{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T06:45:38Z","timestamp":1767077138946,"version":"3.48.0"},"reference-count":56,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T00:00:00Z","timestamp":1764720000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T00:00:00Z","timestamp":1764720000000},"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":[[2025,12,3]]},"DOI":"10.1109\/dicta68720.2025.11302471","type":"proceedings-article","created":{"date-parts":[[2025,12,29]],"date-time":"2025-12-29T18:36:22Z","timestamp":1767033382000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Can Current AI Models Count What We Mean, Not What They See? A Benchmark and Systematic Evaluation"],"prefix":"10.1109","author":[{"given":"Gia Khanh","family":"Nguyen","sequence":"first","affiliation":[{"name":"Australian Institute for Machine Learning, University of Adelaide,SA,Australia"}]},{"given":"Yifeng","family":"Huang","sequence":"additional","affiliation":[{"name":"Stony Brook University,Stony Brook,NY,USA"}]},{"given":"Minh","family":"Hoai","sequence":"additional","affiliation":[{"name":"Australian Institute for Machine Learning, University of Adelaide,SA,Australia"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16170"},{"key":"ref2","article-title":"Open-world text-specified object counting","author":"Amini-Naieni","year":"2023","journal-title":"arXiv"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1547"},{"key":"ref4","article-title":"Qwen2. 5-vl technical report","author":"Bai","year":"2025","journal-title":"arXiv"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00465"},{"key":"ref6","article-title":"A survey on class-agnostic counting: Advancements from reference-based to open-world text-guided approaches","author":"Ciampi","year":"2025","journal-title":"arXiv"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00774"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.5220\/0010303401850195"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01607"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01730"},{"key":"ref11","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024","journal-title":"arXiv"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01396"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-19390-8_48"},{"key":"ref14","article-title":"Abc easy as123: A blind counter for exemplar-free multi-class class-agnostic counting","author":"Hobley","year":"2024","journal-title":"ECCV"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.446"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58542-6_45"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02039"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01615"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611789"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00476"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.28050"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_34"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00120"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00192"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28134"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00131"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58586-0_15"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00663"},{"key":"ref30","article-title":"Class-agnostic counting","author":"Lu","year":"2018","journal-title":"In ACCV"},{"key":"ref31","article-title":"Ovis: Structural embedding alignment for multimodal large language model","author":"Lu","year":"2024","journal-title":"arXiv"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6848"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i18.34151"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20044-1_20"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00294"},{"key":"ref36","article-title":"A novel unified architecture for low-shot counting by detection and segmentation","author":"Pelhan","year":"2024","journal-title":"NeurIPS"},{"key":"ref37","article-title":"Dave-a detect-andverify paradigm for low-shot counting","author":"Pelhan","year":"2024","journal-title":"In CVPR"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-26316-3_5"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_17"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00340"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-69541-5_23"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2020.2974830"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00931"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2020.3035969"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2023.04.018"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00335"},{"key":"ref47","article-title":"Distribution matching for crowd counting","author":"Wang","year":"2020","journal-title":"In NeurIPS"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28396"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1080\/21681163.2016.1149104"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00847"},{"key":"ref51","article-title":"Zeroshot object counting","author":"Xu","year":"2023","journal-title":"In CVPR"},{"key":"ref52","article-title":"Classagnostic few-shot object counting","author":"Yang","year":"2021","journal-title":"In Proc. WACV"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00625"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.70"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72652-1_22"},{"journal-title":"Internvl3: Exploring advanced training and test-time recipes for open-source multimodal models","year":"2025","author":"Zhu","key":"ref56"}],"event":{"name":"2025 International Conference on Digital Image Computing: Techniques and Applications (DICTA)","start":{"date-parts":[[2025,12,3]]},"location":"Adelaide, Australia","end":{"date-parts":[[2025,12,5]]}},"container-title":["2025 International Conference on Digital Image Computing: Techniques and Applications (DICTA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11302408\/11302416\/11302471.pdf?arnumber=11302471","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T06:40:57Z","timestamp":1767076857000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11302471\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,3]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/dicta68720.2025.11302471","relation":{},"subject":[],"published":{"date-parts":[[2025,12,3]]}}}