{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T01:43:22Z","timestamp":1787017402708,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":51,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,8,3]]},"DOI":"10.1145\/3711896.3736914","type":"proceedings-article","created":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T13:32:14Z","timestamp":1754055134000},"page":"143-154","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Does Vector Quantization Fail in Spatio-Temporal Forecasting? Exploring a Differentiable Sparse Soft-Vector Quantization Approach"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-0778-4602","authenticated-orcid":false,"given":"Chao","family":"Chen","sequence":"first","affiliation":[{"name":"Central South University, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1789-5413","authenticated-orcid":false,"given":"Tian","family":"Zhou","sequence":"additional","affiliation":[{"name":"DAMO Academy, Alibaba Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1383-8201","authenticated-orcid":false,"given":"Yanjun","family":"Zhao","sequence":"additional","affiliation":[{"name":"DAMO Academy, Alibaba Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6654-4965","authenticated-orcid":false,"given":"Hui","family":"Liu","sequence":"additional","affiliation":[{"name":"Central South University, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8797-4646","authenticated-orcid":false,"given":"Rong","family":"Jin","sequence":"additional","affiliation":[{"name":"DAMO Academy, Alibaba Group, Bellevue, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5835-7259","authenticated-orcid":false,"given":"Liang","family":"Sun","sequence":"additional","affiliation":[{"name":"DAMO Academy, Alibaba Group, Bellevue, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,8,3]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"MAU: A Motion-Aware Unit for Video Prediction and Beyond. In Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021","author":"Chang Zheng","year":"2021","unstructured":"Zheng Chang, Xinfeng Zhang, Shanshe Wang, Siwei Ma, Yan Ye, Xiang Xinguang, and Wen Gao. 2021. MAU: A Motion-Aware Unit for Video Prediction and Beyond. In Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, December 6-14, 2021, virtual, Marc'Aurelio Ranzato, Alina Beygelzimer, Yann N. Dauphin, Percy Liang, and Jennifer Wortman Vaughan(Eds.). 26950-26962. https:\/\/proceedings.neurips.cc\/paper\/2021\/hash\/e25cfa90f04351958216f97e3efdabe9-Abstract.html"},{"key":"e_1_3_2_2_2_1","volume-title":"The Twelfth International Conference on Learning Representations.","author":"Chen Xinyuan","year":"2023","unstructured":"Xinyuan Chen, Yaohui Wang, Lingjun Zhang, Shaobin Zhuang, Xin Ma, Jiashuo Yu, Yali Wang, Dahua Lin, Yu Qiao, and Ziwei Liu. 2023. Seine: Short-to-long video diffusion model for generative transition and prediction. In The Twelfth International Conference on Learning Representations."},{"key":"e_1_3_2_2_3_1","volume-title":"Self-supervised Learning with Random-projection Quantizer for Speech Recognition. In International Conference on Machine Learning.","author":"Chiu Chung-Cheng","year":"2022","unstructured":"Chung-Cheng Chiu, James Qin, Yu Zhang, Jiahui Yu, and Yonghui Wu. 2022. Self-supervised Learning with Random-projection Quantizer for Speech Recognition. In International Conference on Machine Learning."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/FOCS.2010.38"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206631"},{"key":"e_1_3_2_2_6_1","volume-title":"9th International Conference on Learning Representations, ICLR 2021","author":"Dosovitskiy Alexey","year":"2021","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In 9th International Conference on Learning Representations, ICLR 2021, Virtual Event, Austria, May 3-7, 2021. OpenReview.net. https:\/\/openreview.net\/forum?id=YicbFdNTTy"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1137\/07070471X"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01365"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00317"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913491297"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.5555\/3104322.3104374"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01149"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/S41095-023-0364-2"},{"key":"e_1_3_2_2_14_1","volume-title":"European Conference on Computer Vision. Springer, 393-411","author":"Gupta Agrim","year":"2024","unstructured":"Agrim Gupta, Lijun Yu, Kihyuk Sohn, Xiuye Gu, Meera Hahn, Fei-Fei Li, Irfan Essa, Lu Jiang, and Jos\u00e9 Lezama. 2024. Photorealistic video generation with diffusion models. In European Conference on Computer Vision. Springer, 393-411."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00593"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.248"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01123"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3282631"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2211.03295"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"e_1_3_2_2_22_1","volume-title":"Cox","author":"Lotter William","year":"2017","unstructured":"William Lotter, Gabriel Kreiman, and David D. Cox. 2017. Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning. In 5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24-26, 2017, Conference Track Proceedings. OpenReview.net. https:\/\/openreview.net\/forum?id=B1ewdt9xe"},{"key":"e_1_3_2_2_23_1","volume-title":"NWT: Towards natural audio-to-video generation with representation learning. CoRR","author":"Mama Rayhane","year":"2021","unstructured":"Rayhane Mama, Marc S. Tyndel, Hashiam Kadhim, Cole Clifford, and Ragavan Thurairatnam. 2021a. NWT: Towards natural audio-to-video generation with representation learning. CoRR, Vol. abs\/2106.04283 (2021). arXiv:2106.04283 https:\/\/arxiv.org\/abs\/2106.04283"},{"key":"e_1_3_2_2_24_1","volume-title":"NWT: Towards natural audio-to-video generation with representation learning. CoRR","author":"Mama Rayhane","year":"2021","unstructured":"Rayhane Mama, Marc S. Tyndel, Hashiam Kadhim, Cole Clifford, and Ragavan Thurairatnam. 2021b. NWT: Towards natural audio-to-video generation with representation learning. CoRR, Vol. abs\/2106.04283 (2021). arXiv:2106.04283 https:\/\/arxiv.org\/abs\/2106.04283"},{"key":"e_1_3_2_2_25_1","unstructured":"Yongming Rao Wenliang Zhao Yansong Tang Jie Zhou Ser-Nam Lim and Jiwen Lu. 2022. HorNet: Efficient High-Order Spatial Interactions with Recursive Gated Convolutions. In NeurIPS. http:\/\/papers.nips.cc\/paper_files\/paper\/2022\/hash\/436d042b2dd81214d23ae43eb196b146-Abstract-Conference.html"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1029\/2020MS002203"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2004.1334462"},{"key":"e_1_3_2_2_28_1","volume-title":"Garnett(Eds.)","volume":"28","author":"Zhourong Chen Xingjian SHI","year":"2015","unstructured":"Xingjian SHI, Zhourong Chen, Hao Wang, Dit-Yan Yeung, Wai-kin Wong, and Wang-chun WOO. 2015. Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting. In Advances in Neural Information Processing Systems, C. Cortes, N. Lawrence, D. Lee, M. Sugiyama, and R. Garnett(Eds.), Vol. 28. Curran Associates, Inc. https:\/\/proceedings.neurips.cc\/paper\/2015\/file\/07563a3fe3bbe7e3ba84431ad9d055af-Paper.pdf"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2211.12509"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01800"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2306.11249"},{"key":"e_1_3_2_2_32_1","volume-title":"Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021","author":"Tolstikhin Ilya O.","year":"2021","unstructured":"Ilya O. Tolstikhin, Neil Houlsby, Alexander Kolesnikov, Lucas Beyer, Xiaohua Zhai, Thomas Unterthiner, Jessica Yung, Andreas Steiner, Daniel Keysers, Jakob Uszkoreit, Mario Lucic, and Alexey Dosovitskiy. 2021. MLP-Mixer: An all-MLP Architecture for Vision. In Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, December 6-14, 2021, virtual, Marc'Aurelio Ranzato, Alina Beygelzimer, Yann N. Dauphin, Percy Liang, and Jennifer Wortman Vaughan(Eds.). 24261-24272. https:\/\/proceedings.neurips.cc\/paper\/2021\/hash\/cba0a4ee5ccd02fda0fe3f9a3e7b89fe-Abstract.html"},{"key":"e_1_3_2_2_33_1","article-title":"Patches Are All You Need?","volume":"2023","author":"Trockman Asher","year":"2023","unstructured":"Asher Trockman and J. Zico Kolter. 2023. Patches Are All You Need? Trans. Mach. Learn. Res., Vol. 2023 (2023). https:\/\/openreview.net\/forum?id=rAnB7JSMXL","journal-title":"Trans. Mach. Learn. Res."},{"key":"e_1_3_2_2_34_1","volume-title":"GIVT: Generative Infinite-Vocabulary Transformers. ArXiv","author":"Tschannen Michael","year":"2023","unstructured":"Michael Tschannen, Cian Eastwood, and Fabian Mentzer. 2023. GIVT: Generative Infinite-Vocabulary Transformers. ArXiv, Vol. abs\/2312.02116 (2023). https:\/\/api.semanticscholar.org\/CorpusID:265610025"},{"key":"e_1_3_2_2_35_1","volume-title":"Neural Discrete Representation Learning. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017","author":"van den Oord A\u00e4ron","year":"2017","unstructured":"A\u00e4ron van den Oord, Oriol Vinyals, and Koray Kavukcuoglu. 2017. Neural Discrete Representation Learning. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017, Long Beach, CA, USA, Isabelle Guyon, Ulrike von Luxburg, Samy Bengio, Hanna M. Wallach, Rob Fergus, S. V. N. Vishwanathan, and Roman Garnett(Eds.). 6306-6315. https:\/\/proceedings.neurips.cc\/paper\/2017\/hash\/7a98af17e63a0ac09ce2e96d03992fbc-Abstract.html"},{"key":"e_1_3_2_2_36_1","volume-title":"Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stockholmsm\u00e4ssan","author":"Wang Yunbo","year":"2018","unstructured":"Yunbo Wang, Zhifeng Gao, Mingsheng Long, Jianmin Wang, and Philip S. Yu. 2018. PredRNN: Towards A Resolution of the Deep-in-Time Dilemma in Spatiotemporal Predictive Learning. In Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stockholmsm\u00e4ssan, Stockholm, Sweden, July 10-15, 2018(Proceedings of Machine Learning Research, Vol. 80), Jennifer G. Dy and Andreas Krause(Eds.). PMLR, 5110-5119. http:\/\/proceedings.mlr.press\/v80\/wang18b.html"},{"key":"e_1_3_2_2_37_1","volume-title":"7th International Conference on Learning Representations, ICLR 2019","author":"Wang Yunbo","year":"2019","unstructured":"Yunbo Wang, Lu Jiang, Ming-Hsuan Yang, Li-Jia Li, Mingsheng Long, and Li Fei-Fei. 2019a. Eidetic 3D LSTM: A Model for Video Prediction and Beyond. In 7th International Conference on Learning Representations, ICLR 2019, New Orleans, LA, USA, May 6-9, 2019. OpenReview.net. https:\/\/openreview.net\/forum?id=B1lKS2AqtX"},{"key":"e_1_3_2_2_38_1","volume-title":"Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017","author":"Wang Yunbo","year":"2017","unstructured":"Yunbo Wang, Mingsheng Long, Jianmin Wang, Zhifeng Gao, and Philip S. Yu. 2017. PredRNN: Recurrent Neural Networks for Predictive Learning using Spatiotemporal LSTMs. In Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems 2017, December 4-9, 2017, Long Beach, CA, USA, Isabelle Guyon, Ulrike von Luxburg, Samy Bengio, Hanna M. Wallach, Rob Fergus, S. V. N. Vishwanathan, and Roman Garnett(Eds.). 879-888. https:\/\/proceedings.neurips.cc\/paper\/2017\/hash\/e5f6ad6ce374177eef023bf5d0c018b6-Abstract.html"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3165153"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00937"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2303.16666"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2305.02765"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2310.05737"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2310.05737"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01055"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01055"},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1609\/AAAI.V31I1.10735"},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00394"}],"event":{"name":"KDD '25: The 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Toronto ON Canada","acronym":"KDD '25","sponsor":["SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGMOD ACM Special Interest Group on Management of Data"]},"container-title":["Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3711896.3736914","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T18:17:34Z","timestamp":1777573054000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3711896.3736914"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,3]]},"references-count":51,"alternative-id":["10.1145\/3711896.3736914","10.1145\/3711896"],"URL":"https:\/\/doi.org\/10.1145\/3711896.3736914","relation":{},"subject":[],"published":{"date-parts":[[2025,8,3]]},"assertion":[{"value":"2025-08-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}