{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,25]],"date-time":"2026-07-25T05:23:47Z","timestamp":1784957027355,"version":"3.55.0"},"reference-count":62,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"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":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00119","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"1159-1169","source":"Crossref","is-referenced-by-count":2,"title":["BanglaProtha: Evaluating Vision Language Models in Underrepresented Long-tail Cultural Contexts"],"prefix":"10.1109","author":[{"given":"Md","family":"Fahim","sequence":"first","affiliation":[{"name":"Penta Global Limited"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Md Sakib Ul","family":"Rahman","sequence":"additional","affiliation":[{"name":"University of Maryland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Akm Moshiur","family":"Rahman","sequence":"additional","affiliation":[{"name":"Independent University,CCDS,Bangladesh"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Md Farhan","family":"Ishmam","sequence":"additional","affiliation":[{"name":"University of Utah"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Md Tasmim","family":"Rahman","sequence":"additional","affiliation":[{"name":"Penta Global Limited"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fariha Tanjim","family":"Shifat","sequence":"additional","affiliation":[{"name":"Penta Global Limited"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fabiha","family":"Haider","sequence":"additional","affiliation":[{"name":"Penta Global Limited"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Md Farhad","family":"Alam Bhuiyan","sequence":"additional","affiliation":[{"name":"Penta Global Limited"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","author":"Abdin","year":"2024","journal-title":"Phi-3 technical report: A highly capable language model locally on your phone"},{"key":"ref2","article-title":"Phi-4 technical report","author":"Abdin","year":"2024"},{"key":"ref3","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCIT51783.2020.9392697"},{"key":"ref5","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Alexey","year":"2020"},{"key":"ref6","volume-title":"Model card addendum for Claude 3","year":"2024"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-032-06078-5_27"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3590773"},{"key":"ref10","article-title":"Paligemma: A versatile 3b vlm for transfer","author":"Beyer","year":"2024"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.385"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-naacl.98"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2025.3540388"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.c3nlp-1.7"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.176"},{"key":"ref16","first-page":"24185","article-title":"Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"Chen"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W16-3210"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-51090-4"},{"key":"ref19","article-title":"Are you talking to a machine? dataset and methods for multilingual image question","volume":"28","author":"Gao","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref20","article-title":"Introducing Gemini 2.0: Our new AI model for the agentic era","year":"2024"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.aacl-main.90"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-naacl.403"},{"issue":"2","key":"ref24","first-page":"3","article-title":"Lora: Low-rank adaptation of large language models","volume":"1","author":"Hu","year":"2022","journal-title":"ICLR"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102270"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3530190.3534837"},{"key":"ref27","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"International conference on machine learning","author":"Jia"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"ref29","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International conference on machine learning","author":"Li"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref31","author":"Liu","year":"2024","journal-title":"Llava-next: Improved reasoning, ocr, and world knowledge"},{"key":"ref32","article-title":"Culturevlm: Characterizing and improving cultural understanding of vision-language models for over 100 countries","author":"Liu","year":"2025"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref35","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28212"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"ref38","article-title":"Smolvlm: Redefining small and efficient multimodal models","author":"Marafioti","year":"2025"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00331"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.loresmt-1.7"},{"key":"ref41","article-title":"Llama 3: Connecting the next generation of ai with vision, edge, and mobile devices at Connect 2024","year":"2024"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s42979-021-00975-0"},{"key":"ref43","volume-title":"Bengali culture over a thousand years","author":"Murshid","year":"2018"},{"key":"ref44","article-title":"Having beer after prayer? measuring cultural bias in large language models","author":"Naous","year":"2023"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.329"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.naacl-long.43"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01234"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.1066"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.196"},{"key":"ref50","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCIT57492.2022.10055205"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2019.06.100"},{"key":"ref53","article-title":"Cvqa: Culturally-diverse multilingual visual question answering benchmark","author":"Romero","year":"2024"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_9"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref56","article-title":"Gemma 3 technical report","author":"Team","year":"2025"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01822"},{"key":"ref58","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1800"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"ref61","article-title":"Tcc-bench: Benchmarking the traditional chinese culture understanding capabilities of mllms","author":"Xu","year":"2025"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-demos.38"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492539.pdf?arnumber=11492539","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:09:34Z","timestamp":1778047774000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492539\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":62,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00119","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}