{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,5]],"date-time":"2026-07-05T00:19:34Z","timestamp":1783210774577,"version":"3.54.6"},"reference-count":46,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100009696","name":"Minjiang University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100009696","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004608","name":"Jiangsu Province Natural Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004608","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003392","name":"Fujian Provincial Natural Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003392","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.patcog.2026.114307","type":"journal-article","created":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T07:14:47Z","timestamp":1782198887000},"page":"114307","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PD","title":["Beyond aggregate metrics: Scale-balanced temporal grounding via semantic diffusion encoding and structure-aware decoding"],"prefix":"10.1016","volume":"180","author":[{"given":"Henghao","family":"Zhao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rui","family":"Yan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zechao","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuezhi","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.114307_b1","doi-asserted-by":"crossref","unstructured":"R. Krishna, K. Hata, F. Ren, L. Fei-Fei, J.C. Niebles, Dense-Captioning Events in Videos, in: Proceedings of the IEEE International Conference on Computer Vision, 2017.","DOI":"10.1109\/ICCV.2017.83"},{"key":"10.1016\/j.patcog.2026.114307_b2","doi-asserted-by":"crossref","unstructured":"V. Iashin, E. Rahtu, A better use of audio-visual cues: Dense video captioning with bi-modal transformer, in: Proceedings of the British Machine Vision Conference, 2020.","DOI":"10.5244\/C.34.29"},{"key":"10.1016\/j.patcog.2026.114307_b3","doi-asserted-by":"crossref","unstructured":"J. Lei, L. Yu, T. Berg, M. Bansal, TVQA+: Spatio-Temporal Grounding for Video Question Answering, in: Proceedings of the Annual Meeting of the Association for Computational Linguistics, 2020.","DOI":"10.18653\/v1\/2020.acl-main.730"},{"key":"10.1016\/j.patcog.2026.114307_b4","doi-asserted-by":"crossref","unstructured":"S. Yu, J. Cho, P. Yadav, M. Bansal, Self-chained image-language model for video localization and question answering, in: Advances in Neural Information Processing Systems, 2023.","DOI":"10.52202\/075280-3354"},{"key":"10.1016\/j.patcog.2026.114307_b5","doi-asserted-by":"crossref","unstructured":"J. Gao, C. Sun, Z. Yang, R. Nevatia, Tall: Temporal activity localization via language query, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2017.","DOI":"10.1109\/ICCV.2017.563"},{"issue":"12","key":"10.1016\/j.patcog.2026.114307_b6","doi-asserted-by":"crossref","first-page":"9073","DOI":"10.1109\/TPAMI.2021.3120745","article-title":"Multi-scale 2d temporal adjacency networks for moment localization with natural language","volume":"44","author":"Zhang","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patcog.2026.114307_b7","doi-asserted-by":"crossref","unstructured":"J. Mun, M. Cho, B. Han, Local-global video-text interactions for temporal grounding, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020.","DOI":"10.1109\/CVPR42600.2020.01082"},{"issue":"5","key":"10.1016\/j.patcog.2026.114307_b8","doi-asserted-by":"crossref","first-page":"6598","DOI":"10.1109\/TNNLS.2022.3211850","article-title":"SDN: Semantic decoupling network for temporal language grounding","volume":"35","author":"Jiang","year":"2024","journal-title":"IEEE Trans. Neural Networks Learn. Syst."},{"key":"10.1016\/j.patcog.2026.114307_b9","doi-asserted-by":"crossref","unstructured":"B. Huang, X. Wang, H. Chen, Z. Song, W. Zhu, VTimeLLM: Empower LLM to Grasp Video Moments, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024.","DOI":"10.1109\/CVPR52733.2024.01353"},{"key":"10.1016\/j.patcog.2026.114307_b10","article-title":"VideoExpert: Augmented LLM for temporal-sensitive video understanding","author":"Zhao","year":"2026","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.patcog.2026.114307_b11","unstructured":"J. Lei, T.L. Berg, M. Bansal, Detecting moments and highlights in videos via natural language queries, in: Advances in Neural Information Processing Systems, 2021."},{"key":"10.1016\/j.patcog.2026.114307_b12","doi-asserted-by":"crossref","unstructured":"P. Lee, H. Byun, Bam-detr: Boundary-aligned moment detection transformer for temporal sentence grounding in videos, in: Proceedings of the European Conference on Computer Vision, 2024.","DOI":"10.1007\/978-3-031-72627-9_13"},{"key":"10.1016\/j.patcog.2026.114307_b13","doi-asserted-by":"crossref","unstructured":"W. Moon, S. Hyun, S. Park, D. Park, J.-P. Heo, Query-dependent video representation for moment retrieval and highlight detection, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023.","DOI":"10.1109\/CVPR52729.2023.02205"},{"key":"10.1016\/j.patcog.2026.114307_b14","doi-asserted-by":"crossref","unstructured":"H. Sun, M. Zhou, W. Chen, W. Xie, TR-DETR: Task-reciprocal transformer for joint moment retrieval and highlight detection, in: Proceedings of the AAAI Conference on Artificial Intelligence, 2024.","DOI":"10.1609\/aaai.v38i5.28304"},{"key":"10.1016\/j.patcog.2026.114307_b15","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1162\/tacl_a_00207","article-title":"Grounding action descriptions in videos","volume":"1","author":"Regneri","year":"2013","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"10.1016\/j.patcog.2026.114307_b16","doi-asserted-by":"crossref","unstructured":"L. Anne Hendricks, O. Wang, E. Shechtman, J. Sivic, T. Darrell, B. Russell, Localizing moments in video with natural language, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2017.","DOI":"10.1109\/ICCV.2017.618"},{"key":"10.1016\/j.patcog.2026.114307_b17","doi-asserted-by":"crossref","unstructured":"H. Xu, K. He, B.A. Plummer, L. Sigal, S. Sclaroff, K. Saenko, Multilevel language and vision integration for text-to-clip retrieval, in: Proceedings of the AAAI Conference on Artificial Intelligence, 2019.","DOI":"10.1609\/aaai.v33i01.33019062"},{"key":"10.1016\/j.patcog.2026.114307_b18","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2024.112592","article-title":"Query-aware multi-scale proposal network for weakly supervised temporal sentence grounding in videos","volume":"304","author":"Zhou","year":"2024","journal-title":"Knowl.-Based Syst."},{"issue":"8","key":"10.1016\/j.patcog.2026.114307_b19","doi-asserted-by":"crossref","first-page":"11448","DOI":"10.1109\/TNNLS.2023.3261927","article-title":"M 2 DCapsN: Multimodal, multichannel, and dual-step capsule network for natural language moment localization","volume":"35","author":"Liu","year":"2024","journal-title":"IEEE Trans. Neural Networks Learn. Syst."},{"key":"10.1016\/j.patcog.2026.114307_b20","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.112484","article-title":"Learning unified patterns of multimodalities for video temporal grounding","volume":"172","author":"Yang","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114307_b21","doi-asserted-by":"crossref","unstructured":"R. Zeng, H. Xu, W. Huang, P. Chen, M. Tan, C. Gan, Dense Regression Network for Video Grounding, in: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020.","DOI":"10.1109\/CVPR42600.2020.01030"},{"key":"10.1016\/j.patcog.2026.114307_b22","doi-asserted-by":"crossref","unstructured":"D. He, X. Zhao, J. Huang, F. Li, X. Liu, S. Wen, Read, watch, and move: Reinforcement learning for temporally grounding natural language descriptions in videos, in: Proceedings of the AAAI Conference on Artificial Intelligence, 2019.","DOI":"10.1609\/aaai.v33i01.33018393"},{"key":"10.1016\/j.patcog.2026.114307_b23","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111621","article-title":"Adversarial temporal sentence grounding by learning from external data","volume":"165","author":"Han","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114307_b24","doi-asserted-by":"crossref","unstructured":"S. Ren, L. Yao, S. Li, X. Sun, L. Hou, TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024.","DOI":"10.1109\/CVPR52733.2024.01357"},{"key":"10.1016\/j.patcog.2026.114307_b25","doi-asserted-by":"crossref","unstructured":"Y. Guo, J. Liu, M. Li, D. Chen, X. Tang, D. Sui, Q. Liu, X. Chen, K. Zhao, VTG-LLM: Integrating Timestamp Knowledge into Video LLMs for Enhanced Video Temporal Grounding, in: Proceedings of the AAAI Conference on Artificial Intelligence, 2025.","DOI":"10.1609\/aaai.v39i3.32341"},{"key":"10.1016\/j.patcog.2026.114307_b26","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111670","article-title":"MLLM as video narrator: Mitigating modality imbalance in video moment retrieval","volume":"166","author":"Cai","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114307_b27","series-title":"Advances in Neural Information Processing Systems","article-title":"Time-R1: Post-training large vision language model for temporal video grounding","author":"Wang","year":"2025"},{"key":"10.1016\/j.patcog.2026.114307_b28","doi-asserted-by":"crossref","unstructured":"R. Zeng, J. Mao, M. Lai, M.H. Phan, Y. Dong, W. Wang, Q. Chen, X. Hu, OVG-HQ: Online Video Grounding with Hybrid-Modal Queries, in: IEEE\/CVF International Conference on Computer Vision, 2025.","DOI":"10.1109\/ICCV51701.2025.01959"},{"issue":"5","key":"10.1016\/j.patcog.2026.114307_b29","doi-asserted-by":"crossref","first-page":"3940","DOI":"10.1109\/TCSVT.2024.3513633","article-title":"Improving video moment retrieval by auxiliary moment-query pairs with hyper-interaction","volume":"35","author":"Zeng","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.patcog.2026.114307_b30","article-title":"Learning visual-audio dissonance for moment retrieval and highlight detection","author":"Yang","year":"2026","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.patcog.2026.114307_b31","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.112984","article-title":"Correlation-guided calibration of query dependency for video temporal grounding","volume":"174","author":"Moon","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114307_b32","doi-asserted-by":"crossref","unstructured":"Z. Liu, J. Li, H. Xie, P. Li, J. Ge, S.-A. Liu, G. Jin, Towards Balanced Alignment: Modal-Enhanced Semantic Modeling for Video Moment Retrieval, in: Proceedings of the AAAI Conference on Artificial Intelligence, 2024.","DOI":"10.1609\/aaai.v38i4.28177"},{"key":"10.1016\/j.patcog.2026.114307_b33","doi-asserted-by":"crossref","unstructured":"S. Park, J. Choi, K. Baek, H. Shim, MomentMix Augmentation with Length-Aware DETR for Temporally Robust Moment Retrieval, in: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, 2026.","DOI":"10.1109\/WACV61042.2026.00116"},{"key":"10.1016\/j.patcog.2026.114307_b34","doi-asserted-by":"crossref","unstructured":"Z. Cao, B. Zhang, H. Du, X. Yu, X. Li, S. Wang, FlashVTG: Feature Layering and Adaptive Score Handling Network for Video Temporal Grounding, in: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, 2025.","DOI":"10.1109\/WACV61041.2025.00894"},{"key":"10.1016\/j.patcog.2026.114307_b35","doi-asserted-by":"crossref","unstructured":"G. Sigurdsson, G. Varol, X. Wang, I. Laptev, A. Gupta, Hollywood in homes: Crowdsourcing data collection for activity understanding, in: Proceedings of the European Conference on Computer Vision, 2016.","DOI":"10.1007\/978-3-319-46448-0_31"},{"key":"10.1016\/j.patcog.2026.114307_b36","doi-asserted-by":"crossref","unstructured":"M. Rohrbach, M. Regneri, M. Andriluka, S. Amin, M. Pinkal, B. Schiele, Script data for attribute-based recognition of composite activities, in: Proceedings of the European Conference on Computer Vision, 2012.","DOI":"10.1007\/978-3-642-33718-5_11"},{"key":"10.1016\/j.patcog.2026.114307_b37","unstructured":"X. Glorot, Y. Bengio, Understanding the difficulty of training deep feedforward neural networks, in: Proceedings of the International Conference on Artificial Intelligence and Statistics, 2010."},{"key":"10.1016\/j.patcog.2026.114307_b38","doi-asserted-by":"crossref","unstructured":"Y. Xiao, Z. Luo, Y. Liu, Y. Ma, H. Bian, Y. Ji, Y. Yang, X. Li, Bridging the Gap: A Unified Video Comprehension Framework for Moment Retrieval and Highlight Detection, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024.","DOI":"10.1109\/CVPR52733.2024.01770"},{"key":"10.1016\/j.patcog.2026.114307_b39","doi-asserted-by":"crossref","unstructured":"J. Tang, Z. Wei, Y. Zhu, C. Shi, G. Li, L. Lin, S. Yang, Sim-DETR: Unlock DETR for Temporal Sentence Grounding, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2025.","DOI":"10.1109\/ICCV51701.2025.02113"},{"key":"10.1016\/j.patcog.2026.114307_b40","doi-asserted-by":"crossref","unstructured":"Y. Liu, S. Li, Y. Wu, C.-W. Chen, Y. Shan, X. Qie, Umt: Unified multi-modal transformers for joint video moment retrieval and highlight detection, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022.","DOI":"10.1109\/CVPR52688.2022.00305"},{"key":"10.1016\/j.patcog.2026.114307_b41","doi-asserted-by":"crossref","unstructured":"K. Lin, P. Zhang, J. Chen, S. Pramanick, D. Gao, M. Shou, Univtg: Towards unified video-language temporal grounding, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023.","DOI":"10.1109\/ICCV51070.2023.00262"},{"issue":"8","key":"10.1016\/j.patcog.2026.114307_b42","doi-asserted-by":"crossref","first-page":"14522","DOI":"10.1109\/TNNLS.2024.3516033","article-title":"DiffusionVMR: Diffusion model for joint video moment retrieval and highlight detection","volume":"36","author":"Zhao","year":"2025","journal-title":"IEEE Trans. Neural Networks Learn. Syst."},{"key":"10.1016\/j.patcog.2026.114307_b43","doi-asserted-by":"crossref","unstructured":"J. Yang, P. Wei, H. Li, Z. Ren, Task-Driven Exploration: Decoupling and Inter-Task Feedback for Joint Moment Retrieval and Highlight Detection, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024.","DOI":"10.1109\/CVPR52733.2024.01733"},{"key":"10.1016\/j.patcog.2026.114307_b44","doi-asserted-by":"crossref","unstructured":"Y. Liu, J. He, W. Li, J. Kim, D. Wei, H. Pfister, C.W. Chen, R2-Tuning: Efficient Image-to-Video Transfer Learning for Video Temporal Grounding, in: Proceedings of the European Conference on Computer Vision, 2025.","DOI":"10.1007\/978-3-031-72940-9_24"},{"key":"10.1016\/j.patcog.2026.114307_b45","doi-asserted-by":"crossref","unstructured":"H. Zhang, A. Sun, W. Jing, J.T. Zhou, Span-based Localizing Network for Natural Language Video Localization, in: Proceedings of the Annual Meeting of the Association for Computational Linguistics, 2020.","DOI":"10.18653\/v1\/2020.acl-main.585"},{"key":"10.1016\/j.patcog.2026.114307_b46","unstructured":"X. Zhu, W. Su, L. Lu, B. Li, X. Wang, J. Dai, Deformable DETR: Deformable Transformers for End-to-End Object Detection, in: Proceedings of the International Conference on Learning Representations, 2021."}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326012720?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326012720?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,5]],"date-time":"2026-07-05T00:07:16Z","timestamp":1783210036000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326012720"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":46,"alternative-id":["S0031320326012720"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114307","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Beyond aggregate metrics: Scale-balanced temporal grounding via semantic diffusion encoding and structure-aware decoding","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114307","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"114307"}}