{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T09:20:06Z","timestamp":1771924806958,"version":"3.50.1"},"reference-count":25,"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\/iccvw69036.2025.00637","type":"proceedings-article","created":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T20:44:02Z","timestamp":1771879442000},"page":"6117-6123","source":"Crossref","is-referenced-by-count":0,"title":["ByDeWay: Boost Your Multimodal LLM with DEpth Prompting in a Training-Free Way"],"prefix":"10.1109","author":[{"given":"Rajarshi","family":"Roy","sequence":"first","affiliation":[{"name":"Kalyani Government Engineering College,India"}]},{"given":"Devleena","family":"Das","sequence":"additional","affiliation":[{"name":"Kalyani Government Engineering College,India"}]},{"given":"Ankesh","family":"Banerjee","sequence":"additional","affiliation":[{"name":"Kalyani Government Engineering College,India"}]},{"given":"Arjya","family":"Bhattacharjee","sequence":"additional","affiliation":[{"name":"Kalyani Government Engineering College,India"}]},{"given":"Kousik","family":"Dasgupta","sequence":"additional","affiliation":[{"name":"Kalyani Government Engineering College,India"}]},{"given":"Subarna","family":"Tripathi","sequence":"additional","affiliation":[{"name":"Intel Labs,USA"}]}],"member":"263","reference":[{"key":"ref1","author":"Ahmed","year":"2023","journal-title":"Enhancing image captioning with depth information using a transformer-based framework"},{"key":"ref2","author":"Alayrac","year":"2022","journal-title":"Flamingo: a visual language model for few-shot learning"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref4","article-title":"Hallucination of multimodal large language models: A survey","author":"Bai","year":"2024","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00321"},{"key":"ref6","author":"Fooladgar","year":"2019","journal-title":"Multi-modal attention-based fusion model for semantic segmentation of rgb-depth images"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref8","author":"Li","year":"2023","journal-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref10","article-title":"Kosmos-2: Grounding multimodal large language models to the world","author":"Peng","year":"2023","journal-title":"arXiv preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01236"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462433"},{"key":"ref13","author":"Sun","year":"2025","journal-title":"Descriptive caption enhancement with visual specialists for multimodal perception"},{"key":"ref14","author":"Vichare","year":"2025","journal-title":"Pixie: A context-aware multi-agent multi-modal large language models (llm) architecture for digital marketing"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/194"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.emnlp-main.214"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.218"},{"key":"ref19","article-title":"Visionllm: large language model is also an open-ended decoder for vision-centric tasks","volume-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems","author":"Wang"},{"key":"ref20","author":"Wei","year":"2023","journal-title":"Chain-of-thought prompting elicits reasoning in large language models"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.111522"},{"key":"ref22","article-title":"List items one by one: A new data source and learning paradigm for multimodal llms","author":"Yan","year":"2024","journal-title":"COLM"},{"key":"ref23","author":"Yang","year":"2023","journal-title":"Set-of-mark prompting unleashes extraordinary visual grounding in gpt-4v"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00837"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.940"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision Workshops (ICCVW)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,20]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision Workshops (ICCVW)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11373940\/11374285\/11374560.pdf?arnumber=11374560","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T08:30:35Z","timestamp":1771921835000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11374560\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/iccvw69036.2025.00637","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}