{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T08:36:16Z","timestamp":1789029376477,"version":"build-2803163510"},"publisher-location":"New York, NY, USA","reference-count":68,"publisher":"ACM","funder":[{"name":"Hong Kong SAR RGC Early Career Scheme","award":["2620892"],"award-info":[{"award-number":["2620892"]}]},{"name":"National Natural Science Foundation of China Young Scholar Fund","award":["2402408"],"award-info":[{"award-number":["2402408"]}]},{"name":"HKUST Sports Science and Technology Research Grant","award":["SSTRG24EG04"],"award-info":[{"award-number":["SSTRG24EG04"]}]},{"name":"Innovation and Technology Fund of HKSAR","award":["GHX\/054\/21GD"],"award-info":[{"award-number":["GHX\/054\/21GD"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755705","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:56:44Z","timestamp":1761375404000},"page":"10476-10485","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["SpA2V: Harnessing Spatial Auditory Cues for Audio-driven Spatially-aware Video Generation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-4529-8584","authenticated-orcid":false,"given":"Kien T.","family":"Pham","sequence":"first","affiliation":[{"name":"Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0134-8220","authenticated-orcid":false,"given":"Yingqing","family":"He","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2872-0192","authenticated-orcid":false,"given":"Yazhou","family":"Xing","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2199-3948","authenticated-orcid":false,"given":"Qifeng","family":"Chen","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6148-9709","authenticated-orcid":false,"given":"Long","family":"Chen","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Andreas Blattmann Tim Dockhorn Sumith Kulal Daniel Mendelevitch Maciej Kilian Dominik Lorenz Yam Levi Zion English Vikram Voleti Adam Letts Varun Jampani and Robin Rombach. 2023. Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets. arXiv:2311.15127 [cs.CV] https:\/\/arxiv.org\/abs\/2311.15127"},{"key":"e_1_3_2_1_2_1","first-page":"1877","volume-title":"Lin (Eds.)","volume":"33","author":"Brown Tom","year":"2020","unstructured":"Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel Ziegler, Jeffrey Wu, Clemens Winter, Chris Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei. 2020. Language Models are Few-Shot Learners. In Advances in Neural Information Processing Systems, H. Larochelle, M. Ranzato, R. Hadsell, M.F. Balcan, and H. Lin (Eds.), Vol. 33. Curran Associates, Inc., 1877-1901. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2020\/file\/1457c0d6bfcb4967418bfb8ac142f64a-Paper.pdf"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58583-9_42"},{"key":"e_1_3_2_1_4_1","volume-title":"Audio-visual synchronisation in the wild. arXiv preprint arXiv:2112.04432","author":"Chen Honglie","year":"2021","unstructured":"Honglie Chen, Weidi Xie, Triantafyllos Afouras, Arsha Nagrani, Andrea Vedaldi, and Andrew Zisserman. 2021. Audio-visual synchronisation in the wild. arXiv preprint arXiv:2112.04432 (2021)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"Jianlv Chen Shitao Xiao Peitian Zhang Kun Luo Defu Lian and Zheng Liu. 2023. BGE M3-Embedding: Multi-Lingual Multi-Functionality Multi-Granularity Text Embeddings Through Self-Knowledge Distillation. arXiv:2309.07597 [cs.CL]","DOI":"10.18653\/v1\/2024.findings-acl.137"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3126686.3126723"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02502"},{"key":"e_1_3_2_1_8_1","first-page":"47704","volume-title":"Levine (Eds.)","volume":"36","author":"Copet Jade","year":"2023","unstructured":"Jade Copet, Felix Kreuk, Itai Gat, Tal Remez, David Kant, Gabriel Synnaeve, Yossi Adi, and Alexandre Defossez. 2023. Simple and Controllable Music Generation. In Advances in Neural Information Processing Systems, A. Oh, T. Naumann, A. Globerson, K. Saenko, M. Hardt, and S. Levine (Eds.), Vol. 36. Curran Associates, Inc., 47704-47720. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2023\/file\/94b472a1842cd7c56dcb125fb2765fbd-Paper-Conference.pdf"},{"key":"e_1_3_2_1_9_1","first-page":"33505","article-title":"Learning Spatially-Aware Language and Audio Embeddings","volume":"37","author":"Devnani Bhavika","year":"2024","unstructured":"Bhavika Devnani, Skyler Seto, Zakaria Aldeneh, Alessandro Toso, Elena Menyaylenko, Barry-John Theobald, Jonathan Sheaffer, and Miguel Sarabia. 2024. Learning Spatially-Aware Language and Audio Embeddings. Advances in Neural Information Processing Systems, Vol. 37 (2024), 33505-33537.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.64"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.501"},{"key":"e_1_3_2_1_12_1","unstructured":"Patrick Esser Sumith Kulal Andreas Blattmann Rahim Entezari Jonas M\u00fcller Harry Saini Yam Levi Dominik Lorenz Axel Sauer Frederic Boesel Dustin Podell Tim Dockhorn Zion English Kyle Lacey Alex Goodwin Yannik Marek and Robin Rombach. 2024. Scaling Rectified Flow Transformers for High-Resolution Image Synthesis. arXiv:2403.03206 [cs.CV] https:\/\/arxiv.org\/abs\/2403.03206"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747644"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02069"},{"key":"e_1_3_2_1_15_1","volume-title":"Forty-Second International Conference on Machine Learning.","author":"Gao Kaifeng","year":"2025","unstructured":"Kaifeng Gao, Jiaxin Shi, Hanwang Zhang, Chunping Wang, Jun Xiao, and Long Chen. 2025. Ca2-vdm: Efficient autoregressive video diffusion model with causal generation and cache sharing. In Forty-Second International Conference on Machine Learning."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00041"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.361"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681586"},{"key":"e_1_3_2_1_19_1","volume-title":"The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=Fx2SbBgcte","author":"Guo Yuwei","year":"2024","unstructured":"Yuwei Guo, Ceyuan Yang, Anyi Rao, Zhengyang Liang, Yaohui Wang, Yu Qiao, Maneesh Agrawala, Dahua Lin, and Bo Dai. 2024b. AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=Fx2SbBgcte"},{"key":"e_1_3_2_1_20_1","volume-title":"LTX-Video: Realtime Video Latent Diffusion. arXiv preprint arXiv:2501.00103","author":"HaCohen Yoav","year":"2024","unstructured":"Yoav HaCohen, Nisan Chiprut, Benny Brazowski, Daniel Shalem, Dudu Moshe, Eitan Richardson, Eran Levin, Guy Shiran, Nir Zabari, Ori Gordon, Poriya Panet, Sapir Weissbuch, Victor Kulikov, Yaki Bitterman, Zeev Melumian, and Ofir Bibi. 2024. LTX-Video: Realtime Video Latent Diffusion. arXiv preprint arXiv:2501.00103 (2024)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_22_1","first-page":"6840","volume-title":"Lin (Eds.)","volume":"33","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising Diffusion Probabilistic Models. In Advances in Neural Information Processing Systems, H. Larochelle, M. Ranzato, R. Hadsell, M.F. Balcan, and H. Lin (Eds.), Vol. 33. Curran Associates, Inc., 6840-6851. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2020\/file\/4c5bcfec8584af0d967f1ab10179ca4b-Paper.pdf"},{"key":"e_1_3_2_1_23_1","volume-title":"Sparse in space and time: Audio-visual synchronisation with trainable selectors. arXiv preprint arXiv:2210.07055","author":"Iashin Vladimir","year":"2022","unstructured":"Vladimir Iashin, Weidi Xie, Esa Rahtu, and Andrew Zisserman. 2022. Sparse in space and time: Audio-visual synchronisation with trainable selectors. arXiv preprint arXiv:2210.07055 (2022)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448489"},{"key":"e_1_3_2_1_25_1","volume-title":"Clipdrag: Combining text-based and drag-based instructions for image editing.","author":"Jiang Ziqi","year":"2025","unstructured":"Ziqi Jiang, Zhen Wang, and Long Chen. 2025. Clipdrag: Combining text-based and drag-based instructions for image editing."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475497"},{"key":"e_1_3_2_1_27_1","volume-title":"Proceedings of the 41st International Conference on Machine Learning (Proceedings of Machine Learning Research","volume":"25124","author":"Kondratyuk Dan","year":"2024","unstructured":"Dan Kondratyuk, Lijun Yu, Xiuye Gu, Jose Lezama, Jonathan Huang, Grant Schindler, Rachel Hornung, Vighnesh Birodkar, Jimmy Yan, Ming-Chang Chiu, Krishna Somandepalli, Hassan Akbari, Yair Alon, Yong Cheng, Joshua V. Dillon, Agrim Gupta, Meera Hahn, Anja Hauth, David Hendon, Alonso Martinez, David Minnen, Mikhail Sirotenko, Kihyuk Sohn, Xuan Yang, Hartwig Adam, Ming-Hsuan Yang, Irfan Essa, Huisheng Wang, David A Ross, Bryan Seybold, and Lu Jiang. 2024. VideoPoet: A Large Language Model for Zero-Shot Video Generation. In Proceedings of the 41st International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 235), Ruslan Salakhutdinov, Zico Kolter, Katherine Heller, Adrian Weller, Nuria Oliver, Jonathan Scarlett, and Felix Berkenkamp (Eds.). PMLR, 25105-25124. https:\/\/proceedings.mlr.press\/v235\/kondratyuk24a.html"},{"key":"e_1_3_2_1_28_1","first-page":"14042","article-title":"Ccvs: Context-aware controllable video synthesis","volume":"34","author":"Moing Guillaume Le","year":"2021","unstructured":"Guillaume Le Moing, Jean Ponce, and Cordelia Schmid. 2021. Ccvs: Context-aware controllable video synthesis. Advances in Neural Information Processing Systems, Vol. 34 (2021), 14042-14055.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_3"},{"key":"e_1_3_2_1_30_1","volume-title":"LLaVA-OneVision: Easy Visual Task Transfer. Transactions on Machine Learning Research","author":"Li Bo","year":"2025","unstructured":"Bo Li, Yuanhan Zhang, Dong Guo, Renrui Zhang, Feng Li, Hao Zhang, Kaichen Zhang, Peiyuan Zhang, Yanwei Li, Ziwei Liu, and Chunyuan Li. 2025. LLaVA-OneVision: Easy Visual Task Transfer. Transactions on Machine Learning Research (2025). https:\/\/openreview.net\/forum?id=zKv8qULV6n"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"e_1_3_2_1_32_1","volume-title":"LLM-grounded Video Diffusion Models. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=exKHibougU","author":"Lian Long","year":"2024","unstructured":"Long Lian, Baifeng Shi, Adam Yala, Trevor Darrell, and Boyi Li. 2024. LLM-grounded Video Diffusion Models. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=exKHibougU"},{"key":"e_1_3_2_1_33_1","volume-title":"Proceedings of the 40th International Conference on Machine Learning","author":"Liu Haohe","unstructured":"Haohe Liu, Zehua Chen, Yi Yuan, Xinhao Mei, Xubo Liu, Danilo Mandic, Wenwu Wang, and Mark D. Plumbley. 2023a. AudioLDM: text-to-audio generation with latent diffusion models. In Proceedings of the 40th International Conference on Machine Learning (Honolulu, Hawaii, USA) (ICML'23). JMLR.org, Article 886, 25 pages."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3399607"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","unstructured":"Jiachang Liu Dinghan Shen Yizhe Zhang Bill Dolan Lawrence Carin and Weizhu Chen. 2022. What Makes Good In-Context Examples for GPT-3?. In Proceedings of Deep Learning Inside Out (DeeLIO 2022): The 3rd Workshop on Knowledge Extraction and Integration for Deep Learning Architectures Eneko Agirre Marianna Apidianaki and Ivan Vuli\u0107 (Eds.). Association for Computational Linguistics Dublin Ireland and Online 100-114. doi:10.18653\/v1\/2022.deelio-1.10","DOI":"10.18653\/v1\/2022.deelio-1.10"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02104"},{"key":"e_1_3_2_1_37_1","unstructured":"OpenAI. 2024a. GPT-4 Technical Report. arXiv:2303.08774 [cs.CL] https:\/\/arxiv.org\/abs\/2303.08774"},{"key":"e_1_3_2_1_38_1","unstructured":"OpenAI. 2024b. GPT-4o System Card. arXiv:2410.21276 [cs.CL] https:\/\/arxiv.org\/abs\/2410.21276"},{"key":"e_1_3_2_1_39_1","unstructured":"Mayu Otani Naoto Inoue Kotaro Kikuchi and Riku Togashi. 2024. LTSim: Layout Transportation-based Similarity Measure for Evaluating Layout Generation. arXiv:2407.12356 [cs.CV] https:\/\/arxiv.org\/abs\/2407.12356"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00280"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681079"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_44_1","volume-title":"U-Net: Convolutional Networks for Biomedical Image Segmentation. ArXiv","author":"Ronneberger Olaf","year":"2015","unstructured":"Olaf Ronneberger, Philipp Fischer, and Thomas Brox. 2015. U-Net: Convolutional Networks for Biomedical Image Segmentation. ArXiv, Vol. abs\/1505.04597 (2015). https:\/\/api.semanticscholar.org\/CorpusID:3719281"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00985"},{"key":"e_1_3_2_1_46_1","first-page":"2256","volume-title":"Proceedings of the 32nd International Conference on International Conference on Machine Learning -","volume":"37","author":"Sohl-Dickstein Jascha","year":"2015","unstructured":"Jascha Sohl-Dickstein, Eric A. Weiss, Niru Maheswaranathan, and Surya Ganguli. 2015. Deep unsupervised learning using nonequilibrium thermodynamics. In Proceedings of the 32nd International Conference on International Conference on Machine Learning - Volume 37 (Lille, France) (ICML'15). JMLR.org, 2256-2265."},{"key":"e_1_3_2_1_47_1","volume-title":"International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=PxTIG12RRHS","author":"Song Yang","year":"2021","unstructured":"Yang Song, Jascha Sohl-Dickstein, Diederik P Kingma, Abhishek Kumar, Stefano Ermon, and Ben Poole. 2021. Score-Based Generative Modeling through Stochastic Differential Equations. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=PxTIG12RRHS"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28314"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","unstructured":"Shuai Tan Bin Ji and Ye Pan. 2024a. Style2Talker: high-resolution talking head generation with emotion style and art style. In Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence and Thirty-Sixth Conference on Innovative Applications of Artificial Intelligence and Fourteenth Symposium on Educational Advances in Artificial Intelligence (AAAI'24\/IAAI'24\/EAAI'24). AAAI Press Article 565 9 pages. doi:10.1609\/aaai.v38i5.28313","DOI":"10.1609\/aaai.v38i5.28313"},{"key":"e_1_3_2_1_50_1","unstructured":"Gemini Team. 2024a. Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context. arXiv:2403.05530 [cs.CL] https:\/\/arxiv.org\/abs\/2403.05530"},{"key":"e_1_3_2_1_51_1","volume-title":"Gemini: A Family of Highly Capable Multimodal Models. arXiv:2312.11805 [cs.CL] https:\/\/arxiv.org\/abs\/2312.11805","author":"Team Gemini","year":"2024","unstructured":"Gemini Team. 2024b. Gemini: A Family of Highly Capable Multimodal Models. arXiv:2312.11805 [cs.CL] https:\/\/arxiv.org\/abs\/2312.11805"},{"key":"e_1_3_2_1_52_1","unstructured":"Llama 3 Team. 2024c. The Llama 3 Herd of Models. arXiv:2407.21783 [cs.AI] https:\/\/arxiv.org\/abs\/2407.21783"},{"key":"e_1_3_2_1_53_1","unstructured":"Thomas Unterthiner Sjoerd van Steenkiste Karol Kurach Raphael Marinier Marcin Michalski and Sylvain Gelly. 2019. Towards Accurate Generative Models of Video: A New Metric & Challenges. arXiv:1812.01717 [cs.CV] https:\/\/arxiv.org\/abs\/1812.01717"},{"key":"e_1_3_2_1_54_1","volume-title":"Forty-Second International Conference on Machine Learning.","author":"Wang Zhen","year":"2025","unstructured":"Zhen Wang, Yilei Jiang, Dong Zheng, Jun Xiao, and Long Chen. 2025. Event-customized image generation. In Forty-Second International Conference on Machine Learning."},{"key":"e_1_3_2_1_55_1","volume-title":"Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation. In IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP.","author":"Yusong","year":"2023","unstructured":"Yusong Wu*, Ke Chen*, Tianyu Zhang*, Yuchen Hui*, Taylor Berg-Kirkpatrick, and Shlomo Dubnov. 2023. Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation. In IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP."},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00683"},{"key":"e_1_3_2_1_57_1","volume-title":"Track Anything: Segment Anything Meets Videos. arXiv:2304.11968 [cs.CV]","author":"Yang Jinyu","year":"2023","unstructured":"Jinyu Yang, Mingqi Gao, Zhe Li, Shang Gao, Fangjing Wang, and Feng Zheng. 2023. Track Anything: Segment Anything Meets Videos. arXiv:2304.11968 [cs.CV]"},{"key":"e_1_3_2_1_58_1","unstructured":"Tong Yang Yu Huang Yingbin Liang and Yuejie Chi. 2024. In-Context Learning with Representations: Contextual Generalization of Trained Transformers. In The Thirty-eighth Annual Conference on Neural Information Processing Systems. https:\/\/openreview.net\/forum?id=ik37kKxKBm"},{"key":"e_1_3_2_1_59_1","volume-title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer. In The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=LQzN6TRFg9","author":"Yang Zhuoyi","year":"2025","unstructured":"Zhuoyi Yang, Jiayan Teng, Wendi Zheng, Ming Ding, Shiyu Huang, Jiazheng Xu, Yuanming Yang, Wenyi Hong, Xiaohan Zhang, Guanyu Feng, Da Yin, Yuxuan.Zhang, Weihan Wang, Yean Cheng, Bin Xu, Xiaotao Gu, Yuxiao Dong, and Jie Tang. 2025. CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer. In The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=LQzN6TRFg9"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28486"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.738"},{"key":"e_1_3_2_1_62_1","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV).","author":"Zhang Lin","year":"2024","unstructured":"Lin Zhang, Shentong Mo, Yijing Zhang, and Pedro Morgado. 2024a. Audio-Synchronized Visual Animation. In Proceedings of the European Conference on Computer Vision (ECCV)."},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.126278"},{"key":"e_1_3_2_1_64_1","volume-title":"Bat: Learning to reason about spatial sounds with large language models. arXiv preprint arXiv:2402.01591","author":"Zheng Zhisheng","year":"2024","unstructured":"Zhisheng Zheng, Puyuan Peng, Ziyang Ma, Xie Chen, Eunsol Choi, and David Harwath. 2024. Bat: Learning to reason about spatial sounds with large language models. arXiv preprint arXiv:2402.01591 (2024)."},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00651"},{"key":"e_1_3_2_1_66_1","unstructured":"Jinxing Zhou Xuyang Shen Jianyuan Wang Jiayi Zhang Weixuan Sun Jing Zhang Stan Birchfield Dan Guo Lingpeng Kong Meng Wang et al. 2024b. Audio-visual segmentation with semantics. International Journal of Computer Vision (2024) 1-21."},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3183931"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/IT57431.2023.10078724"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","acronym":"MM '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755705","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:34:13Z","timestamp":1765308853000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755705"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":68,"alternative-id":["10.1145\/3746027.3755705","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755705","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"}}]}}