{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T06:21:10Z","timestamp":1780467670734,"version":"3.54.1"},"reference-count":54,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T00:00:00Z","timestamp":1761004800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T00:00:00Z","timestamp":1761004800000},"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":["Mach. Intell. Res."],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1007\/s11633-025-1555-3","type":"journal-article","created":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T07:46:10Z","timestamp":1761032770000},"page":"1031-1047","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Unleashing the Power of CNN and Transformer for Balanced RGB-event Video Recognition"],"prefix":"10.1007","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6117-6745","authenticated-orcid":false,"given":"Xiao","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8151-5220","authenticated-orcid":false,"given":"Yao","family":"Rong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8378-8160","authenticated-orcid":false,"given":"Shiao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5344-958X","authenticated-orcid":false,"given":"Yuan","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6982-2315","authenticated-orcid":false,"given":"Zhe","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6238-1596","authenticated-orcid":false,"given":"Bo","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2978-5935","authenticated-orcid":false,"given":"Yonghong","family":"Tian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8564-6510","authenticated-orcid":false,"given":"Jin","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,10,21]]},"reference":[{"issue":"1","key":"1555_CR1","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1109\/TPAMI.2020.3008413","volume":"44","author":"G Gallego","year":"2022","unstructured":"G. Gallego, T. Delbr\u00fcck, G. Orchard, C. Bartolozzi, B. Taba, A. Censi, S. Leutenegger, A. J. Davison, J. Conradt, K. Daniilidis, D. Scaramuzza. Event-based vision: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 44, no. 1, pp. 154\u2013180, 2022. DOI: https:\/\/doi.org\/10.1109\/TPAMI.2020.3008413.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1555_CR2","doi-asserted-by":"publisher","first-page":"19248","DOI":"10.1109\/CVPR52733.2024.01821","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"X Wang","year":"2024","unstructured":"X. Wang, S. Wang, C. Tang, L. Zhu, B. Jiang, Y. Tian, J. Tang. Event stream-based visual object tracking: A high-resolution benchmark dataset and a novel baseline. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, USA, pp. 19248\u201319257, 2024. DOI: https:\/\/doi.org\/10.1109\/CVPR52733.2024.01821."},{"issue":"3","key":"1555_CR3","doi-asserted-by":"publisher","first-page":"1997","DOI":"10.1109\/TCYB.2023.3318601","volume":"54","author":"X Wang","year":"2024","unstructured":"X. Wang, J. Li, L. Zhu, Z. Zhang, Z. Chen, X. Li, Y. Wang, Y. Tian, F. Wu. VisEvent: Reliable object tracking via collaboration of frame and event flows. IEEE Transactions on Cybernetics, vol. 54, no. 3, pp. 1997\u20132010, 2024. DOI: https:\/\/doi.org\/10.1109\/TCYB.2023.3318601.","journal-title":"IEEE Transactions on Cybernetics"},{"key":"1555_CR4","doi-asserted-by":"publisher","first-page":"111080","DOI":"10.1016\/j.patcog.2024.111080","volume":"158","author":"D Li","year":"2025","unstructured":"D. Li, J. Jin, Y. Zhang, Y. Zhong, Y. Wu, L. Chen, X. Wang, B. Luo. Semantic-aware frame-event fusion based pattern recognition via large vision-language models. Pattern Recognition, vol. 158, Article number 111080, 2025. DOI: https:\/\/doi.org\/10.1016\/j.patcog.2024.111080.","journal-title":"Pattern Recognition"},{"key":"1555_CR5","doi-asserted-by":"publisher","first-page":"5615","DOI":"10.1609\/aaai.v38i6.28372","volume-title":"Proceedings of the 38th Conference on Artificial Intelligence","author":"X Wang","year":"2024","unstructured":"X. Wang, Z. Wu, B. Jiang, Z. Bao, L. Zhu, G. Li, Y. Wang, Y. Tian. HARDVS: Revisiting human activity recognition with dynamic vision sensors. In Proceedings of the 38th Conference on Artificial Intelligence, Vancouver, Canada, pp. 5615\u20135623, 2024. DOI: https:\/\/doi.org\/10.1609\/aaai.v38i6.28372."},{"key":"1555_CR6","first-page":"13884","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"M Gehrig","year":"2023","unstructured":"M. Gehrig, D. Scaramuzza. Recurrent vision transformers for object detection with event cameras. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, Canada, pp. 13884\u201313893, 2023. DOI: 10.1109\/CVPR52729.2023.01334."},{"key":"1555_CR7","doi-asserted-by":"publisher","first-page":"660","DOI":"10.1007\/978-3-031-20068-7_38","volume-title":"Proceedings of the 17th European Conference on Computer Vision","author":"M Teng","year":"2022","unstructured":"M. Teng, C. Zhou, H. Lou, B. Shi. NEST: Neural event stack for event-based image enhancement. In Proceedings of the 17th European Conference on Computer Vision, Tel Aviv, Israel, pp. 660\u2013676, 2022. DOI: https:\/\/doi.org\/10.1007\/978-3-031-20068-7_38."},{"key":"1555_CR8","doi-asserted-by":"publisher","first-page":"3594","DOI":"10.1109\/CVPR52688.2022.00358","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"L Zhu","year":"2022","unstructured":"L. Zhu, X. Wang, Y. Chang, J. Li, T. Huang, Y. Tian. Event-based video reconstruction via potential-assisted spiking neural network. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, USA, pp. 3594\u20133604, 2022. DOI: https:\/\/doi.org\/10.1109\/CVPR52688.2022.00358."},{"key":"1555_CR9","doi-asserted-by":"publisher","first-page":"1920","DOI":"10.1109\/TMM.2023.3290432","volume":"26","author":"Y Jiang","year":"2024","unstructured":"Y. Jiang, Y. Wang, S. Li, Y. Zhang, M. Zhao, Y. Gao. Event-based low-illumination image enhancement. IEEE Transactions on Multimedia, vol. 26, pp. 1920\u20131931, 2024. DOI: https:\/\/doi.org\/10.1109\/TMM.2023.3290432.","journal-title":"IEEE Transactions on Multimedia"},{"key":"1555_CR10","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1109\/TMM.2023.3260638","volume":"26","author":"S Ding","year":"2024","unstructured":"S. Ding, J. Chen, Y. Wang, Y. Kang, W. Song, J. Cheng, Y. Cao. E-MLB: Multilevel benchmark for eventbased camera denoising. IEEE Transactions on Multimedia, vol. 26, pp. 65\u201376, 2024. DOI: https:\/\/doi.org\/10.1109\/TMM.2023.3260638.","journal-title":"IEEE Transactions on Multimedia"},{"key":"1555_CR11","doi-asserted-by":"publisher","first-page":"1148","DOI":"10.1109\/TMM.2020.2993957","volume":"23","author":"J Wu","year":"2021","unstructured":"J. Wu, C. Ma, L. Li, W. Dong, G. Shi. Probabilistic undirected graph based denoising method for dynamic vision sensor. IEEE Transactions on Multimedia, vol. 23, pp. 1148\u20131159, 2021. DOI: https:\/\/doi.org\/10.1109\/TMM.2020.2993957.","journal-title":"IEEE Transactions on Multimedia"},{"key":"1555_CR12","doi-asserted-by":"publisher","first-page":"1684","DOI":"10.1109\/CVPRW.2019.00215","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops","author":"C Scheerlinck","year":"2019","unstructured":"C. Scheerlinck, H. Rebecq, T. Stoffregen, N. Barnes, R. Mahony, D. Scaramuzza. CED: Color event camera dataset. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, Long Beach, USA, pp. 1684\u20131693, 2019. DOI: https:\/\/doi.org\/10.1109\/CVPRW.2019.00215."},{"key":"1555_CR13","volume-title":"SSTFormer: Bridging spiking neural network and memory support transformer for frame-event based recognition","author":"X Wang","year":"2023","unstructured":"X. Wang, Y. Rong, Z. Wu, L. Zhu, B. Jiang, J. Tang, Y. Tian. SSTFormer: Bridging spiking neural network and memory support transformer for frame-event based recognition, [Online], Available: https:\/\/arxiv.org\/abs\/2308.04369, 2023."},{"key":"1555_CR14","doi-asserted-by":"publisher","first-page":"7772","DOI":"10.1109\/CVPR46437.2021.00768","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Y Jing","year":"2021","unstructured":"Y. Jing, Y. Yang, X. Wang, M. Song, D. Tao. Turning frequency to resolution: Video super-resolution via event cameras. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Nashville, USA, pp. 7772\u20137781, 2021. DOI: https:\/\/doi.org\/10.1109\/CVPR46437.2021.00768."},{"key":"1555_CR15","doi-asserted-by":"publisher","first-page":"7083","DOI":"10.1109\/ICCV.2019.00718","volume-title":"Proceedings of IEEE\/CVF International Conference on Computer Vision","author":"J Lin","year":"2019","unstructured":"J. Lin, C. Gan, S. Han. TSM: Temporal shift module for efficient video understanding. In Proceedings of IEEE\/CVF International Conference on Computer Vision, Seoul, Republic of Korea, pp. 7083\u20137093, 2019. DOI: https:\/\/doi.org\/10.1109\/ICCV.2019.00718."},{"key":"1555_CR16","doi-asserted-by":"publisher","first-page":"13708","DOI":"10.1109\/ICCV48922.2021.01345","volume-title":"Proceedings of IEEE\/CVF International Conference on Computer Vision","author":"Z Liu","year":"2021","unstructured":"Z. Liu, L. Wang, W. Wu, C. Qian, T. Lu. TAM: Temporal adaptive module for video recognition. In Proceedings of IEEE\/CVF International Conference on Computer Vision, Montreal, Canada, pp. 13708\u201313718, 2021. DOI: https:\/\/doi.org\/10.1109\/ICCV48922.2021.01345."},{"key":"1555_CR17","doi-asserted-by":"publisher","first-page":"3202","DOI":"10.1109\/CVPR52688.2022.00320","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Z Liu","year":"2022","unstructured":"Z. Liu, J. Ning, Y. Cao, Y. Wei, Z. Zhang, S. Lin, H. Hu. Video swin transformer. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, USA, pp. 3202\u20133211, 2022. DOI: https:\/\/doi.org\/10.1109\/CVPR52688.2022.00320."},{"key":"1555_CR18","doi-asserted-by":"publisher","first-page":"770","DOI":"10.1109\/CVPR.2016.90","volume-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition","author":"K He","year":"2016","unstructured":"K. He, X. Zhang, S. Ren, J. Sun. Deep residual learning for image recognition. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, USA, pp. 770\u2013778, 2016. DOI: https:\/\/doi.org\/10.1109\/CVPR.2016.90."},{"issue":"1","key":"1555_CR19","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1109\/TPAMI.2022.3152247","volume":"45","author":"K Han","year":"2023","unstructured":"K. Han, Y. Wang, H. Chen, X. Chen, J. Guo, Z. Liu, Y. Tang, A. Xiao, C. Xu, Y. Xu, Z. Yang, Y. Zhang, D. Tao. A survey on vision transformer. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 45, no. 1, pp. 87\u2013110, 2023. DOI: https:\/\/doi.org\/10.1109\/TPAMI.2022.3152247.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"4","key":"1555_CR20","doi-asserted-by":"publisher","first-page":"447","DOI":"10.1007\/s11633-022-1410-8","volume":"20","author":"X Wang","year":"2023","unstructured":"X. Wang, G. Chen, G. Qian, P. Gao, X. Y. Wei, Y. Wang, Y. Tian, W. Gao. Large-scale multi-modal pretrained models: A comprehensive survey. Machine Intelligence Research, vol. 20, no. 4, pp. 447\u2013482, 2023. DOI: https:\/\/doi.org\/10.1007\/s11633-022-1410-8.","journal-title":"Machine Intelligence Research"},{"key":"1555_CR21","doi-asserted-by":"publisher","first-page":"19866","DOI":"10.1109\/ICCV51070.2023.01819","volume-title":"Proceedings of IEEE\/CVF International Conference on Computer Vision","author":"H Cho","year":"2023","unstructured":"H. Cho, H. Kim, Y. Chae, K. J. Yoon. Label-free eventbased object recognition via joint learning with image reconstruction from events. In Proceedings of IEEE\/CVF International Conference on Computer Vision, Paris, France, pp. 19866\u201319877, 2023. DOI: https:\/\/doi.org\/10.1109\/ICCV51070.2023.01819."},{"key":"1555_CR22","doi-asserted-by":"publisher","first-page":"10426","DOI":"10.1109\/ICPR48806.2021.9412991","volume-title":"Proceedings of the 25th International Conference on Pattern Recognition","author":"S U. Innocenti","year":"2021","unstructured":"S. U. Innocenti, F. Becattini, F. Pernici, A. Del Bimbo. Temporal binary representation for event-based action recognition. In Proceedings of the 25th International Conference on Pattern Recognition, Milan, Italy, pp. 10426\u201310432, 2021. DOI: https:\/\/doi.org\/10.1109\/ICPR48806.2021.9412991."},{"key":"1555_CR23","doi-asserted-by":"publisher","first-page":"17745","DOI":"10.1109\/CVPR52688.2022.01722","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"J Kim","year":"2022","unstructured":"J. Kim, I. Hwang, Y. M. Kim. Ev-TTA: Test-time adaptation for event-based object recognition. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, USA, pp. 17745\u201317754, 2022. DOI: https:\/\/doi.org\/10.1109\/CVPR52688.2022.01722."},{"key":"1555_CR24","doi-asserted-by":"publisher","first-page":"1127","DOI":"10.1109\/WACV.2019.00125","volume-title":"Proceedings of IEEE Winter Conference on Applications of Computer Vision","author":"M Cannici","year":"2019","unstructured":"M. Cannici, M. Ciccone, A. Romanoni, M. Matteucci. Attention mechanisms for object recognition with eventbased cameras. In Proceedings of IEEE Winter Conference on Applications of Computer Vision, Waikoloa, USA, pp. 1127\u20131136, 2019. DOI: https:\/\/doi.org\/10.1109\/WACV.2019.00125."},{"key":"1555_CR25","doi-asserted-by":"publisher","first-page":"6351","DOI":"10.1109\/CVPR.2019.00652","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Y Wang","year":"2019","unstructured":"Y. Wang, B. Du, Y. Shen, K. Wu, G. Zhao, J. Sun, H. Wen. EV-Gait: Event-based robust gait recognition using dynamic vision sensors. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, USA, pp. 6351\u20136360, 2019. DOI: https:\/\/doi.org\/10.1109\/CVPR.2019.00652."},{"key":"1555_CR26","doi-asserted-by":"publisher","first-page":"1743","DOI":"10.24963\/ijcai.2021\/240","volume-title":"Proceedings of the 30th International Joint Conference on Artificial Intelligence","author":"Q Liu","year":"2021","unstructured":"Q. Liu, D. Xing, H. Tang, D. Ma, G. Pan. Event-based action recognition using motion information and spiking neural networks. In Proceedings of the 30th International Joint Conference on Artificial Intelligence, Montreal, Canada, pp. 1743\u20131749, 2021. DOI: https:\/\/doi.org\/10.24963\/ijcai.2021\/240."},{"key":"1555_CR27","doi-asserted-by":"publisher","first-page":"3694","DOI":"10.1109\/TMM.2022.3164261","volume":"25","author":"M Islam","year":"2023","unstructured":"M. Islam, M. S. Yasar, T. Iqbal. MAVEN: A memory augmented recurrent approach for multimodal fusion. IEEE Transactions on Multimedia, vol. 25, pp. 3694\u20133708, 2023. DOI: https:\/\/doi.org\/10.1109\/TMM.2022.3164261.","journal-title":"IEEE Transactions on Multimedia"},{"key":"1555_CR28","doi-asserted-by":"publisher","first-page":"4121","DOI":"10.1109\/TMM.2022.3171679","volume":"25","author":"S Mai","year":"2023","unstructured":"S. Mai, Y. Zeng, H. Hu. Multimodal information bottleneck: Learning minimal sufficient unimodal and multimodal representations. IEEE Transactions on Multimedia, vol. 25, pp. 4121\u20134134, 2023. DOI: https:\/\/doi.org\/10.1109\/TMM.2022.3171679.","journal-title":"IEEE Transactions on Multimedia"},{"key":"1555_CR29","doi-asserted-by":"publisher","first-page":"4335","DOI":"10.1109\/TMM.2022.3174341","volume":"25","author":"X Wang","year":"2023","unstructured":"X. Wang, X. Shu, S. Zhang, B. Jiang, Y. Wang, Y. Tian, F. Wu. MFGNet: Dynamic modality-aware filter generation for RGB-T tracking. IEEE Transactions on Multimedia, vol. 25, pp. 4335\u20134348, 2023. DOI: https:\/\/doi.org\/10.1109\/TMM.2022.3174341.","journal-title":"IEEE Transactions on Multimedia"},{"key":"1555_CR30","doi-asserted-by":"publisher","first-page":"2671","DOI":"10.1109\/ICIP46576.2022.9897492","volume-title":"In Proceedings of IEEE International Conference on Image Processing","author":"Z Huang","year":"2022","unstructured":"Z. Huang, R. Huang, L. Sun, C. Zhao, M. Huang, S. Su. VEFNet: An event-RGB cross modality fusion network for visual place recognition. In Proceedings of IEEE International Conference on Image Processing, Bordeaux, France, pp. 2671\u20132675, 2022. DOI: https:\/\/doi.org\/10.1109\/ICIP46576.2022.9897492."},{"key":"1555_CR31","first-page":"6000","volume-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems","author":"A Vaswani","year":"2017","unstructured":"A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, L. Kaiser, I. Polosukhin. Attention is all you need. In Proceedings of the 31st International Conference on Neural Information Processing Systems, Long Beach, USA, pp. 6000\u20136010, 2017."},{"key":"1555_CR32","doi-asserted-by":"publisher","first-page":"1105","DOI":"10.1109\/ICCV48922.2021.00114","volume-title":"Proceedings of IEEE\/CVF International Conference on Computer Vision","author":"T D Truong","year":"2021","unstructured":"T. D. Truong, C. N. Duong, T. De Vu, H. A. Pham, B. Raj, N. Le, K. Luu. The right to talk: An audio-visual transformer approach. In Proceedings of IEEE\/CVF International Conference on Computer Vision, Montreal, Canada, pp. 1105\u20131114, 2021. DOI: https:\/\/doi.org\/10.1109\/ICCV48922.2021.00114."},{"key":"1555_CR33","first-page":"8748","volume-title":"Proceedings of the 38th International Conference on Machine Learning","author":"A Radford","year":"2021","unstructured":"A. Radford, J. W. Kim, C. Hallacy, A. Ramesh, G. Goh, S. Agarwal, G. Sastry, A. Askell, P. Mishkin, J. Clark, G. Krueger, I. Sutskever. Learning transferable visual models from natural language supervision. In Proceedings of the 38th International Conference on Machine Learning, pp. 8748\u20138763, 2021."},{"key":"1555_CR34","doi-asserted-by":"publisher","first-page":"16000","DOI":"10.1109\/CVPR52688.2022.01553","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"K He","year":"2022","unstructured":"K. He, X. Chen, S. Xie, Y. Li, P. Doll\u00e4r, R. Girshick. Masked autoencoders are scalable vision learners. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, USA, pp. 16000\u201316009, 2022. DOI: https:\/\/doi.org\/10.1109\/CVPR52688.2022.01553."},{"key":"1555_CR35","doi-asserted-by":"publisher","first-page":"3163","DOI":"10.1109\/ICCVW54120.2021.00355","volume-title":"Proceedings of IEEE\/CVF International Conference on Computer Vision Workshops","author":"D Neimark","year":"2021","unstructured":"D. Neimark, O. Bar, M. Zohar, D. Asselmann. Video transformer network. In Proceedings of IEEE\/CVF International Conference on Computer Vision Workshops, Montreal, Canada, pp. 3163\u20133172, 2021. DOI: https:\/\/doi.org\/10.1109\/ICCVW54120.2021.00355."},{"key":"1555_CR36","doi-asserted-by":"publisher","first-page":"367","DOI":"10.1109\/ICCV48922.2021.00042","volume-title":"Proceedings of IEEE\/CVF International Conference on Computer Vision","author":"Z Peng","year":"2021","unstructured":"Z. Peng, W. Huang, S. Gu, L. Xie, Y. Wang, J. Jiao, Q. Ye. Conformer: Local features coupling global representations for visual recognition. In Proceedings of IEEE\/CVF International Conference on Computer Vision, Montreal, Canada, pp. 367\u2013376, 2021. DOI: https:\/\/doi.org\/10.1109\/ICCV48922.2021.00042."},{"key":"1555_CR37","first-page":"1088","volume-title":"Proceedings of the 35th International Conference on Neural Information Processing Systems","author":"A Nagrani","year":"2021","unstructured":"A. Nagrani, S. Yang, A. Arnab, A. Jansen, C. Schmid, C. Sun. Attention bottlenecks for multimodal fusion. In Proceedings of the 35th International Conference on Neural Information Processing Systems, Article number 1088, 2021."},{"issue":"12","key":"1555_CR38","doi-asserted-by":"publisher","first-page":"14679","DOI":"10.1109\/TITS.2023.3300537","volume":"24","author":"J Zhang","year":"2023","unstructured":"J. Zhang, H. Liu, K. Yang, X. Hu, R. Liu, R. Stiefelhagen. CMX: Cross-modal fusion for RGB-X semantic segmentation with transformers. IEEE Transactions on Intelligent Transportation Systems, vol. 24, no. 12, pp. 14679\u201314694, 2023. DOI: https:\/\/doi.org\/10.1109\/TITS.2023.3300537.","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"1555_CR39","doi-asserted-by":"publisher","first-page":"5542515","DOI":"10.1109\/TGRS.2022.3215816","volume":"60","author":"C Zhao","year":"2022","unstructured":"C. Zhao, H. Liu, N. Su, Y. Yan. TFTN: A transformerbased fusion tracking framework of hyperspectral and RGB. IEEE Transactions on Geoscience and Remote Sensing, vol. 60, Article number 5542515, 2022. DOI: https:\/\/doi.org\/10.1109\/TGRS.2022.3215816.","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"1555_CR40","first-page":"1403","volume-title":"Proceedings of the 35th International Conference on Neural Information Processing Systems","author":"A Bo\u017e\u010d","year":"2021","unstructured":"A. Bo\u017e\u010d, P. R. Palafox, J. Thies, A. Dai, M. Nie\u00dfner. TransformerFusion: Monocular RGB scene reconstruction using transformers. In Proceedings of the 35th International Conference on Neural Information Processing Systems, pp. 1403\u20131414, 2021."},{"key":"1555_CR41","volume-title":"Transformer-based network for RGB-D saliency detection","author":"Y Wang","year":"2021","unstructured":"Y. Wang, X. Jia, L. Zhang, Y. Li, J. Elder, H. Lu. Transformer-based network for RGB-D saliency detection, [Online], Available: https:\/\/arxiv.org\/abs\/2112.00582, 2021."},{"key":"1555_CR42","doi-asserted-by":"publisher","first-page":"7507105","DOI":"10.1109\/LGRS.2022.3179721","volume":"19","author":"H Zhou","year":"2022","unstructured":"H. Zhou, C. Tian, Z. Zhang, Q. Huo, Y. Xie, Z. Li. Multispectral fusion transformer network for RGBthermal urban scene semantic segmentation. IEEE Geoscience and Remote Sensing Letters, vol. 19, Article number 7507105, 2022. DOI: https:\/\/doi.org\/10.1109\/LGRS.2022.3179721.","journal-title":"IEEE Geoscience and Remote Sensing Letters"},{"issue":"1","key":"1555_CR43","doi-asserted-by":"publisher","first-page":"246","DOI":"10.1109\/TCDS.2020.3048883","volume":"14","author":"X Li","year":"2022","unstructured":"X. Li, Y. Hou, P. Wang, Z. Gao, M. Xu, W. Li. Trear: Transformer-based RGB-D egocentric action recognition. IEEE Transactions on Cognitive and Developmental Systems, vol. 14, no. 1, pp. 246\u2013252, 2022. DOI: https:\/\/doi.org\/10.1109\/TCDS.2020.3048883.","journal-title":"IEEE Transactions on Cognitive and Developmental Systems"},{"key":"1555_CR44","doi-asserted-by":"publisher","first-page":"12186","DOI":"10.1109\/CVPR52688.2022.01187","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Y Wang","year":"2022","unstructured":"Y. Wang, X. Chen, L. Cao, W. Huang, F. Sun, Y. Wang. Multimodal token fusion for vision transformers. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, USA, pp. 12186\u201312195, 2022. DOI: https:\/\/doi.org\/10.1109\/CVPR52688.2022.01187."},{"key":"1555_CR45","doi-asserted-by":"publisher","first-page":"7077","DOI":"10.1109\/CVPR46437.2021.00700","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"A Prakash","year":"2021","unstructured":"A. Prakash, K. Chitta, A. Geiger. Multi-modal fusion transformer for end-to-end autonomous driving. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Nashville, USA, pp. 7077\u20137087, 2021. DOI: https:\/\/doi.org\/10.1109\/CVPR46437.2021.00700."},{"key":"1555_CR46","volume-title":"Proceedings of the 9th International Conference on Learning Representations","author":"A Dosovitskiy","year":"2021","unstructured":"A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner, M. Dehghani, M. Minderer, G. Heigold, S. Gelly, J. Uszkoreit, N. Houlsby. An image is worth 16\u00d716 words: Transformers for image recognition at scale. In Proceedings of the 9th International Conference on Learning Representations, 2021."},{"key":"1555_CR47","doi-asserted-by":"publisher","first-page":"421","DOI":"10.1007\/978-3-642-35289-8_25","volume-title":"Neural Networks: Tricks of the Trade","author":"L Bottou","year":"2012","unstructured":"L. Bottou. Stochastic gradient descent tricks. Neural Networks: Tricks of the Trade, 2nd ed., G. Montavon, G. B. Orr, K. R. M\u00fcller, Eds., Berlin, Heidelberg, Germany: Springer, pp. 421\u2013436, 2012. DOI: https:\/\/doi.org\/10.1007\/978-3-642-35289-8_25.","edition":"2nd ed."},{"key":"1555_CR48","first-page":"721","volume-title":"Proceedings of the 33rd International Conference on Neural Information Processing Systems","author":"A Paszke","year":"2019","unstructured":"A. Paszke, S. Gross, F. Massa, A. Lerer, J. Bradbury, G. Chanan, T. Killeen, Z. Lin, N. Gimelshein, L. Antiga, A. Desmaison, A. K\u00f6pf, E. Yang, Z. DeVito, M. Raison, A. Tejani, S. Chilamkurthy, B. Steiner, L. Fang, J. Bai, S. Chintala. PyTorch: An imperative style, high-performance deep learning library. In Proceedings of the 33rd International Conference on Neural Information Processing Systems, Vancouver, Canada, Article number 721, 2019."},{"key":"1555_CR49","doi-asserted-by":"publisher","first-page":"4489","DOI":"10.1109\/ICCV.2015.510","volume-title":"Proceedings of IEEE International Conference on Computer Vision","author":"D Tran","year":"2015","unstructured":"D. Tran, L. Bourdev, R. Fergus, L. Torresani, M. Paluri. Learning spatiotemporal features with 3D convolutional networks. In Proceedings of IEEE International Conference on Computer Vision, Santiago, Chile, pp. 4489\u20134497, 2015. DOI: https:\/\/doi.org\/10.1109\/ICCV.2015.510."},{"key":"1555_CR50","first-page":"813","volume-title":"Proceedings of the 38th International Conference on Machine Learning","author":"G Bertasius","year":"2021","unstructured":"G. Bertasius, H. Wang, L. Torresani. Is space-time attention all you need for video understanding?. In Proceedings of the 38th International Conference on Machine Learning, pp. 813\u2013824, 2021."},{"key":"1555_CR51","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1109\/CVPR42600.2020.00028","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"C Feichtenhofer","year":"2020","unstructured":"C. Feichtenhofer. X3D: Expanding architectures for efficient video recognition. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, USA, pp. 203\u2013213, 2020. DOI: https:\/\/doi.org\/10.1109\/CVPR42600.2020.00028."},{"key":"1555_CR52","doi-asserted-by":"publisher","first-page":"13214","DOI":"10.1109\/CVPR46437.2021.01301","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Z Wang","year":"2021","unstructured":"Z. Wang, Q. She, A. Smolic. ACTION-Net: Multipath excitation for action recognition. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Nashville, USA, pp. 13214\u201313223, 2021. DOI: https:\/\/doi.org\/10.1109\/CVPR46437.2021.01301."},{"key":"1555_CR53","doi-asserted-by":"publisher","first-page":"4804","DOI":"10.1109\/CVPR52688.2022.00476","volume-title":"Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Y Li","year":"2022","unstructured":"Y. Li, C. Y. Wu, H. Fan, K. Mangalam, B. Xiong, J. Malik, C. Feichtenhofer. MViTv2: Improved multiscale vision transformers for classification and detection. In Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, USA, pp. 4804\u20134814, 2022. DOI: https:\/\/doi.org\/10.1109\/CVPR52688.2022.00476."},{"key":"1555_CR54","volume-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"J Li","year":"2023","unstructured":"J. Li, D. Li, S. Savarese, S. Hoi. BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models, [Online], Available: https:\/\/arxiv.org\/abs\/2301.12597, 2023."}],"container-title":["Machine Intelligence Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11633-025-1555-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11633-025-1555-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11633-025-1555-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,26]],"date-time":"2025-11-26T10:03:04Z","timestamp":1764151384000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11633-025-1555-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,21]]},"references-count":54,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,12]]}},"alternative-id":["1555"],"URL":"https:\/\/doi.org\/10.1007\/s11633-025-1555-3","relation":{},"ISSN":["2731-538X","2731-5398"],"issn-type":[{"value":"2731-538X","type":"print"},{"value":"2731-5398","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,21]]},"assertion":[{"value":"26 August 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 March 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 October 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declared that they have no conflicts of interest to this work.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations of conflict of interest"}}]}}