{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T10:20:08Z","timestamp":1783160408975,"version":"3.54.6"},"reference-count":56,"publisher":"Elsevier BV","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.elsevier.com\/tdm\/userlicense\/1.0\/"},{"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.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100007957","name":"Chongqing Municipal Education Commission","doi-asserted-by":"publisher","award":["HZ2021008"],"award-info":[{"award-number":["HZ2021008"]}],"id":[{"id":"10.13039\/501100007957","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Image and Vision Computing"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.imavis.2026.106046","type":"journal-article","created":{"date-parts":[[2026,5,30]],"date-time":"2026-05-30T06:31:17Z","timestamp":1780122677000},"page":"106046","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["MTF-CLIP: Efficient multimodal action recognition framework exploring multi-criteria token fusion"],"prefix":"10.1016","volume":"172","author":[{"given":"Jianjun","family":"Lei","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dingyuan","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ying","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.imavis.2026.106046_b1","series-title":"Proceedings of the 38th International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume":"vol. 139","author":"Radford","year":"2021"},{"key":"10.1016\/j.imavis.2026.106046_b2","doi-asserted-by":"crossref","unstructured":"T. Han, W. Xie, A. Zisserman, Temporal Alignment Networks for Long-Term Video, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2022, pp. 2906\u20132916.","DOI":"10.1109\/CVPR52688.2022.00292"},{"key":"10.1016\/j.imavis.2026.106046_b3","doi-asserted-by":"crossref","unstructured":"V. Choutas, P. Weinzaepfel, J. Revaud, C. Schmid, PoTion: Pose MoTion Representation for Action Recognition, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR, 2018, pp. 7024\u20137033.","DOI":"10.1109\/CVPR.2018.00734"},{"key":"10.1016\/j.imavis.2026.106046_b4","doi-asserted-by":"crossref","unstructured":"C. Feichtenhofer, X3D: Expanding Architectures for Efficient Video Recognition, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2020.","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"10.1016\/j.imavis.2026.106046_b5","series-title":"Proceedings of the 38th International Conference on Machine Learning","first-page":"813","article-title":"Is space-time attention all you need for video understanding?","volume":"vol. 2","author":"Bertasius","year":"2021"},{"key":"10.1016\/j.imavis.2026.106046_b6","doi-asserted-by":"crossref","unstructured":"A. Arnab, M. Dehghani, G. Heigold, C. Sun, M. Lu\u010di\u0107, C. Schmid, ViViT: A Video Vision Transformer, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, ICCV, 2021, pp. 6836\u20136846.","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"10.1016\/j.imavis.2026.106046_b7","doi-asserted-by":"crossref","DOI":"10.1016\/j.imavis.2023.104740","article-title":"Fsformer: Fast-slow transformer for video action recognition","volume":"137","author":"Li","year":"2023","journal-title":"Image Vis. Comput."},{"key":"10.1016\/j.imavis.2026.106046_b8","doi-asserted-by":"crossref","DOI":"10.1016\/j.imavis.2024.105295","article-title":"Background debiased class incremental learning for video action recognition","volume":"151","author":"Nguyen","year":"2024","journal-title":"Image Vis. Comput."},{"key":"10.1016\/j.imavis.2026.106046_b9","doi-asserted-by":"crossref","unstructured":"C. Yang, Z. An, L. Huang, J. Bi, X. Yu, H. Yang, B. Diao, Y. Xu, Clip-kd: An empirical study of clip model distillation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 15952\u201315962.","DOI":"10.1109\/CVPR52733.2024.01510"},{"key":"10.1016\/j.imavis.2026.106046_b10","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111547","article-title":"DC-CLIP: Multilingual CLIP compression via vision-language distillation and vision-language alignment","volume":"164","author":"Zhang","year":"2025","journal-title":"Pattern Recognit."},{"issue":"1","key":"10.1016\/j.imavis.2026.106046_b11","doi-asserted-by":"crossref","first-page":"625","DOI":"10.1109\/TNNLS.2023.3331841","article-title":"Actionclip: Adapting language-image pretrained models for video action recognition","volume":"36","author":"Wang","year":"2025","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.imavis.2026.106046_b12","first-page":"26462","article-title":"ST-adapter: Parameter-efficient image-to-video transfer learning","volume":"vol. 35","author":"Pan","year":"2022"},{"key":"10.1016\/j.imavis.2026.106046_b13","doi-asserted-by":"crossref","unstructured":"S.T. Wasim, M. Naseer, S. Khan, F.S. Khan, M. Shah, Vita-CLIP: Video and Text Adaptive CLIP via Multimodal Prompting, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2023, pp. 23034\u201323044.","DOI":"10.1109\/CVPR52729.2023.02206"},{"key":"10.1016\/j.imavis.2026.106046_b14","doi-asserted-by":"crossref","DOI":"10.1016\/j.imavis.2025.105748","article-title":"PHMG: Prompt-based human motion generation for action recognition","volume":"163","author":"Lu","year":"2025","journal-title":"Image Vis. Comput."},{"key":"10.1016\/j.imavis.2026.106046_b15","series-title":"The kinetics human action video dataset","author":"Kay","year":"2017"},{"key":"10.1016\/j.imavis.2026.106046_b16","series-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","author":"Soomro","year":"2012"},{"key":"10.1016\/j.imavis.2026.106046_b17","doi-asserted-by":"crossref","unstructured":"H. Kuehne, H. Jhuang, E. Garrote, T. Poggio, T. Serre, HMDB: A large video database for human motion recognition, in: 2011 International Conference on Computer Vision, 2011, pp. 2556\u20132563.","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"10.1016\/j.imavis.2026.106046_b18","doi-asserted-by":"crossref","unstructured":"Z. Liu, J. Ning, Y. Cao, Y. Wei, Z. Zhang, S. Lin, H. Hu, Video Swin Transformer, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2022, pp. 3202\u20133211.","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"10.1016\/j.imavis.2026.106046_b19","doi-asserted-by":"crossref","DOI":"10.1016\/j.imavis.2025.105855","article-title":"WAM-net: Wavelet-based adaptive multi-scale fusion network for fine-grained action recognition","volume":"166","author":"Di","year":"2026","journal-title":"Image Vis. Comput."},{"key":"10.1016\/j.imavis.2026.106046_b20","series-title":"Computer Vision \u2013 ECCV 2022","first-page":"620","article-title":"Spvit: Enabling faster vision transformers via latency-aware soft token pruning","author":"Kong","year":"2022"},{"key":"10.1016\/j.imavis.2026.106046_b21","doi-asserted-by":"crossref","unstructured":"S. Long, Z. Zhao, J. Pi, S. Wang, J. Wang, Beyond Attentive Tokens: Incorporating Token Importance and Diversity for Efficient Vision Transformers, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2023, pp. 10334\u201310343.","DOI":"10.1109\/CVPR52729.2023.00996"},{"key":"10.1016\/j.imavis.2026.106046_b22","doi-asserted-by":"crossref","unstructured":"D. Marin, J.-H.R. Chang, A. Ranjan, A. Prabhu, M. Rastegari, O. Tuzel, Token Pooling in Vision Transformers for Image Classification, in: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, WACV, 2023, pp. 12\u201321.","DOI":"10.1109\/WACV56688.2023.00010"},{"key":"10.1016\/j.imavis.2026.106046_b23","series-title":"Computer Vision \u2013 ECCV 2022","first-page":"388","article-title":"Frozen CLIP models are efficient video learners","author":"Lin","year":"2022"},{"key":"10.1016\/j.imavis.2026.106046_b24","series-title":"Computer Vision \u2013 ECCV 2022","first-page":"1","article-title":"Expanding language-image pretrained models for general video recognition","author":"Ni","year":"2022"},{"key":"10.1016\/j.imavis.2026.106046_b25","first-page":"2847","article-title":"Revisiting classifier: Transferring vision-language models for video recognition","volume":"vol. 37","author":"Wu","year":"2023"},{"key":"10.1016\/j.imavis.2026.106046_b26","doi-asserted-by":"crossref","unstructured":"W. Wu, X. Wang, H. Luo, J. Wang, Y. Yang, W. Ouyang, Bidirectional Cross-Modal Knowledge Exploration for Video Recognition With Pre-Trained Vision-Language Models, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2023, pp. 6620\u20136630.","DOI":"10.1109\/CVPR52729.2023.00640"},{"issue":"9","key":"10.1016\/j.imavis.2026.106046_b27","doi-asserted-by":"crossref","first-page":"8172","DOI":"10.1109\/TCSVT.2024.3390133","article-title":"GBC: Guided alignment and adaptive boosting CLIP bridging vision and language for robust action recognition","volume":"34","author":"Yang","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.imavis.2026.106046_b28","first-page":"5517","article-title":"A multimodal, multi-task adapting framework for video action recognition","volume":"vol. 38","author":"Wang","year":"2024"},{"key":"10.1016\/j.imavis.2026.106046_b29","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111402","article-title":"Semantic matters: A constrained approach for zero-shot video action recognition","volume":"162","author":"Quan","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.imavis.2026.106046_b30","first-page":"9689","article-title":"Building a multi-modal spatiotemporal expert for zero-shot action recognition with clip","volume":"vol. 39","author":"Yu","year":"2025"},{"issue":"9","key":"10.1016\/j.imavis.2026.106046_b31","doi-asserted-by":"crossref","first-page":"2337","DOI":"10.1007\/s11263-022-01653-1","article-title":"Learning to prompt for vision-language models","volume":"130","author":"Zhou","year":"2022","journal-title":"Int. J. Comput. Vis."},{"issue":"2","key":"10.1016\/j.imavis.2026.106046_b32","doi-asserted-by":"crossref","first-page":"581","DOI":"10.1007\/s11263-023-01891-x","article-title":"Clip-adapter: Better vision-language models with feature adapters","volume":"132","author":"Gao","year":"2024","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.imavis.2026.106046_b33","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110559","article-title":"Ta-adapter: Enhancing few-shot CLIP with task-aware encoders","volume":"153","author":"Zhang","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.imavis.2026.106046_b34","unstructured":"J. Tao, X. Qi, W. Wang, Y. Xia, P. Luo, AIM: Adapting Image Models for Efficient Video Action Recognition, in: International Conference on Learning Representations, ICLR, 2023."},{"key":"10.1016\/j.imavis.2026.106046_b35","doi-asserted-by":"crossref","DOI":"10.1016\/j.adhoc.2020.102380","article-title":"Vdarn: Video disentangling attentive relation network for few-shot and zero-shot action recognition","volume":"113","author":"Su","year":"2021","journal-title":"Ad Hoc Networks"},{"key":"10.1016\/j.imavis.2026.106046_b36","article-title":"Unbiased spatial-temporal atomic fusion-based zero-shot action recognition","author":"Xing","year":"2025","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.imavis.2026.106046_b37","article-title":"Prvr: Partially relevant video retrieval","author":"Chen","year":"2025","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.imavis.2026.106046_b38","doi-asserted-by":"crossref","unstructured":"B. Liu, T. Zheng, P. Zheng, D. Liu, X. Qu, J. Gao, J. Dong, X. Wang, Lite-mkd: A multi-modal knowledge distillation framework for lightweight few-shot action recognition, in: Proceedings of the 31st ACM International Conference on Multimedia, 2023, pp. 7283\u20137294.","DOI":"10.1145\/3581783.3612279"},{"key":"10.1016\/j.imavis.2026.106046_b39","doi-asserted-by":"crossref","unstructured":"S. Lee, J. Choi, H.J. Kim, Multi-criteria Token Fusion with One-step-ahead Attention for Efficient Vision Transformers, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2024, pp. 15741\u201315750.","DOI":"10.1109\/CVPR52733.2024.01490"},{"key":"10.1016\/j.imavis.2026.106046_b40","doi-asserted-by":"crossref","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 the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2022, pp. 4804\u20134814.","DOI":"10.1109\/CVPR52688.2022.00476"},{"issue":"2","key":"10.1016\/j.imavis.2026.106046_b41","doi-asserted-by":"crossref","first-page":"5752","DOI":"10.1109\/TCE.2025.3570181","article-title":"AFES: Attention-based feature excitation and sorting for action recognition","volume":"71","author":"Zhou","year":"2025","journal-title":"IEEE Trans. Consum. Electron."},{"key":"10.1016\/j.imavis.2026.106046_b42","series-title":"Uniformer: Unified transformer for efficient spatiotemporal representation learning","author":"Li","year":"2022"},{"key":"10.1016\/j.imavis.2026.106046_b43","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111770","article-title":"VLPA-CLIP: Video language prompting and adapting CLIP for efficient video action recognition","volume":"168","author":"Wang","year":"2025","journal-title":"Pattern Recognit."},{"issue":"3","key":"10.1016\/j.imavis.2026.106046_b44","doi-asserted-by":"crossref","first-page":"977","DOI":"10.1109\/TCSVT.2022.3207518","article-title":"A progressive difference method for capturing visual tempos on action recognition","volume":"33","author":"Sheng","year":"2023","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"3","key":"10.1016\/j.imavis.2026.106046_b45","first-page":"3347","article-title":"Learning SpatioTemporal and motion features in a unified 2D network for action recognition","volume":"45","author":"Wang","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.imavis.2026.106046_b46","doi-asserted-by":"crossref","first-page":"2573","DOI":"10.1109\/TMM.2022.3148588","article-title":"Attention-driven appearance-motion fusion network for action recognition","volume":"25","author":"Liu","year":"2023","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.imavis.2026.106046_b47","doi-asserted-by":"crossref","unstructured":"X. Liu, S.L. Pintea, F.K. Nejadasl, O. Booij, J.C. van Gemert, No Frame Left Behind: Full Video Action Recognition, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2021, pp. 14892\u201314901.","DOI":"10.1109\/CVPR46437.2021.01465"},{"key":"10.1016\/j.imavis.2026.106046_b48","first-page":"2943","article-title":"Mvfnet: Multi-view fusion network for efficient video recognition","volume":"vol. 35","author":"Wu","year":"2021"},{"issue":"10","key":"10.1016\/j.imavis.2026.106046_b49","doi-asserted-by":"crossref","first-page":"7010","DOI":"10.1109\/TPAMI.2021.3100277","article-title":"Interaction-aware spatio-temporal pyramid attention networks for action classification","volume":"44","author":"Hu","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"9","key":"10.1016\/j.imavis.2026.106046_b50","first-page":"4839","article-title":"Depthwise spatio-temporal STFT convolutional neural networks for human action recognition","volume":"44","author":"Kumawat","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.imavis.2026.106046_b51","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1109\/TIP.2022.3228156","article-title":"Pose-appearance relational modeling for video action recognition","volume":"32","author":"Cui","year":"2023","journal-title":"IEEE Trans. Image Process."},{"issue":"9","key":"10.1016\/j.imavis.2026.106046_b52","doi-asserted-by":"crossref","first-page":"5174","DOI":"10.1109\/TCSVT.2023.3250646","article-title":"Spatio-temporal adaptive network with bidirectional temporal difference for action recognition","volume":"33","author":"Li","year":"2023","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.imavis.2026.106046_b53","doi-asserted-by":"crossref","unstructured":"X. Li, S. Li, M. Ma, Interactive and Balanced Multimodal Learning via Cross Attention and Gradient Modulation for Compressed Video Action Recognition, in: ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP, 2025, pp. 1\u20135.","DOI":"10.1109\/ICASSP49660.2025.10888127"},{"key":"10.1016\/j.imavis.2026.106046_b54","doi-asserted-by":"crossref","first-page":"971","DOI":"10.1109\/LSP.2025.3533307","article-title":"EVA: Enabling video attributes with hierarchical prompt tuning for action recognition","volume":"32","author":"Ruan","year":"2025","journal-title":"IEEE Signal Process. Lett."},{"key":"10.1016\/j.imavis.2026.106046_b55","doi-asserted-by":"crossref","unstructured":"S. Chen, D. Huang, Elaborative Rehearsal for Zero-Shot Action Recognition, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, ICCV, 2021, pp. 13638\u201313647.","DOI":"10.1109\/ICCV48922.2021.01338"},{"key":"10.1016\/j.imavis.2026.106046_b56","doi-asserted-by":"crossref","first-page":"1336","DOI":"10.1109\/LSP.2025.3548448","article-title":"From body parts to holistic action: A fine-grained teacher-student clip for action recognition","volume":"32","author":"Ou","year":"2025","journal-title":"IEEE Signal Process. Lett."}],"container-title":["Image and Vision Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0262885626001538?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0262885626001538?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T10:13:03Z","timestamp":1783159983000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0262885626001538"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":56,"alternative-id":["S0262885626001538"],"URL":"https:\/\/doi.org\/10.1016\/j.imavis.2026.106046","relation":{},"ISSN":["0262-8856"],"issn-type":[{"value":"0262-8856","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"MTF-CLIP: Efficient multimodal action recognition framework exploring multi-criteria token fusion","name":"articletitle","label":"Article Title"},{"value":"Image and Vision Computing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.imavis.2026.106046","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"106046"}}