{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T16:59:33Z","timestamp":1783529973144,"version":"3.55.0"},"reference-count":59,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00178","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"1825-1835","source":"Crossref","is-referenced-by-count":2,"title":["HOLa: Zero-Shot HOI Detection with Low-Rank Decomposed VLM Feature Adaptation"],"prefix":"10.1109","author":[{"given":"Qinqian","family":"Lei","sequence":"first","affiliation":[{"name":"National University of Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Mississippi"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Robby T.","family":"Tan","sequence":"additional","affiliation":[{"name":"National University of Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6616"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0034"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00048"},{"key":"ref6","article-title":"Qahoi: query-based anchors for human-object interaction detection","author":"Chen","year":"2021","journal-title":"arXiv preprint"},{"key":"ref7","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref8","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00872"},{"key":"ref11","article-title":"Open-vocabulary object detection via vision and language knowledge distillation","author":"Gu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_35"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00056"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01441"},{"key":"ref16","article-title":"Lora: Low-rank adaptation of large language models","author":"Edward","year":"2021","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00286"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01594-9"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1775"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00596"},{"key":"ref23","first-page":"1","article-title":"Exploring conditional multi-modal prompts for zero-shot hoi detection","volume-title":"European Conference on Computer Vision","author":"Lei","year":"2024"},{"key":"ref24","first-page":"1288812900. PMLR","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"International Conference on Machine Learning","author":"Li","year":"2022"},{"key":"ref25","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0924"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01949"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02484"},{"key":"ref30","article-title":"Visual instruction tuning","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems, 36"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02665"},{"key":"ref32","article-title":"Clip4hoi: Towards adapting clip for practical zero-shot hoi detection","author":"Mao","year":"2024","journal-title":"Advances in Neural Information Processing Systems, 36"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_42"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02251"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01645"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01895"},{"key":"ref37","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref38","article-title":"Regularizing cnns with locally constrained decorrelations","author":"Rodr\u00edguez","year":"2016","journal-title":"arXiv preprint"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1038"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01372"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00516"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01027"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02642"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01687"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25385"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01466"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20086-1_8"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02249"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2712"},{"key":"ref50","article-title":"Unified vision and language prompt learning","author":"Zang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01416"},{"key":"ref52","first-page":"13319","article-title":"Spatially conditioned graphs for detecting human-object interactions","volume-title":"In Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Frederic","year":"2021"},{"key":"ref53","first-page":"20104","article-title":"Efficient two-stage detection of human-object interactions with a novel unary-pairwise transformer","volume-title":"In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Frederic","year":"2022"},{"key":"ref54","first-page":"10411","article-title":"Exploring predicate visual context in detecting of human-object interactions","volume-title":"In Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Frederic","year":"2023"},{"key":"ref55","article-title":"Perceiving 3d human-object spatial arrangements from a single image in the wild","volume-title":"In Computer Vision-ECCV 2020: 16th European Conference, Glasgow, UK","author":"Jason","year":"2020"},{"key":"ref56","article-title":"Tip-adapter: Training-free clip-adapter for better visionlanguage modeling","author":"Zhang","year":"2021","journal-title":"arXiv preprint"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01165"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444920.pdf?arnumber=11444920","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:00:38Z","timestamp":1777611638000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444920\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00178","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}