{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T06:49:44Z","timestamp":1774594184088,"version":"3.50.1"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,8]]},"DOI":"10.1109\/bigdata66926.2025.11402227","type":"proceedings-article","created":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T20:57:57Z","timestamp":1772830677000},"page":"2013-2022","source":"Crossref","is-referenced-by-count":0,"title":["SOP-Guided Co-Enhanced CLIP for Action Recognition in Logistics Warehouse Packaging"],"prefix":"10.1109","author":[{"given":"Wenting","family":"Qi","sequence":"first","affiliation":[{"name":"JD Logistics,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kexin","family":"Zhang","sequence":"additional","affiliation":[{"name":"JD Logistics,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Sun","sequence":"additional","affiliation":[{"name":"JD Logistics,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haichao","family":"Zhang","sequence":"additional","affiliation":[{"name":"JD Logistics,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoyin","family":"Xu","sequence":"additional","affiliation":[{"name":"JD Logistics,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hengle","family":"Qin","sequence":"additional","affiliation":[{"name":"JD Logistics,Beijing,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Digital economy report 2024: Shaping an environmentally sustainable and inclusive digital future"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0286382"},{"key":"ref3","volume-title":"JD Logistics, Official \u201cServices Products\u201d webpage of JD Logistics, 2025, jD Logistics offers \u201csafe, reliable, time-leading, and professional\u201d courier express services supported by a global, intelligent logistics infrastructure"},{"key":"ref4","volume-title":"Wikipedia contributors","year":"2025"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3390\/s19051005"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3390\/electronics13234733"},{"key":"ref7","volume-title":"Actionclip: A new paradigm for video action recognition","author":"Wang","year":"2021"},{"key":"ref8","volume-title":"Vilp: Knowledge exploration using vision, language, and pose embeddings for video action recognition","author":"Chaudhuri","year":"2023"},{"key":"ref9","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proceedings of the 38th International Conference on Machine Learning (ICML)","volume":"139","author":"Radford","year":"2021"},{"key":"ref10","volume":"abs\/2005.11401","author":"Lewis","year":"2020","journal-title":"Retrieval-augmented generation for knowledge-intensive NLP tasks"},{"key":"ref11","author":"Wang","year":"2024","journal-title":"YOLOv10: Real-time end-to-end object detection"},{"key":"ref12","first-page":"28","author":"J. J. B.","year":"2019","journal-title":"Warehouse & Distribution Science"},{"key":"ref13","first-page":"10","volume-title":"Chapter 6: Process in warehousing","year":"2023"},{"key":"ref14","article-title":"Space-time transformers","author":"Bertasius","year":"2021","journal-title":"ICCV"},{"key":"ref15","article-title":"Action transformer: Learning spatial-temporal representations for action recognition","author":"Girdhar","year":"2021","journal-title":"CVPR"},{"key":"ref16","author":"Dosovitskiy","year":"2020","journal-title":"Image transformer"},{"key":"ref17","volume-title":"Insights into the challenges and opportunities of large multi-modal models for blind and low vision users: A case study on clip","author":"Massiceti","year":"2024"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3390\/agriculture15111173"},{"key":"ref19","volume-title":"Temporal sequence-based object detection and action recognition in yolo-based methods","author":"Helian","year":"2025"},{"key":"ref20","volume-title":"Rethinking clip-based video learners in cross-domain open-vocabulary action recognition","author":"Lin","year":"2024"},{"key":"ref21","volume-title":"Bert: Pretraining of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019"},{"key":"ref22","volume":"abs\/1506.02640","author":"Redmon","year":"2016","journal-title":"You only look once: Unified, real-time object detection"},{"issue":"1","key":"ref23","first-page":"55","article-title":"A survey of perceptual hashing algorithms for image and video retrieval","volume":"8","author":"Morrison","year":"2018","journal-title":"Journal of Image and Video Processing"},{"issue":"2","key":"ref24","first-page":"45","article-title":"Image hashing based on perceptual feature for efficient image search","volume":"10","author":"Liu","year":"2017","journal-title":"International Journal of Image Processing"},{"key":"ref25","volume-title":"Ultralytics yolov5","year":"2023"},{"key":"ref26","first-page":"38","article-title":"Transformers: State-of-the-art natural language processing","volume-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations","author":"Wolf"},{"key":"ref27","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"Journal of Machine Learning Research"},{"key":"ref28","volume-title":"Yolov5: You only look once version 5","author":"Jocher","year":"2023"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"ref30","volume-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","author":"Li","year":"2022"},{"key":"ref31","volume-title":"Multiscale vision transformers for image recognition","author":"Chen","year":"2021"}],"event":{"name":"2025 IEEE International Conference on Big Data (BigData)","location":"Macau, China","start":{"date-parts":[[2025,12,8]]},"end":{"date-parts":[[2025,12,11]]}},"container-title":["2025 IEEE International Conference on Big Data (BigData)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11400704\/11400712\/11402227.pdf?arnumber=11402227","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T05:20:22Z","timestamp":1774588822000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11402227\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,8]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/bigdata66926.2025.11402227","relation":{},"subject":[],"published":{"date-parts":[[2025,12,8]]}}}