{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T18:28:53Z","timestamp":1774722533424,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":53,"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"}],"funder":[{"name":"Pioneer? and ?Leading Goose? R&D Program of Zhejiang","award":["2023C01045"],"award-info":[{"award-number":["2023C01045"]}]},{"name":"Ningbo Youth Science and Technology Innovation Leading Talent Project","award":["2024QL044"],"award-info":[{"award-number":["2024QL044"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3680870","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:27Z","timestamp":1729925967000},"page":"758-767","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["PSSD-Transformer: Powerful Sparse Spike-Driven Transformer for Image Semantic Segmentation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6134-1309","authenticated-orcid":false,"given":"Hongzhi","family":"Wang","sequence":"first","affiliation":[{"name":"School of Software Technology, Zhejiang University, Ningbo, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4749-5552","authenticated-orcid":false,"given":"Xiubo","family":"Liang","sequence":"additional","affiliation":[{"name":"School of Software Technology, Zhejiang University, Ningbo, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4393-1937","authenticated-orcid":false,"given":"Tao","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Software Technology, Zhejiang University, Ningbo, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9915-9841","authenticated-orcid":false,"given":"Yue","family":"Gu","sequence":"additional","affiliation":[{"name":"School of Software Technology, Zhejiang University, Ningbo, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2709-396X","authenticated-orcid":false,"given":"Weidong","family":"Geng","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Segnet: A deep convolutional encoder-decoder architecture for image segmentation","author":"Badrinarayanan Vijay","year":"2017","unstructured":"Vijay Badrinarayanan, Alex Kendall, and Roberto Cipolla. 2017. Segnet: A deep convolutional encoder-decoder architecture for image segmentation. IEEE transactions on pattern analysis and machine intelligence 39, 12 (2017), 2481--2495."},{"key":"e_1_3_2_1_2_1","volume-title":"SpikingBERT: Distilling BERT to Train Spiking Language Models Using Implicit Differentiation. arXiv preprint arXiv:2308.10873","author":"Bal Malyaban","year":"2023","unstructured":"Malyaban Bal and Abhronil Sengupta. 2023. SpikingBERT: Distilling BERT to Train Spiking Language Models Using Implicit Differentiation. arXiv preprint arXiv:2308.10873 (2023)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/82.842110"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19874"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0788-3"},{"key":"e_1_3_2_1_7_1","volume-title":"Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs","author":"Chen Liang-Chieh","year":"2017","unstructured":"Liang-Chieh Chen, George Papandreou, Iasonas Kokkinos, Kevin Murphy, and Alan L Yuille. 2017. Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE transactions on pattern analysis and machine intelligence 40, 4 (2017), 834--848."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2018.112130359"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2018.112130359"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2021.3067593"},{"key":"e_1_3_2_1_12_1","volume-title":"Theoretical neuroscience: computational and mathematical modeling of neural systems","author":"Dayan Peter","unstructured":"Peter Dayan and Laurence F Abbott. 2005. Theoretical neuroscience: computational and mathematical modeling of neural systems. MIT press."},{"key":"e_1_3_2_1_13_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly et al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_1_14_1","volume-title":"Machine learning for medical imaging. radiographics 37, 2","author":"Erickson Bradley J","year":"2017","unstructured":"Bradley J Erickson, Panagiotis Korfiatis, Zeynettin Akkus, and Timothy L Kline. 2017. Machine learning for medical imaging. radiographics 37, 2 (2017), 505--515."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1088\/1741-2560\/13\/5\/051001"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.11.118"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3154443"},{"key":"e_1_3_2_1_18_1","volume-title":"Interlaced sparse self-attention for semantic segmentation. arXiv preprint arXiv:1907.12273","author":"Huang Lang","year":"2019","unstructured":"Lang Huang, Yuhui Yuan, Jianyuan Guo, Chao Zhang, Xilin Chen, and Jingdong Wang. 2019. Interlaced sparse self-attention for semantic segmentation. arXiv preprint arXiv:1907.12273 (2019)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00141"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6787"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207075"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9892262"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"crossref","unstructured":"Jesse Levinson Jake Askeland Jan Becker Jennifer Dolson David Held Soeren Kammel J Zico Kolter Dirk Langer Oliver Pink Vaughan Pratt et al. 2011. Towards fully autonomous driving: Systems and algorithms. In 2011 IEEE intelligent vehicles symposium (IV). IEEE 163--168.","DOI":"10.1109\/IVS.2011.5940562"},{"key":"e_1_3_2_1_24_1","volume-title":"International conference on machine learning. PMLR, 6316--6325","author":"Li Yuhang","year":"2021","unstructured":"Yuhang Li, Shikuang Deng, Xin Dong, Ruihao Gong, and Shi Gu. 2021. A free lunch from ANN: Towards efficient, accurate spiking neural networks calibration. In International conference on machine learning. PMLR, 6316--6325."},{"key":"e_1_3_2_1_25_1","volume-title":"Spike calibration: Fast and accurate conversion of spiking neural network for object detection and segmentation. arXiv preprint arXiv:2207.02702","author":"Li Yang","year":"2022","unstructured":"Yang Li, Xiang He, Yiting Dong, Qingqun Kong, and Yi Zeng. 2022. Spike calibration: Fast and accurate conversion of spiking neural network for object detection and segmentation. arXiv preprint arXiv:2207.02702 (2022)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42254-020-0208-2"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"crossref","unstructured":"Paul A Merolla John V Arthur Rodrigo Alvarez-Icaza Andrew S Cassidy Jun Sawada Filipp Akopyan Bryan L Jackson Nabil Imam Chen Guo Yutaka Nakamura et al. 2014. A million spiking-neuron integrated circuit with a scalable communication network and interface. Science 345 6197 (2014) 668--673.","DOI":"10.1126\/science.1254642"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.01.005"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2019.2931595"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"crossref","unstructured":"Jing Pei Lei Deng Sen Song Mingguo Zhao Youhui Zhang Shuang Wu Guanrui Wang Zhe Zou Zhenzhi Wu Wei He et al. 2019. Towards artificial general intelligence with hybrid Tianjic chip architecture. Nature 572 7767 (2019) 106--111.","DOI":"10.1038\/s41586-019-1424-8"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2017.2750080"},{"key":"e_1_3_2_1_33_1","volume-title":"A survey of neuromorphic computing and neural networks in hardware. arXiv preprint arXiv:1705.06963","author":"Schuman Catherine D","year":"2017","unstructured":"Catherine D Schuman, Thomas E Potok, Robert M Patton, J Douglas Birdwell, Mark E Dean, Garrett S Rose, and James S Plank. 2017. A survey of neuromorphic computing and neural networks in hardware. arXiv preprint arXiv:1705.06963 (2017)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"e_1_3_2_1_35_1","volume-title":"2011 IEEE Custom Integrated Circuits Conference (CICC). IEEE, 1--4.","author":"Brezzo Bernard","year":"2011","unstructured":"Jae-sun Seo, Bernard Brezzo, Yong Liu, Benjamin D Parker, Steven K Esser, Robert K Montoye, Bipin Rajendran, Jos\u00e9 A Tierno, Leland Chang, Dharmendra S Modha, et al. 2011. A 45nm CMOS neuromorphic chip with a scalable architecture for learning in networks of spiking neurons. In 2011 IEEE Custom Integrated Circuits Conference (CICC). IEEE, 1--4."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i1.27817"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"e_1_3_2_1_38_1","volume-title":"Deep Directly-Trained Spiking Neural Networks for Object Detection. arXiv preprint arXiv:2307.11411","author":"Su Qiaoyi","year":"2023","unstructured":"Qiaoyi Su, Yuhong Chou, Yifan Hu, Jianing Li, Shijie Mei, Ziyang Zhang, and Guoqi Li. 2023. Deep Directly-Trained Spiking Neural Networks for Object Detection. arXiv preprint arXiv:2307.11411 (2023)."},{"key":"e_1_3_2_1_39_1","volume-title":"Overview of deep learning in medical imaging. Radiological physics and technology 10, 3","author":"Suzuki Kenji","year":"2017","unstructured":"Kenji Suzuki. 2017. Overview of deep learning in medical imaging. Radiological physics and technology 10, 3 (2017), 257--273."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41928-018-0103-3"},{"key":"e_1_3_2_1_41_1","volume-title":"Spiking GATs: Learning Graph Attentions via Spiking Neural Network. arXiv preprint arXiv:2209.13539","author":"Wang Beibei","year":"2022","unstructured":"Beibei Wang and Bo Jiang. 2022. Spiking GATs: Learning Graph Attentions via Spiking Neural Network. arXiv preprint arXiv:2209.13539 (2022)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"crossref","unstructured":"Panqu Wang Pengfei Chen Ye Yuan Ding Liu Zehua Huang Xiaodi Hou and Garrison Cottrell. 2018. Understanding convolution for semantic segmentation. In 2018 IEEE winter conference on applications of computer vision (WACV). Ieee 1451--1460.","DOI":"10.1109\/WACV.2018.00163"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"e_1_3_2_1_44_1","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume":"34","author":"Xie Enze","year":"2021","unstructured":"Enze Xie, Wenhai Wang, Zhiding Yu, Anima Anandkumar, Jose M Alvarez, and Ping Luo. 2021. SegFormer: Simple and efficient design for semantic segmentation with transformers. Advances in Neural Information Processing Systems 34 (2021), 12077--12090.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00762"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3232106"},{"key":"e_1_3_2_1_47_1","volume-title":"arXiv preprint arXiv:2307.01694","author":"Yao Man","year":"2023","unstructured":"Man Yao, Jiakui Hu, Zhaokun Zhou, Li Yuan, Yonghong Tian, Bo Xu, and Guoqi Li. 2023. Spike-driven Transformer. arXiv preprint arXiv:2307.01694 (2023)."},{"key":"e_1_3_2_1_48_1","volume-title":"A survey of autonomous driving: Common practices and emerging technologies","author":"Yurtsever Ekim","year":"2020","unstructured":"Ekim Yurtsever, Jacob Lambert, Alexander Carballo, and Kazuya Takeda. 2020. A survey of autonomous driving: Common practices and emerging technologies. IEEE access 8 (2020), 58443--58469."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00747"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"e_1_3_2_1_51_1","volume-title":"Spikformer: When spiking neural network meets transformer. arXiv preprint arXiv:2209.15425","author":"Zhou Zhaokun","year":"2022","unstructured":"Zhaokun Zhou, Yuesheng Zhu, Chao He, YaoweiWang, Shuicheng Yan, Yonghong Tian, and Li Yuan. 2022. Spikformer: When spiking neural network meets transformer. arXiv preprint arXiv:2209.15425 (2022)."},{"key":"e_1_3_2_1_52_1","volume-title":"Spikegpt: Generative pre-trained language model with spiking neural networks. arXiv preprint arXiv:2302.13939","author":"Zhu Rui-Jie","year":"2023","unstructured":"Rui-Jie Zhu, Qihang Zhao, and Jason K Eshraghian. 2023. Spikegpt: Generative pre-trained language model with spiking neural networks. arXiv preprint arXiv:2302.13939 (2023)."},{"key":"e_1_3_2_1_53_1","volume-title":"Spiking graph convolutional networks. arXiv preprint arXiv:2205.02767","author":"Zhu Zulun","year":"2022","unstructured":"Zulun Zhu, Jiaying Peng, Jintang Li, Liang Chen, Qi Yu, and Siqiang Luo. 2022. Spiking graph convolutional networks. arXiv preprint arXiv:2205.02767 (2022)."}],"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\/3664647.3680870","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3680870","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:08Z","timestamp":1750295888000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680870"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":53,"alternative-id":["10.1145\/3664647.3680870","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3680870","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"}}]}}