{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T20:28:11Z","timestamp":1780086491065,"version":"3.54.0"},"reference-count":71,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Center for Applied Research in Artificial Intelligence"},{"name":"DAPA and ADD","award":["UD230017TD"],"award-info":[{"award-number":["UD230017TD"]}]},{"DOI":"10.13039\/501100010418","name":"IITP","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100010418","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Korea Government (MSIT), Development of Previsional Intelligence based on Long-Term Visual Memory Network","award":["2020-0-00004"],"award-info":[{"award-number":["2020-0-00004"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,9]]},"DOI":"10.1109\/tcsvt.2024.3383914","type":"journal-article","created":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T20:06:11Z","timestamp":1712001971000},"page":"7975-7985","source":"Crossref","is-referenced-by-count":15,"title":["Integrating Language-Derived Appearance Elements With Visual Cues in Pedestrian Detection"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4486-9026","authenticated-orcid":false,"given":"Sungjune","family":"Park","sequence":"first","affiliation":[{"name":"Image and Video Systems Laboratory, School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Yuseong-gu, Daejeon, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6524-8689","authenticated-orcid":false,"given":"Hyunjun","family":"Kim","sequence":"additional","affiliation":[{"name":"Image and Video Systems Laboratory, School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Yuseong-gu, Daejeon, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5306-6853","authenticated-orcid":false,"given":"Yong Man","family":"Ro","sequence":"additional","affiliation":[{"name":"Image and Video Systems Laboratory, School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Yuseong-gu, Daejeon, Republic of Korea"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.lindif.2023.102274"},{"key":"ref2","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Brown"},{"key":"ref3","article-title":"CTRL: A conditional transformer language model for controllable generation","author":"Shirish Keskar","year":"2019","journal-title":"arXiv:1909.05858"},{"key":"ref4","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.740"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3235704"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3245584"},{"key":"ref8","article-title":"Open-vocabulary object detection via vision and language knowledge distillation","author":"Gu","year":"2021","journal-title":"arXiv:2104.13921"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01839"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01456"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00637"},{"key":"ref12","article-title":"VisionLLM: Large language model is also an open-ended decoder for vision-centric tasks","author":"Wang","year":"2023","journal-title":"arXiv:2305.11175"},{"key":"ref13","article-title":"PaLM: Scaling language modeling with pathways","author":"Chowdhery","year":"2022","journal-title":"arXiv:2204.02311"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01438"},{"issue":"1","key":"ref15","first-page":"5485","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3000223"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3076466"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3060162"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3245613"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2883558"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2913114"},{"key":"ref22","article-title":"CrowdHuman: A benchmark for detecting human in a crowd","author":"Shao","year":"2018","journal-title":"arXiv:1805.00123"},{"key":"ref23","article-title":"WIDER face and pedestrian challenge 2018: Methods and results","author":"Change Loy","year":"2019","journal-title":"arXiv:1902.06854"},{"key":"ref24","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv:2302.13971"},{"key":"ref25","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv:2307.09288"},{"key":"ref26","article-title":"No language left behind: Scaling human-centered machine translation","author":"Team","year":"2022","journal-title":"arXiv:2207.04672"},{"key":"ref27","first-page":"10755","article-title":"Falcon-40b: An open large language model with state-of-the-art performance","volume-title":"Proc. Findings Assoc. Comput. Linguistics: ACL","author":"Almazrouei"},{"key":"ref28","article-title":"MT5: A massively multilingual pre-trained text-to-text transformer","author":"Xue","year":"2020","journal-title":"arXiv:2010.11934"},{"key":"ref29","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018","journal-title":"OpenAI Blog"},{"key":"ref30","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. ICML","author":"Radford"},{"key":"ref31","first-page":"1","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Lu"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3233554"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3284979"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3253548"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2023.3301933"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/SMC.2013.737"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_45"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6690"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16313"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25124"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3079141"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2015.2397199"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2016.2581660"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2015.2501940"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2749620"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3020691"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00093"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00708"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3273853"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2830102"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3076733"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00644"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/219717.219748"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-90-481-8847-5_10"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref56","article-title":"LAION-400M: Open dataset of CLIP-filtered 400 million image-text pairs","author":"Schuhmann","year":"2021","journal-title":"arXiv:2111.02114"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.448"},{"key":"ref58","article-title":"VT-CLIP: Enhancing vision-language models with visual-guided texts","author":"Qiu","year":"2021","journal-title":"arXiv:2112.02399"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref61","volume-title":"Natural Language Processing With Python: Analyzing Text With the Natural Language Toolkit","author":"Bird","year":"2009"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.146"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01422"},{"key":"ref64","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020","journal-title":"arXiv:2010.04159"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108605"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref68","first-page":"15558","article-title":"K-lite: Learning transferable visual models with external knowledge","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Shen"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01756"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00562"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10700029\/10487978.pdf?arnumber=10487978","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,9]],"date-time":"2025-01-09T20:13:58Z","timestamp":1736453638000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10487978\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9]]},"references-count":71,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3383914","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9]]}}}