{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T14:55:28Z","timestamp":1782312928710,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":45,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2021YFF0900500, 2020YFA0714001"],"award-info":[{"award-number":["2021YFF0900500, 2020YFA0714001"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100017052","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U22B2035, 62272128, 62206141, 62236009, 62131005, 12171072, 61825101 and 62027804"],"award-info":[{"award-number":["U22B2035, 62272128, 62206141, 62236009, 62131005, 12171072, 61825101 and 62027804"]}],"id":[{"id":"10.13039\/100017052","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Open Research Fund Program of Data Recovery Key Laboratory of Sichuan Province","award":["DRN2302"],"award-info":[{"award-number":["DRN2302"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3611759","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:40Z","timestamp":1698391660000},"page":"3994-4002","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":20,"title":["Motion-Decoupled Spiking Transformer for Audio-Visual Zero-Shot Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2393-9016","authenticated-orcid":false,"given":"Wenrui","family":"Li","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6540-946X","authenticated-orcid":false,"given":"Xi-Le","family":"Zhao","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Sichuan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0799-440X","authenticated-orcid":false,"given":"Zhengyu","family":"Ma","sequence":"additional","affiliation":[{"name":"Peng Cheng Laboratory, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5763-2493","authenticated-orcid":false,"given":"Xingtao","family":"Wang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9660-3636","authenticated-orcid":false,"given":"Xiaopeng","family":"Fan","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Harbin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2978-5935","authenticated-orcid":false,"given":"Yonghong","family":"Tian","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00313"},{"key":"e_1_3_2_1_2_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Mercea Otniel-Bogdan","year":"2022","unstructured":"Otniel-Bogdan Mercea, Lukas Riesch, A Koepke, and Zeynep Akata. Audio-visual generalised zero-shot learning with cross-modal attention and language. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20044-1_28"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i11.17215"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00466"},{"key":"e_1_3_2_1_6_1","volume-title":"European Conference on Computer Vision (ECCV).","author":"Chen Zhuangzhuang","unstructured":"Zhuangzhuang Chen, Jin Zhang, Pan Wang, Jie Chen, and Jianqiang Li. When active learning meets implicit semantic data augmentation. In European Conference on Computer Vision (ECCV)."},{"key":"e_1_3_2_1_7_1","volume":"201","author":"Li Jianqiang","unstructured":"Jianqiang Li, Zhuang-Zhuang Chen, Luxiang Huang, Min Fang, Bing Li, Xianghua Fu, Huihui Wang, and Qingguo Zhao. Automatic classification of fetal heart rate based on convolutional neural network. IEEE Internet of Things Journal, 2019.","journal-title":"Things Journal"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2019.2962086"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58542-6_29"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00844"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00450"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00581"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00111"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00994"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.473"},{"key":"e_1_3_2_1_16_1","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV) Workshops","author":"Roitberg Alina","year":"2018","unstructured":"Alina Roitberg, Manuel Martinez, Monica Haurilet, and Rainer Stiefelhagen. Towards a fair evaluation of zero-shot action recognition using external data. In Proceedings of the European Conference on Computer Vision (ECCV) Workshops, 2018."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00467"},{"key":"e_1_3_2_1_18_1","volume-title":"Pattern Recognition: 43rd DAGM German Conference (DAGM GCPR)","author":"Gowda Shreyank N","year":"2022","unstructured":"Shreyank N Gowda, Laura Sevilla-Lara, Kiyoon Kim, Frank Keller, and Marcus Rohrbach. A new split for evaluating true zero-shot action recognition. In Pattern Recognition: 43rd DAGM German Conference (DAGM GCPR), 2022."},{"key":"e_1_3_2_1_19_1","volume-title":"Action2vec: A crossmodal embedding approach to action learning. arXiv preprint arXiv:1901.00484","author":"Hahn Meera","year":"2019","unstructured":"Meera Hahn, Andrew Silva, and James M Rehg. Action2vec: A crossmodal embedding approach to action learning. arXiv preprint arXiv:1901.00484, 2019."},{"key":"e_1_3_2_1_20_1","volume-title":"International conference on machine learning (ICML)","author":"Romera-Paredes Bernardino","year":"2015","unstructured":"Bernardino Romera-Paredes and Philip Torr. An embarrassingly simple approach to zero-shot learning. In International conference on machine learning (ICML), 2015."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414994"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3065234"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"e_1_3_2_1_24_1","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Aytar Yusuf","year":"2016","unstructured":"Yusuf Aytar, Carl Vondrick, and Antonio Torralba. Soundnet: Learning sound representations from unlabeled video. Advances in Neural Information Processing Systems (NeurIPS), 2016."},{"key":"e_1_3_2_1_25_1","volume-title":"Andrew Senior, Oriol Vinyals, and Andrew Zisserman. Deep audio-visual speech recognition","author":"Afouras Triantafyllos","year":"2018","unstructured":"Triantafyllos Afouras, Joon Son Chung, Andrew Senior, Oriol Vinyals, and Andrew Zisserman. Deep audio-visual speech recognition. IEEE transactions on pattern analysis and machine intelligence (TPAMI), 2018."},{"key":"e_1_3_2_1_26_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Rebecq Henri","year":"2019","unstructured":"Henri Rebecq, Rene Ranftl, Vladlen Koltun, and Davide Scaramuzza. Events-to-video: Bringing modern computer vision to event cameras. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2963386"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"crossref","unstructured":"Jacques Kaiser J. Camilo Vasquez Tieck Christian Hubschneider Peter Wolf Michael Weber Michael Hoff Alexander Friedrich Konrad Wojtasik Arne Roennau Ralf Kohlhaas R\u00fcdiger Dillmann and J. Marius Z\u00f6llner. Towards a framework for end-to-end control of a simulated vehicle with spiking neural networks. In IEEE International Conference on Simulation Modeling and Programming for Autonomous Robots (SIMPAR) 2016.","DOI":"10.1109\/SIMPAR.2016.7862386"},{"key":"e_1_3_2_1_29_1","volume-title":"Proceedings of The 2nd Conference on Robot Learning, Proceedings of Machine Learning Research (PMLR)","author":"Rebecq Henri","year":"2018","unstructured":"Henri Rebecq, Daniel Gehrig, and Davide Scaramuzza. Esim: an open event camera simulator. In Proceedings of The 2nd Conference on Robot Learning, Proceedings of Machine Learning Research (PMLR), 2018."},{"key":"e_1_3_2_1_30_1","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Fang Wei","year":"2021","unstructured":"Wei Fang, Zhaofei Yu, Yanqi Chen, Tiejun Huang, Timoth\u00e9e Masquelier, and Yonghong Tian. Deep residual learning in spiking neural networks. In Advances in Neural Information Processing Systems (NeurIPS), 2021."},{"key":"e_1_3_2_1_31_1","volume-title":"International Conference on Machine Learning (ICML)","author":"Chen Yanqi","year":"2022","unstructured":"Yanqi Chen, Zhaofei Yu, Wei Fang, Zhengyu Ma, Tiejun Huang, and Yonghong Tian. State transition of dendritic spines improves learning of sparse spiking neural networks. In International Conference on Machine Learning (ICML), 2022."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/236"},{"key":"e_1_3_2_1_33_1","volume-title":"Deep spiking neural networks with high representation similarity model visual pathways of macaque and mouse. arXiv preprint arXiv:2303.06060","author":"Huang Liwei","year":"2023","unstructured":"Liwei Huang, Zhengyu Ma, Liutao Yu, Huihui Zhou, and Yonghong Tian. Deep spiking neural networks with high representation similarity model visual pathways of macaque and mouse. arXiv preprint arXiv:2303.06060, 2023."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00266"},{"key":"e_1_3_2_1_35_1","volume-title":"Neuron-based spiking transmission and reasoning network for robust image-text retrieval","author":"Li Wenrui","year":"2022","unstructured":"Wenrui Li, Zhengyu Ma, Liang-Jian Deng, Xiaopeng Fan, and Yonghong Tian. Neuron-based spiking transmission and reasoning network for robust image-text retrieval. IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2022."},{"key":"e_1_3_2_1_36_1","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Asano Yuki","year":"2020","unstructured":"Yuki Asano, Mandela Patrick, Christian Rupprecht, and Andrea Vedaldi. Labelling unlabelled videos from scratch with multi-modal self-supervision. Advances in Neural Information Processing Systems (NeurIPS), 2020."},{"key":"e_1_3_2_1_37_1","volume-title":"Frontiers in Neuroscience","author":"Lee Jun Haeng","year":"2016","unstructured":"Jun Haeng Lee, Tobi Delbruck, and Michael Pfeiffer. Training deep spiking neural networks using backpropagation. Frontiers in Neuroscience, 2016."},{"key":"e_1_3_2_1_38_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Akata Zeynep","year":"2015","unstructured":"Zeynep Akata, Scott Reed, Daniel Walter, Honglak Lee, and Bernt Schiele. Evalu- ation of output embeddings for fine-grained image classification. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2015."},{"key":"e_1_3_2_1_39_1","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Frome Andrea","year":"2013","unstructured":"Andrea Frome, Greg S Corrado, Jon Shlens, Samy Bengio, Jeff Dean, Marc'Aurelio Ranzato, and Tomas Mikolov. Devise: A deep visual-semantic embedding model. Advances in Neural Information Processing Systems (NeurIPS), 2013."},{"key":"e_1_3_2_1_40_1","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Xu Wenjia","year":"2020","unstructured":"Wenjia Xu, Yongqin Xian, Jiuniu Wang, Bernt Schiele, and Zeynep Akata. Attribute prototype network for zero-shot learning. Advances in Neural Information Processing Systems (NeurIPS), 2020."},{"key":"e_1_3_2_1_41_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Xian Yongqin","year":"2019","unstructured":"Yongqin Xian, Saurabh Sharma, Bernt Schiele, and Zeynep Akata. f-vaegan-d2: A feature generating framework for any-shot learning. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2019."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093438"},{"key":"e_1_3_2_1_43_1","volume-title":"Zero-shot learning-a comprehensive evaluation of the good, the bad and the ugly","author":"Xian Yongqin","year":"2018","unstructured":"Yongqin Xian, Christoph H Lampert, Bernt Schiele, and Zeynep Akata. Zero-shot learning-a comprehensive evaluation of the good, the bad and the ugly. IEEE transactions on pattern analysis and machine intelligence, 2018."},{"key":"e_1_3_2_1_44_1","volume-title":"Amir Roshan Zamir, and Mubarak Shah. Ucf101: A dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402","author":"Soomro Khurram","year":"2012","unstructured":"Khurram Soomro, Amir Roshan Zamir, and Mubarak Shah. Ucf101: A dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402, 2012."},{"key":"e_1_3_2_1_45_1","volume-title":"IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"Chen Honglie","year":"2020","unstructured":"Honglie Chen, Weidi Xie, Andrea Vedaldi, and Andrew Zisserman. Vggsound: A large-scale audio-visual dataset. In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020."}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","location":"Ottawa ON Canada","acronym":"MM '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611759","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3611759","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:14:25Z","timestamp":1755821665000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611759"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":45,"alternative-id":["10.1145\/3581783.3611759","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3611759","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}