Chiu, Joe Heyward, Viorica Patraucean, Jiajun Shen, Antoine Miech, Andrew Zisserman, and Aida Nematzdeh. 2023. A Simple Recipe for Contrastively Pre-training Video-First Encoders Beyond 16 Frames. arXiv preprint arXiv:2312.07395 (2023)."},{"key":"e_1_3_2_1_39_1","volume-title":"Proceedings of the 40th annual meeting of the Association for Computational Linguistics. 311--318","author":"Papineni Kishore","year":"2002","unstructured":"Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. Bleu: a method for automatic evaluation of machine translation. In Proceedings of the 40th annual meeting of the Association for Computational Linguistics. 311--318."},{"key":"e_1_3_2_1_40_1","volume-title":"Mining Fine-Grained Image-Text Alignment for Zero-Shot Captioning via Text-Only Training. arXiv preprint arXiv:2401.02347","author":"Qiu Longtian","year":"2024","unstructured":"Longtian Qiu, Shan Ning, and Xuming He. 2024. Mining Fine-Grained Image-Text Alignment for Zero-Shot Captioning via Text-Only Training. arXiv preprint arXiv:2401.02347 (2024)."},{"key":"e_1_3_2_1_41_1","volume-title":"International conference on machine learning. PMLR, 8748--8763","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 International conference on machine learning. PMLR, 8748--8763."},{"key":"e_1_3_2_1_42_1","unstructured":"Alec Radford Karthik Narasimhan Tim Salimans Ilya Sutskever et al. 2018. Improving language understanding by generative pre-training. (2018)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1202"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01743"},{"key":"e_1_3_2_1_45_1","volume-title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer. arXiv preprint arXiv:1701.06538","author":"Shazeer Noam","year":"2017","unstructured":"Noam Shazeer, Azalia Mirhoseini, Krzysztof Maziarz, Andy Davis, Quoc Le, Geoffrey Hinton, and Jeff Dean. 2017. Outrageously large neural networks: The sparsely-gated mixture-of-experts layer. arXiv preprint arXiv:1701.06538 (2017)."},{"key":"e_1_3_2_1_46_1","volume-title":"Language models can see: plugging visual controls in text generation. arXiv preprint arXiv:2205.02655","author":"Su Yixuan","year":"2022","unstructured":"Yixuan Su, Tian Lan, Yahui Liu, Fangyu Liu, Dani Yogatama, Yan Wang, Lingpeng Kong, and Nigel Collier. 2022. Language models can see: plugging visual controls in text generation. arXiv preprint arXiv:2205.02655 (2022)."},{"key":"e_1_3_2_1_47_1","volume-title":"Lst: Ladder side-tuning for parameter and memory efficient transfer learning. arXiv preprint arXiv:2206.06522","author":"Sung Yi-Lin","year":"2022","unstructured":"Yi-Lin Sung, Jaemin Cho, and Mohit Bansal. 2022. Lst: Ladder side-tuning for parameter and memory efficient transfer learning. arXiv preprint arXiv:2206.06522 (2022)."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00516"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01739"},{"key":"e_1_3_2_1_50_1","volume-title":"Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timoth\u00e9e Lacroix, Baptiste Rozi\u00e8re, Naman Goyal, Eric Hambro, Faisal Azhar, et al. 2023. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"e_1_3_2_1_52_1","volume-title":"GLUE: A multi-task benchmark and analysis platform for natural language understanding. arXiv preprint arXiv:1804.07461","author":"Wang Alex","year":"2018","unstructured":"Alex Wang, Amanpreet Singh, Julian Michael, Felix Hill, Omer Levy, and Samuel R Bowman. 2018. GLUE: A multi-task benchmark and analysis platform for natural language understanding. arXiv preprint arXiv:1804.07461 (2018)."},{"key":"e_1_3_2_1_53_1","volume-title":"Git: A generative image-to-text transformer for vision and language. arXiv preprint arXiv:2205.14100","author":"Wang Jianfeng","year":"2022","unstructured":"Jianfeng Wang, Zhengyuan Yang, Xiaowei Hu, Linjie Li, Kevin Lin, Zhe Gan, Zicheng Liu, Ce Liu, and Lijuan Wang. 2022. Git: A generative image-to-text transformer for vision and language. arXiv preprint arXiv:2205.14100 (2022)."},{"key":"e_1_3_2_1_54_1","volume-title":"Zero-shot Image Captioning by Anchor-augmented Vision-Language Space Alignment. arXiv preprint arXiv:2211.07275","author":"Wang Junyang","year":"2022","unstructured":"Junyang Wang, Yi Zhang, Ming Yan, Ji Zhang, and Jitao Sang. 2022. Zero-shot Image Captioning by Anchor-augmented Vision-Language Space Alignment. arXiv preprint arXiv:2211.07275 (2022)."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00468"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"crossref","unstructured":"Yi Wang Kunchang Li Xinhao Li Jiashuo Yu Yinan He Guo Chen Baoqi Pei Rongkun Zheng Jilan Xu Zun Wang et al. 2024. InternVideo2: Scaling Video Foundation Models for Multimodal Video Understanding. arXiv preprint arXiv:2403.15377 (2024).","DOI":"10.1007\/978-3-031-73013-9_23"},{"key":"e_1_3_2_1_57_1","volume-title":"PaLM2-VAdapter: Progressively Aligned Language Model Makes a Strong Vision-language Adapter. arXiv preprint arXiv:2402.10896","author":"Xiao Junfei","year":"2024","unstructured":"Junfei Xiao, Zheng Xu, Alan Yuille, Shen Yan, and Boyu Wang. 2024. PaLM2-VAdapter: Progressively Aligned Language Model Makes a Strong Vision-language Adapter. arXiv preprint arXiv:2402.10896 (2024)."},{"key":"e_1_3_2_1_58_1","volume-title":"International Conference on Machine Learning. PMLR, 38728--38748","author":"Xu Haiyang","year":"2023","unstructured":"Haiyang Xu, Qinghao Ye, Ming Yan, Yaya Shi, Jiabo Ye, Yuanhong Xu, Chenliang Li, Bin Bi, Qi Qian, Wei Wang, et al. 2023. mplug-2: A modularized multi-modal foundation model across text, image and video. In International Conference on Machine Learning. PMLR, 38728--38748."},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681039"},{"key":"e_1_3_2_1_61_1","volume-title":"Video-Text Modeling with Zero-Shot Transfer from Contrastive Captioners. arXiv preprint arXiv:2212.04979","author":"Yan Shen","year":"2022","unstructured":"Shen Yan, Tao Zhu, Zirui Wang, Yuan Cao, Mi Zhang, Soham Ghosh, Yonghui Wu, and Jiahui Yu. 2022. Video-Text Modeling with Zero-Shot Transfer from Contrastive Captioners. arXiv preprint arXiv:2212.04979 (2022)."},{"key":"e_1_3_2_1_62_1","volume-title":"Antoine Miech, Jordi Pont-Tuset, Ivan Laptev, Josef Sivic, and Cordelia Schmid.","author":"Yang Antoine","year":"2023","unstructured":"Antoine Yang, Arsha Nagrani, Paul Hongsuck Seo, Antoine Miech, Jordi Pont-Tuset, Ivan Laptev, Josef Sivic, and Cordelia Schmid. 2023. Vid2Seq: Large-scale pretraining of a visual language model for dense video captioning. arXiv preprint arXiv:2302.14115 (2023)."},{"key":"e_1_3_2_1_63_1","volume-title":"Multicapclip: Auto-encoding prompts for zero-shot multilingual visual captioning. arXiv preprint arXiv:2308.13218","author":"Yang Bang","year":"2023","unstructured":"Bang Yang, Fenglin Liu, Xian Wu, Yaowei Wang, Xu Sun, and Yuexian Zou. 2023. Multicapclip: Auto-encoding prompts for zero-shot multilingual visual captioning. arXiv preprint arXiv:2308.13218 (2023)."},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28475"},{"key":"e_1_3_2_1_65_1","volume-title":"HiTeA: Hierarchical Temporal-Aware Video-Language Pre-training. arXiv preprint arXiv:2212.14546","author":"Ye Qinghao","year":"2022","unstructured":"Qinghao Ye, Guohai Xu, Ming Yan, Haiyang Xu, Qi Qian, Ji Zhang, and Fei Huang. 2022. HiTeA: Hierarchical Temporal-Aware Video-Language Pre-training. arXiv preprint arXiv:2212.14546 (2022)."},{"key":"e_1_3_2_1_66_1","volume-title":"Coca: Contrastive captioners are image-text foundation models. arXiv preprint arXiv:2205.01917","author":"Yu Jiahui","year":"2022","unstructured":"Jiahui Yu, Zirui Wang, Vijay Vasudevan, Legg Yeung, Mojtaba Seyedhosseini, and Yonghui Wu. 2022. Coca: Contrastive captioners are image-text foundation models. arXiv preprint arXiv:2205.01917 (2022)."},{"key":"e_1_3_2_1_67_1","volume-title":"Bitfit: Simple parameter-efficient fine-tuning for transformer-based masked language-models. arXiv preprint arXiv:2106.10199","author":"Zaken Elad Ben","year":"2021","unstructured":"Elad Ben Zaken, Shauli Ravfogel, and Yoav Goldberg. 2021. Bitfit: Simple parameter-efficient fine-tuning for transformer-based masked language-models. arXiv preprint arXiv:2106.10199 (2021)."},{"key":"e_1_3_2_1_68_1","unstructured":"Andy Zeng Adrian Wong Stefan Welker Krzysztof Choromanski Federico Tombari Aveek Purohit Michael Ryoo Vikas Sindhwani Johnny Lee Vincent Vanhoucke et al. 2022. Socratic models: Composing zero-shot multimodal reasoning with language. arXiv preprint arXiv:2204.00598 (2022)."},{"key":"e_1_3_2_1_69_1","volume-title":"MeaCap: Memory-Augmented Zero-shot Image Captioning. arXiv preprint arXiv:2403.03715","author":"Zeng Zequn","year":"2024","unstructured":"Zequn Zeng, Yan Xie, Hao Zhang, Chiyu Chen, Zhengjue Wang, and Bo Chen. 2024. MeaCap: Memory-Augmented Zero-shot Image Captioning. arXiv preprint arXiv:2403.03715 (2024)."},{"key":"e_1_3_2_1_70_1","volume-title":"Llama-adapter: Efficient fine-tuning of language models with zero-init attention. arXiv preprint arXiv:2303.16199","author":"Zhang Renrui","year":"2023","unstructured":"Renrui Zhang, Jiaming Han, Aojun Zhou, Xiangfei Hu, Shilin Yan, Pan Lu, Hongsheng Li, Peng Gao, and Yu Qiao. 2023. Llama-adapter: Efficient fine-tuning of language models with zero-init attention. arXiv preprint arXiv:2303.16199 (2023)."},{"key":"e_1_3_2_1_71_1","volume-title":"Xi Victoria Lin, et al","author":"Zhang Susan","year":"2022","unstructured":"Susan Zhang, Stephen Roller, Naman Goyal, Mikel Artetxe, Moya Chen, Shuohui Chen, Christopher Dewan, Mona Diab, Xian Li, Xi Victoria Lin, et al. 2022. Opt: Open pre-trained transformer language models. arXiv preprint arXiv:2205.01068 (2022)."},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"crossref","unstructured":"Yue Zhao Long Zhao Xingyi Zhou Jialin Wu Chun-Te Chu Hui Miao Florian Schroff Hartwig Adam Ting Liu Boqing Gong et al. 2024. Distilling vision-language models on millions of videos. arXiv preprint arXiv:2401.06129 (2024).","DOI":"10.1109\/CVPR52733.2024.01245"},{"key":"e_1_3_2_1_73_1","volume-title":"Chatbridge: Bridging modalities with large language model as a language catalyst. arXiv preprint arXiv:2305.16103","author":"Zhao Zijia","year":"2023","unstructured":"Zijia Zhao, Longteng Guo, Tongtian Yue, Sihan Chen, Shuai Shao, Xinxin Zhu, Zehuan Yuan, and Jing Liu. 2023. Chatbridge: Bridging modalities with large language model as a language catalyst. arXiv preprint arXiv:2305.16103 (2023)."},{"key":"e_1_3_2_1_74_1","volume-title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models. arXiv preprint arXiv:2304.10592","author":"Zhu Deyao","year":"2023","unstructured":"Deyao Zhu, Jun Chen, Xiaoqian Shen, Xiang Li, and Mohamed Elhoseiny. 2023. MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models. arXiv preprint arXiv:2304.10592 (2023)."},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01630"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680686","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3680686","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:57Z","timestamp":1750295877000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680686"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":75,"alternative-id":["10.1145\/3664647.3680686","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3680686","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}