{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,27]],"date-time":"2026-10-27T18:06:44Z","timestamp":1793124404763,"version":"4.5.0"},"reference-count":92,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1007\/s11263-026-02936-7","type":"journal-article","created":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T07:31:09Z","timestamp":1785569469000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Human Activity Recognition using RGB-DVS Cameras: A Multi-modal Heat Conduction Model and A Benchmark Dataset"],"prefix":"10.1007","volume":"134","author":[{"given":"Shiao","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6117-6745","authenticated-orcid":false,"given":"Xiao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lin","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guoqi","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yaowei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yonghong","family":"Tian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jin","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,1]]},"reference":[{"key":"2936_CR1","doi-asserted-by":"crossref","unstructured":"Ahmad, T., Jin, L., Zhang, X., Lai, S., Tang, G., & Lin, L. (2021). Graph convolutional neural network for human action recognition: A comprehensive survey. IEEE Transactions on Artificial Intelligence,2(2), 128\u2013145.","DOI":"10.1109\/TAI.2021.3076974"},{"key":"2936_CR2","doi-asserted-by":"crossref","unstructured":"Amir, A., Taba, B., Berg, D., Melano, T., McKinstry, J., Di\u00a0Nolfo, C., Nayak, T., Andreopoulos, A., Garreau, G., & Mendoza, M.(2017). A low power, fully event-based gesture recognition system. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7243\u20137252","DOI":"10.1109\/CVPR.2017.781"},{"key":"2936_CR3","unstructured":"Bertasius, G., Wang, H., & Torresani, L.(2021). Is space-time attention all you need for video understanding? In: ICML, vol. 2, p. 4"},{"key":"2936_CR4","doi-asserted-by":"publisher","first-page":"9084","DOI":"10.1109\/TIP.2020.3023597","volume":"29","author":"Y Bi","year":"2020","unstructured":"Bi, Y., Chadha, A., Abbas, A., Bourtsoulatze, E., & Andreopoulos, Y. (2020). Graph-based spatio-temporal feature learning for neuromorphic vision sensing. IEEE Transactions on Image Processing, 29, 9084\u20139098.","journal-title":"IEEE Transactions on Image Processing"},{"issue":"10","key":"2936_CR5","doi-asserted-by":"publisher","first-page":"2333","DOI":"10.1109\/JSSC.2014.2342715","volume":"49","author":"C Brandli","year":"2014","unstructured":"Brandli, C., Berner, R., Yang, M., Liu, S.-C., & Delbruck, T. (2014). A 240$$\\times $$ 180 130 db 3 $$\\mu $$s latency global shutter spatiotemporal vision sensor. IEEE Journal of Solid-State Circuits, 49(10), 2333\u20132341.","journal-title":"IEEE Journal of Solid-State Circuits"},{"key":"2936_CR6","doi-asserted-by":"crossref","unstructured":"Caba Heilbron, F., Escorcia, V., Ghanem, B., & Carlos Niebles, J. (2015). Activitynet: A large-scale video benchmark for human activity understanding. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 961\u2013970)","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"2936_CR7","doi-asserted-by":"crossref","unstructured":"Cai, H., Li, J., Hu, M., Gan, C., & Han, S. (2022). Efficientvit: Multi-scale linear attention for high-resolution dense prediction. Preprint arXiv:2205.14756.","DOI":"10.1109\/ICCV51070.2023.01587"},{"key":"2936_CR8","doi-asserted-by":"crossref","unstructured":"Cannici, M., Plizzari, C., Planamente, M., Ciccone, M., Bottino, A., Caputo, B., & Matteucci, M. (2021). N-rod: A neuromorphic dataset for synthetic-to-real domain adaptation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (pp. 1342\u20131347)","DOI":"10.1109\/CVPRW53098.2021.00148"},{"key":"2936_CR9","unstructured":"Carreira, J., Noland, E., Hillier, C., & Zisserman, A. (2019). A short note on the kinetics-700 human action dataset arXiv:1907.06987 arXiv preprint."},{"key":"2936_CR10","unstructured":"Chen, Y., Dai, X., Chen, D., Liu, M., Yuan, L., Liu, Z., & Lin, Y.(2022). Self-supervised learning based on heat equation. preprint arXiv:2211.13228"},{"key":"2936_CR11","doi-asserted-by":"crossref","unstructured":"Chen, S., & Guo, M. (2019). Live demonstration: Celex-v: a 1m pixel multi-mode event-based sensor. IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (pp. 1682\u20131683). IEEE.","DOI":"10.1109\/CVPRW.2019.00214"},{"key":"2936_CR12","doi-asserted-by":"publisher","first-page":"276","DOI":"10.1109\/TCI.2019.2948755","volume":"6","author":"H Chen","year":"2019","unstructured":"Chen, H., Liu, W., Goel, R., Lua, R. C., Mittal, S., Huang, Y., Veeraraghavan, A., & Patel, A. B. (2019). Fast retinomorphic event-driven representations for video gameplay and action recognition. IEEE Transactions on Computational Imaging, 6, 276\u2013290.","journal-title":"IEEE Transactions on Computational Imaging"},{"key":"2936_CR13","doi-asserted-by":"publisher","first-page":"8926","DOI":"10.1109\/TMM.2025.3607771","volume":"27","author":"L Chen","year":"2025","unstructured":"Chen, L., Li, D., Wang, X., Shao, P., Zhang, W., Wang, Y., Tian, Y., & Tang, J. (2025). Retain, blend, and exchange: A quality-aware spatial-stereo fusion approach for event stream recognition. IEEE Transactions on Multimedia, 27, 8926\u20138939.","journal-title":"IEEE Transactions on Multimedia"},{"key":"2936_CR14","doi-asserted-by":"crossref","unstructured":"Chen, J., Meng, J., Wang, X., & Yuan, J. (2020). Dynamic graph cnn for event-camera based gesture recognition. 2020 IEEE International Symposium on Circuits and Systems (ISCAS) (pp. 1\u20135). IEEE.","DOI":"10.1109\/ISCAS45731.2020.9181247"},{"issue":"2","key":"2936_CR15","doi-asserted-by":"publisher","first-page":"508","DOI":"10.1109\/TASE.2020.3045880","volume":"18","author":"G Chen","year":"2021","unstructured":"Chen, G., Xu, Z., Li, Z., Tang, H., Qu, S., Ren, K., & Knoll, A. (2021). A novel illumination-robust hand gesture recognition system with event-based neuromorphic vision sensor. IEEE Transactions on Automation Science and Engineering, 18(2), 508\u2013520.","journal-title":"IEEE Transactions on Automation Science and Engineering"},{"issue":"4","key":"2936_CR16","first-page":"1","volume":"54","author":"K Chen","year":"2021","unstructured":"Chen, K., Zhang, D., Yao, L., Guo, B., Yu, Z., & Liu, Y. (2021). Deep learning for sensor-based human activity recognition: Overview, challenges, and opportunities. ACM Computing Surveys (CSUR), 54(4), 1\u201340.","journal-title":"ACM Computing Surveys (CSUR)"},{"key":"2936_CR17","unstructured":"Child, R., Gray, S., Radford, A., & Sutskever, I. (2019). Generating long sequences with sparse transformers preprint arXiv:1904.10509."},{"key":"2936_CR18","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1016\/j.cviu.2018.09.001","volume":"176","author":"G Ciocca","year":"2018","unstructured":"Ciocca, G., Napoletano, P., & Schettini, R. (2018). Cnn-based features for retrieval and classification of food images. Computer Vision and Image Understanding, 176, 70\u201377.","journal-title":"Computer Vision and Image Understanding"},{"key":"2936_CR19","doi-asserted-by":"publisher","first-page":"594","DOI":"10.3389\/fnins.2016.00594","volume":"10","author":"X Clady","year":"2017","unstructured":"Clady, X., Maro, J.-M., Barr\u00e9, S., & Benosman, R. B. (2017). A motion-based feature for event-based pattern recognition. Frontiers in neuroscience, 10, 594.","journal-title":"Frontiers in neuroscience"},{"key":"2936_CR20","doi-asserted-by":"crossref","unstructured":"Dao, T., Fu, D., Ermon, S., Rudra, A., & R\u00e9, C. (2022). Flashattention: Fast and memory-efficient exact attention with io-awareness. Advances in Neural Information Processing Systems,35, 16344\u201316359.","DOI":"10.52202\/068431-1189"},{"key":"2936_CR21","unstructured":"De Groot, S. R., & Mazur, P. (2013). Non-equilibrium Thermodynamics"},{"key":"2936_CR22","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., & Gelly, S. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. International Conference on Learning Representations"},{"key":"2936_CR23","unstructured":"Duan, Y., Wang, W., Chen, Z., Zhu, X., Lu, L., Lu, T., Qiao, Y., Li, H., Dai, J., & Wang, W.(2024). Vision-rwkv: Efficient and scalable visual perception with rwkv-like architectures. In: The Thirteenth International Conference on Learning Representations"},{"key":"2936_CR24","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C. (2020). X3d: Expanding architectures for efficient video recognition. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (pp. 203\u2013213)","DOI":"10.1109\/CVPR42600.2020.00028"},{"issue":"1","key":"2936_CR25","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1109\/TPAMI.2020.3008413","volume":"44","author":"G Gallego","year":"2020","unstructured":"Gallego, G., Delbr\u00fcck, T., Orchard, G., Bartolozzi, C., Taba, B., Censi, A., Leutenegger, S., Davison, A. J., Conradt, J., & Daniilidis, K. (2020). Event-based vision: A survey. IEEE transactions on pattern analysis and machine intelligence, 44(1), 154\u2013180.","journal-title":"IEEE transactions on pattern analysis and machine intelligence"},{"issue":"04","key":"2936_CR26","doi-asserted-by":"publisher","first-page":"295","DOI":"10.1142\/S0129065709002002","volume":"19","author":"S Ghosh-Dastidar","year":"2009","unstructured":"Ghosh-Dastidar, S., & Adeli, H. (2009). Spiking neural networks. International journal of neural systems, 19(04), 295\u2013308.","journal-title":"International journal of neural systems"},{"issue":"7","key":"2936_CR27","doi-asserted-by":"publisher","first-page":"6238","DOI":"10.1109\/TCSVT.2024.3358415","volume":"34","author":"D Guo","year":"2024","unstructured":"Guo, D., Li, K., Hu, B., Zhang, Y., & Wang, M. (2024). Benchmarking micro-action recognition: Dataset, methods, and applications. IEEE Transactions on Circuits and Systems for Video Technology, 34(7), 6238\u20136252.","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"2936_CR28","doi-asserted-by":"crossref","unstructured":"Herrmann, C., Bowen, R. S., & Zabih, R. (2020). Channel selection using gumbel softmax. European Conference on Computer Vision (pp. 241\u2013257). Springer.","DOI":"10.1007\/978-3-030-58583-9_15"},{"key":"2936_CR29","doi-asserted-by":"publisher","first-page":"8633","DOI":"10.52202\/068431-0628","volume":"35","author":"J Ho","year":"2022","unstructured":"Ho, J., Salimans, T., Gritsenko, A., Chan, W., Norouzi, M., & Fleet, D. J. (2022). Video diffusion models. Advances in Neural Information Processing Systems, 35, 8633\u20138646.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2936_CR30","doi-asserted-by":"crossref","unstructured":"Huang, Z., Huang, R., Sun, L., Zhao, C., Huang, M., & Su, S.(2022). Vefnet: An event-rgb cross modality fusion network for visual place recognition. In: 2022 IEEE International Conference on Image Processing (ICIP), pp. 2671\u20132675. IEEE","DOI":"10.1109\/ICIP46576.2022.9897492"},{"key":"2936_CR31","unstructured":"Jang, E., Gu, S., & Poole, B. (2016). Categorical reparameterization with gumbel-softmax preprint arXiv:1611.01144."},{"issue":"1","key":"2936_CR32","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1109\/TPAMI.2012.59","volume":"35","author":"S Ji","year":"2012","unstructured":"Ji, S., Xu, W., Yang, M., & Yu, K. (2012). 3d convolutional neural networks for human action recognition. IEEE transactions on pattern analysis and machine intelligence, 35(1), 221\u2013231.","journal-title":"IEEE transactions on pattern analysis and machine intelligence"},{"key":"2936_CR33","unstructured":"Katharopoulos, A., Vyas, A., Pappas, N., & Fleuret, F. (2020). Transformers are rnns: Fast autoregressive transformers with linear attention. International Conference on Machine Learning (pp. 5156\u20135165) PMLR."},{"key":"2936_CR34","unstructured":"Kayalibay, B., Jensen, G., & van\u00a0der Smagt, P.(2017). Cnn-based segmentation of medical imaging data. preprint arXiv:1701.03056"},{"key":"2936_CR35","doi-asserted-by":"crossref","unstructured":"Kim, J., Bae, J., Park, G., Zhang, D., & Kim, Y.M.(2021). N-imagenet: Towards robust, fine-grained object recognition with event cameras. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2146\u20132156","DOI":"10.1109\/ICCV48922.2021.00215"},{"issue":"3","key":"2936_CR36","doi-asserted-by":"publisher","first-page":"615","DOI":"10.1109\/TPAMI.2011.209","volume":"34","author":"O Kliper-Gross","year":"2011","unstructured":"Kliper-Gross, O., Hassner, T., & Wolf, L. (2011). The action similarity labeling challenge. IEEE Transactions on Pattern Analysis and Machine Intelligence, 34(3), 615\u2013621.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2936_CR37","unstructured":"Kong, Y., & Fu, Y. (2018). Human action recognition and prediction: A survey.Preprint arXiv:1806.11230."},{"key":"2936_CR38","doi-asserted-by":"crossref","unstructured":"Kuehne, H., Jhuang, H., Garrote, E., Poggio, T., & Serre, T. (2011). Hmdb: a large video database for human motion recognition. 2011 International Conference on Computer Vision (pp. 2556\u20132563). IEEE.","DOI":"10.1109\/ICCV.2011.6126543"},{"issue":"7","key":"2936_CR39","doi-asserted-by":"publisher","first-page":"1346","DOI":"10.1109\/TPAMI.2016.2574707","volume":"39","author":"X Lagorce","year":"2016","unstructured":"Lagorce, X., Orchard, G., Galluppi, F., Shi, B. E., & Benosman, R. B. (2016). Hots: a hierarchy of event-based time-surfaces for pattern recognition. IEEE transactions on pattern analysis and machine intelligence, 39(7), 1346\u20131359.","journal-title":"IEEE transactions on pattern analysis and machine intelligence"},{"key":"2936_CR40","doi-asserted-by":"crossref","unstructured":"Li, H., Liu, H., Ji, X., Li, G., & Shi, L. (2017). Cifar10-dvs: an event-stream dataset for object classification. Frontiers in Neuroscience,11, 309.","DOI":"10.3389\/fnins.2017.00309"},{"key":"2936_CR41","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.111080","volume":"158","author":"D Li","year":"2025","unstructured":"Li, D., Jin, J., Zhang, Y., Zhong, Y., Wu, Y., Chen, L., Wang, X., & Luo, B. (2025). Semantic-aware frame-event fusion based pattern recognition via large vision-language models. Pattern Recognition, 158, Article 111080.","journal-title":"Pattern Recognition"},{"key":"2936_CR42","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2021.726582","volume":"15","author":"Y Lin","year":"2021","unstructured":"Lin, Y., Ding, W., Qiang, S., Deng, L., & Li, G. (2021). Es-imagenet: A million event-stream classification dataset for spiking neural networks. Frontiers in neuroscience, 15, Article 726582.","journal-title":"Frontiers in neuroscience"},{"key":"2936_CR43","doi-asserted-by":"crossref","unstructured":"Lin, J., Gan, C., & Han, S. (2019). Tsm: Temporal shift module for efficient video understanding. IEEE\/CVF International Conference on Computer Vision (ICCV) (pp. 7082\u20137092)","DOI":"10.1109\/ICCV.2019.00718"},{"key":"2936_CR44","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S.,& Guo, B.(2021). Swin transformer: Hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10012\u201310022","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"2936_CR45","doi-asserted-by":"crossref","unstructured":"Liu, Y., Tian, Y., Zhao, Y., Yu, H., Xie, L., Wang, Y., Ye, Q., Jiao, J., & Liu, Y. (2024). Vmamba: Visual state space model. Advances in Neural Information Processing Systems,37, 103031\u2013103063.","DOI":"10.52202\/079017-3273"},{"issue":"2","key":"2936_CR46","doi-asserted-by":"publisher","first-page":"567","DOI":"10.1007\/s11263-024-02196-3","volume":"133","author":"C Liu","year":"2025","unstructured":"Liu, C., Dong, Y., Xiang, W., Yang, X., Su, H., Zhu, J., Chen, Y., He, Y., Xue, H., & Zheng, S. (2025). A comprehensive study on robustness of image classification models: Benchmarking and rethinking. International Journal of Computer Vision, 133(2), 567\u2013589.","journal-title":"International Journal of Computer Vision"},{"key":"2936_CR47","doi-asserted-by":"crossref","unstructured":"Liu, Z., Ning, J., Cao, Y., Wei, Y., Zhang, Z., Lin, S., & Hu, H. (2022). Video swin transformer. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (pp. 3202\u20133211)","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"2936_CR48","doi-asserted-by":"crossref","unstructured":"Liu, Z., Wang, L., Wu, W., Qian, C., & Lu, T. (2021). Tam: Temporal adaptive module for video recognition. Proceedings of the IEEE\/CVF International Conference on Computer Vision (pp. 13708\u201313718)","DOI":"10.1109\/ICCV48922.2021.01345"},{"key":"2936_CR49","doi-asserted-by":"crossref","unstructured":"Liu, Q., Xing, D., Tang, H., Ma, D., & Pan, G. (2021). Event-based action recognition using motion information and spiking neural networks. IJCAI, 1743\u20131749.","DOI":"10.24963\/ijcai.2021\/240"},{"key":"2936_CR50","doi-asserted-by":"crossref","unstructured":"Li, Y., Wu, C.-Y., Fan, H., Mangalam, K., Xiong, B., Malik, J., & Feichtenhofer, C. (2022). Mvitv 2: Improved multiscale vision transformers for classification and detection. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (pp. 4804\u20134814)","DOI":"10.1109\/CVPR52688.2022.00476"},{"key":"2936_CR51","doi-asserted-by":"crossref","unstructured":"Lu, A., Li, C., Zhao, J., Tang, J., & Luo, B.(2024). Modality-missing rgbt tracking: Invertible prompt learning and high-quality benchmarks. International Journal of Computer Vision, 1\u201321","DOI":"10.1007\/s11263-024-02311-4"},{"issue":"6","key":"2936_CR52","doi-asserted-by":"publisher","first-page":"7077","DOI":"10.1007\/s11042-018-6467-6","volume":"78","author":"N Mahmoudi","year":"2019","unstructured":"Mahmoudi, N., Ahadi, S. M., & Rahmati, M. (2019). Multi-target tracking using cnn-based features: Cnnmtt. Multimedia Tools and Applications, 78(6), 7077\u20137096.","journal-title":"Multimedia Tools and Applications"},{"key":"2936_CR53","doi-asserted-by":"crossref","unstructured":"Miao, S., Chen, G., Ning, X., Zi, Y., Ren, K., Bing, Z., & Knoll, A. (2019). Neuromorphic vision datasets for pedestrian detection, action recognition, and fall detection. Frontiers in Neurorobotics,13, 38.","DOI":"10.3389\/fnbot.2019.00038"},{"key":"2936_CR54","doi-asserted-by":"crossref","unstructured":"Orchard, G., Jayawant, A., Cohen, G. K., & Thakor, N. (2015). Converting static image datasets to spiking neuromorphic datasets using saccades. Frontiers in Neuroscience,9, 437.","DOI":"10.3389\/fnins.2015.00437"},{"key":"2936_CR55","unstructured":"Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., & Antiga, L. (2019). Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems, 32,"},{"issue":"4","key":"2936_CR56","doi-asserted-by":"publisher","first-page":"6616","DOI":"10.1109\/LRA.2021.3093870","volume":"6","author":"M Planamente","year":"2021","unstructured":"Planamente, M., Plizzari, C., Cannici, M., Ciccone, M., Strada, F., Bottino, A., Matteucci, M., & Caputo, B. (2021). Da4event: towards bridging the sim-to-real gap for event cameras using domain adaptation. IEEE Robotics and Automation Letters, 6(4), 6616\u20136623.","journal-title":"IEEE Robotics and Automation Letters"},{"issue":"1","key":"2936_CR57","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1109\/JSSC.2010.2085952","volume":"46","author":"C Posch","year":"2010","unstructured":"Posch, C., Matolin, D., & Wohlgenannt, R. (2010). A qvga 143 db dynamic range frame-free pwm image sensor with lossless pixel-level video compression and time-domain cds. IEEE Journal of Solid-State Circuits, 46(1), 259\u2013275.","journal-title":"IEEE Journal of Solid-State Circuits"},{"issue":"7","key":"2936_CR58","doi-asserted-by":"publisher","first-page":"5222","DOI":"10.1109\/TIV.2024.3350669","volume":"9","author":"PK Sarker","year":"2024","unstructured":"Sarker, P. K., Zhao, Q., & Uddin, M. K. (2024). Transformer-based person re-identification: A comprehensive review. IEEE Transactions on Intelligent Vehicles, 9(7), 5222\u20135239.","journal-title":"IEEE Transactions on Intelligent Vehicles"},{"key":"2936_CR59","doi-asserted-by":"crossref","unstructured":"Serrano-Gotarredona, T., & Linares-Barranco, B. (2015). Poker-dvs and mnist-dvs. their history, how they were made, and other details. Frontiers in Neuroscience,9, 481.","DOI":"10.3389\/fnins.2015.00481"},{"key":"2936_CR60","doi-asserted-by":"crossref","unstructured":"Sironi, A., Brambilla, M., Bourdis, N., Lagorce, X., & Benosman, R. (2018). Hats: Histograms of averaged time surfaces for robust event-based object classification. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 1731\u20131740)","DOI":"10.1109\/CVPR.2018.00186"},{"key":"2936_CR61","unstructured":"Soomro, K., Zamir, A. R., & Shah, M. (2012). Ucf101: A dataset of 101 human actions classes from videos in the wild preprint arXiv:1212.0402."},{"issue":"11","key":"2936_CR62","first-page":"1","volume":"2","author":"K Soomro","year":"2012","unstructured":"Soomro, K., Zamir, A. R., & Shah, M. (2012). A dataset of 101 human action classes from videos in the wild. Center for Research in Computer Vision, 2(11), 1\u20137.","journal-title":"Center for Research in Computer Vision"},{"key":"2936_CR63","doi-asserted-by":"crossref","unstructured":"Tavanaei, A., Ghodrati, M., Kheradpisheh, S. R., Masquelier, T., & Maida, A. (2019). Deep learning in spiking neural networks. Neural Networks,111, 47\u201363.","DOI":"10.1016\/j.neunet.2018.12.002"},{"key":"2936_CR64","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., & Paluri, M. (2015). Learning spatiotemporal features with 3d convolutional networks. Proceedings of the IEEE International Conference on Computer Vision (pp. 4489\u20134497)","DOI":"10.1109\/ICCV.2015.510"},{"issue":"7","key":"2936_CR65","doi-asserted-by":"publisher","first-page":"2264","DOI":"10.1007\/s11263-021-01467-7","volume":"129","author":"G Varol","year":"2021","unstructured":"Varol, G., Laptev, I., Schmid, C., & Zisserman, A. (2021). Synthetic humans for action recognition from unseen viewpoints. International Journal of Computer Vision, 129(7), 2264\u20132287.","journal-title":"International Journal of Computer Vision"},{"key":"2936_CR66","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., & Polosukhin, I.(2017). Attention is all you need. Advances in neural information processing systems30"},{"key":"2936_CR67","doi-asserted-by":"crossref","unstructured":"Wang, Z., Liu, Y., Tian, Y., Liu, Y., Wang, Y., & Ye, Q.(2025). Building vision models upon heat conduction. In: Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR), pp. 9707\u20139717","DOI":"10.1109\/CVPR52734.2025.00907"},{"key":"2936_CR68","doi-asserted-by":"crossref","unstructured":"Wang, X., Rong, Y., Wang, S., Chen, Y., Wu, Z., Jiang, B., Tian, Y., & Tang, J.(2025). Unleashing the power of cnn and transformer for balanced rgb-event video recognition. Machine Intelligence Research","DOI":"10.1007\/s11633-025-1555-3"},{"key":"2936_CR69","doi-asserted-by":"crossref","unstructured":"Wang, Z., She, Q., & Smolic, A. (2021). Action-net: Multipath excitation for action recognition. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (pp. 13214\u201313223)","DOI":"10.1109\/CVPR46437.2021.01301"},{"key":"2936_CR70","doi-asserted-by":"crossref","unstructured":"Wang, X., Wang, S., Tang, C., Zhu, L., Jiang, B., Tian, Y., & Tang, J.(2024). Event stream-based visual object tracking: A high-resolution benchmark dataset and a novel baseline. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19248\u201319257","DOI":"10.1109\/CVPR52733.2024.01821"},{"key":"2936_CR71","doi-asserted-by":"crossref","unstructured":"Wang, X., Wu, Z., Jiang, B., Bao, Z., Zhu, L., Li, G., Wang, Y., & Tian, Y.(2024). Hardvs: Revisiting human activity recognition with dynamic vision sensors. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, pp. 5615\u20135623","DOI":"10.1609\/aaai.v38i6.28372"},{"key":"2936_CR72","doi-asserted-by":"crossref","unstructured":"Wang, X., Jin, Y., Wu, W., Zhang, W., Zhu, L., Jiang, B., & Tian, Y. (2025). Object detection using event camera: A moe heat conduction based detector and a new benchmark dataset. Proceedings of the Computer Vision and Pattern Recognition Conference (pp. 29321\u201329330)","DOI":"10.1109\/CVPR52734.2025.02730"},{"issue":"5","key":"2936_CR73","first-page":"1","volume":"20","author":"J Wang","year":"2024","unstructured":"Wang, J., Li, G., Shi, J., & Xi, J. (2024). Weighted guided optional fusion network for rgb-t salient object detection. ACM Transactions on Multimedia Computing, Communications and Applications, 20(5), 1\u201320.","journal-title":"ACM Transactions on Multimedia Computing, Communications and Applications"},{"issue":"8","key":"2936_CR74","doi-asserted-by":"publisher","first-page":"7526","DOI":"10.1109\/TCSVT.2025.3549459","volume":"35","author":"Q Wang","year":"2025","unstructured":"Wang, Q., Li, Z., Zhang, S., Chi, N., & Dai, Q. (2025). Wavefusion: A novel wavelet vision transformer with saliency-guided enhancement for multimodal image fusion. IEEE Transactions on Circuits and Systems for Video Technology, 35(8), 7526\u20137542.","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"issue":"3","key":"2936_CR75","doi-asserted-by":"publisher","first-page":"1997","DOI":"10.1109\/TCYB.2023.3318601","volume":"54","author":"X Wang","year":"2023","unstructured":"Wang, X., Li, J., Zhu, L., Zhang, Z., Chen, Z., Li, X., Wang, Y., Tian, Y., & Wu, F. (2023). Visevent: Reliable object tracking via collaboration of frame and event flows. IEEE Transactions on Cybernetics, 54(3), 1997\u20132010.","journal-title":"IEEE Transactions on Cybernetics"},{"issue":"6","key":"2936_CR76","doi-asserted-by":"publisher","first-page":"1488","DOI":"10.1109\/TCDS.2025.3568833","volume":"17","author":"X Wang","year":"2025","unstructured":"Wang, X., Rong, Y., Wu, Z., Zhu, L., Jiang, B., Tang, J., & Tian, Y. (2025). Sstformer: Bridging spiking neural network and memory support transformer for frame-event based-recognition. IEEE Transactions on Cognitive and Developmental Systems, 17(6), 1488\u20131502.","journal-title":"IEEE Transactions on Cognitive and Developmental Systems"},{"key":"2936_CR77","doi-asserted-by":"crossref","unstructured":"Wang, Q., Xu, Z., Lin, Y., Ye, J., Li, H., Zhu, G., Shah, A., Bennamoun, S. A., Zhang, M., & L. (2024). Dailydvs-200: A comprehensive benchmark dataset for event-based action recognition. European Conference on Computer Vision (pp. 55\u201372)","DOI":"10.1007\/978-3-031-72907-2_4"},{"key":"2936_CR78","doi-asserted-by":"publisher","first-page":"6490","DOI":"10.1109\/TIP.2025.3611602","volume":"34","author":"L Wang","year":"2025","unstructured":"Wang, L., Zhang, X., Jia, C., & Ma, S. (2025). Mafs: Masked autoencoder for infrared-visible image fusion and semantic segmentation. IEEE Transactions on Image Processing, 34, 6490\u20136505.","journal-title":"IEEE Transactions on Image Processing"},{"issue":"7","key":"2936_CR79","first-page":"3436","volume":"44","author":"Y Wang","year":"2021","unstructured":"Wang, Y., Zhang, X., Shen, Y., Du, B., Zhao, G., Cui, L., & Wen, H. (2021). Event-stream representation for human gaits identification using deep neural networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(7), 3436\u20133449.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"2936_CR80","doi-asserted-by":"crossref","unstructured":"Wang, Q., Zhang, Y., Yuan, J., & Lu, Y. (2019). Space-time event clouds for gesture recognition: From rgb cameras to event cameras. 2019 IEEE Winter Conference on Applications of Computer Vision (WACV) (pp. 1826\u20131835). IEEE.","DOI":"10.1109\/WACV.2019.00199"},{"key":"2936_CR81","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108220","volume":"121","author":"X Wang","year":"2022","unstructured":"Wang, X., Zheng, S., Yang, R., Zheng, A., Chen, Z., Tang, J., & Luo, B. (2022). Pedestrian attribute recognition: A survey. Pattern Recognition, 121, Article 108220.","journal-title":"Pattern Recognition"},{"key":"2936_CR82","doi-asserted-by":"crossref","unstructured":"Wu, X., & Yuan, J. (2020). Multipath event-based network for low-power human action recognition. 2020 IEEE 6th World Forum on Internet of Things (WF-IoT) (pp. 1\u20135). IEEE.","DOI":"10.1109\/WF-IoT48130.2020.9221355"},{"key":"2936_CR83","doi-asserted-by":"crossref","unstructured":"Xiao, B., Shi, D., Bi, X., Li, W., & Gao, X. (2024). Cs-colbp: Cross-scale co-occurrence local binary pattern for image classification. International Journal of Computer Vision, 1\u201318.","DOI":"10.1007\/s11263-024-02297-z"},{"key":"2936_CR84","doi-asserted-by":"publisher","first-page":"1143","DOI":"10.3389\/fnins.2020.590164","volume":"14","author":"Y Xing","year":"2020","unstructured":"Xing, Y., Di Caterina, G., & Soraghan, J. (2020). A new spiking convolutional recurrent neural network (scrnn) with applications to event-based hand gesture recognition. Frontiers in Neuroscience, 14, 1143.","journal-title":"Frontiers in Neuroscience"},{"issue":"2","key":"2936_CR85","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3696415","volume":"57","author":"Z Xing","year":"2024","unstructured":"Xing, Z., Feng, Q., Chen, H., Dai, Q., Hu, H., Xu, H., Wu, Z., & Jiang, Y.-G. (2024). A survey on video diffusion models. ACM Computing Surveys, 57(2), 1\u201342.","journal-title":"ACM Computing Surveys"},{"issue":"7","key":"2936_CR86","doi-asserted-by":"publisher","first-page":"863","DOI":"10.3390\/brainsci12070863","volume":"12","author":"K Yamazaki","year":"2022","unstructured":"Yamazaki, K., Vo-Ho, V.-K., Bulsara, D., & Le, N. (2022). Spiking neural networks and their applications: A review. Brain Sciences, 12(7), 863.","journal-title":"Brain Sciences"},{"key":"2936_CR87","doi-asserted-by":"crossref","unstructured":"Yao, B., Jiang, X., Khosla, A., Lin, A. L., Guibas, L., & Fei-Fei, L. (2011). Human action recognition by learning bases of action attributes and parts. 2011 International Conference on Computer Vision (pp. 1331\u20131338). IEEE.","DOI":"10.1109\/ICCV.2011.6126386"},{"key":"2936_CR88","doi-asserted-by":"crossref","unstructured":"Yuan, C., Jin, Y., Wu, Z., Wei, F., Wang, Y., Chen, L., & Wang, X.(2023). Learning bottleneck transformer for event image-voxel feature fusion based classification. In: Chinese Conference on Pattern Recognition and Computer Vision (PRCV), pp. 3\u201315. Springer","DOI":"10.1007\/978-981-99-8429-9_1"},{"key":"2936_CR89","unstructured":"Zhang, X., Chen, Z., Zhang, J., Liu, T., & Tao, D.(2024). Learning general and specific embedding with transformer for few-shot object detection. International Journal of Computer Vision, 1\u201317"},{"issue":"5","key":"2936_CR90","doi-asserted-by":"publisher","first-page":"1005","DOI":"10.3390\/s19051005","volume":"19","author":"H-B Zhang","year":"2019","unstructured":"Zhang, H.-B., Zhang, Y.-X., Zhong, B., Lei, Q., Yang, L., Du, J.-X., & Chen, D.-S. (2019). A comprehensive survey of vision-based human action recognition methods. Sensors, 19(5), 1005.","journal-title":"Sensors"},{"key":"2936_CR91","doi-asserted-by":"crossref","unstructured":"Zhong, H., Tang, F., Chen, Z., Chang, H. J., & Gao, Y. (2025). Amdanet: Attention-driven multi-perspective discrepancy alignment for rgb-infrared image fusion and segmentation. Proceedings of the IEEE\/CVF International Conference on Computer Vision (pp. 10645\u201310655)","DOI":"10.1109\/ICCV51701.2025.00991"},{"key":"2936_CR92","unstructured":"Zhu, L., Liao, B., Zhang, Q., Wang, X., Liu, W., & Wang, X.(2024). Vision mamba: Efficient visual representation learning with bidirectional state space model. In: International Conference on Machine Learning, pp. 62429\u201362442"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-026-02936-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-026-02936-7","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-026-02936-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,22]],"date-time":"2026-08-22T03:24:52Z","timestamp":1787369092000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-026-02936-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":92,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2026,8]]}},"alternative-id":["2936"],"URL":"https:\/\/doi.org\/10.1007\/s11263-026-02936-7","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"9 April 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 June 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 August 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"377"}}