{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,5]],"date-time":"2026-09-05T16:41:47Z","timestamp":1788626507437,"version":"build-2803163510"},"reference-count":58,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"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":[[2024,7,15]]},"DOI":"10.1109\/icme57554.2024.10687511","type":"proceedings-article","created":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T17:24:16Z","timestamp":1727717056000},"page":"1-5","source":"Crossref","is-referenced-by-count":4,"title":["COCO is \u201cALL\u201d You Need for Visual Instruction Fine-tuning"],"prefix":"10.1109","author":[{"given":"Xiaotian","family":"Han","sequence":"first","affiliation":[{"name":"ByteDance Inc"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiqi","family":"Wang","sequence":"additional","affiliation":[{"name":"ByteDance Inc"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bohan","family":"Zhai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Quanzeng","family":"You","sequence":"additional","affiliation":[{"name":"ByteDance Inc"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongxia","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"GPT-4 Technical Report","year":"2023"},{"key":"ref2","article-title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","author":"Touvron","year":"2023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-55560-2_5"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.33540\/2168"},{"key":"ref5","article-title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","author":"Dai","year":"2023"},{"key":"ref6","article-title":"MIMIC-IT: Multi-Modal In-Context Instruction Tuning","author":"Li","year":"2023"},{"key":"ref7","article-title":"LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understanding","author":"Zhang","year":"2023"},{"key":"ref8","article-title":"SVIT: Scaling up Visual Instruction Tuning","author":"Zhao","year":"2023"},{"key":"ref9","article-title":"LAMM: Language-Assisted Multi-Modal Instruction-Tuning Dataset, Framework, and Benchmark","author":"Yin","year":"2023"},{"key":"ref10","article-title":"To See is to Believe: Prompting GPT-4V for Better Visual Instruction Tuning","author":"Wang","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00904"},{"key":"ref12","article-title":"Microsoft COCO Captions: Data Collection and Evaluation Server","author":"Chen","year":"2015"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00380"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref17","article-title":"MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models","author":"Fu","year":"2023"},{"key":"ref18","article-title":"SEED-Bench-2: Benchmarking Multimodal Large Language Models","author":"Li","year":"2023"},{"key":"ref19","article-title":"MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI","author":"Yue","year":"2023"},{"key":"ref20","article-title":"MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities","author":"Yu","year":"2023"},{"key":"ref21","article-title":"InfiMM-Eval: Complex Open-Ended Reasoning Evaluation For Multi-Modal Large Language Models","author":"Han","year":"2023"},{"key":"ref22","article-title":"Improved Baselines with Visual Instruction Tuning","author":"Liu","year":"2023"},{"key":"ref23","article-title":"Microsoft COCO: Common Objects in Context","author":"Lin","year":"2015"},{"key":"ref24","article-title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","author":"Krishna","year":"2016"},{"key":"ref25","article-title":"MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Action","author":"Yang","year":"2023"},{"key":"ref26","article-title":"HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face","author":"Shen","year":"2023"},{"key":"ref27","article-title":"Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models","author":"Wu","year":"2023"},{"key":"ref28","article-title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond","author":"Bai","year":"2023"},{"key":"ref29","article-title":"Flamingo: a Visual Language Model for Few-Shot Learning","author":"Alayrac","year":"2022"},{"key":"ref30","article-title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","author":"Li","year":"2023"},{"key":"ref31","article-title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","author":"Zhu","year":"2023"},{"key":"ref32","article-title":"LAION-5B: An open large-scale dataset for training next generation image-text models","author":"Schuhmann","year":"2022"},{"key":"ref33","article-title":"COYO-700M: Image-Text Pair Dataset","author":"Byeon","year":"2022"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/2812802"},{"key":"ref35","article-title":"Multimodal C4: An Open, Billion-scale Corpus of Images Interleaved With Text","author":"Zhu","year":"2023"},{"key":"ref36","article-title":"CogVLM: Visual Expert for Pretrained Language Models","author":"Wang","year":"2023"},{"key":"ref37","article-title":"MMICL: Empowering Vision-language Model with Multi-Modal In-Context Learning","author":"Zhao","year":"2023"},{"key":"ref38","article-title":"ShareGPT4V: Improving Large Multi-Modal Models with Better Captions","author":"Chen","year":"2023"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.356"},{"key":"ref40","article-title":"Exploring Models and Data for Image Question Answering","author":"Ren","year":"2015"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.540"},{"key":"ref42","article-title":"The Color of the Cat is Gray: 1 Million Full-Sentences Visual Question Answering (FSVQA)","author":"Shin","year":"2016"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00566"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00331"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_9"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.217"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463259"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220036"},{"key":"ref49","article-title":"Interpretable Counting for Visual Question Answering","author":"Trott","year":"2018"},{"key":"ref50","article-title":"TallyQA: Answering Complex Counting Questions","author":"Acharya","year":"2018"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_34"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00439"},{"key":"ref53","article-title":"Point and Ask: Incorporating Pointing into Visual Question Answering","author":"Mani","year":"2022"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1152"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1184"},{"key":"ref56","article-title":"Sparkles: Unlocking Chats Across Multiple Images for Multimodal Instruction-Following Models","author":"Huang","year":"2023"},{"key":"ref57","article-title":"Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models","author":"Plummer","year":"2016"},{"key":"ref58","article-title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","author":"Wei","year":"2023"}],"event":{"name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","location":"Niagara Falls, ON, Canada","start":{"date-parts":[[2024,7,15]]},"end":{"date-parts":[[2024,7,19]]}},"container-title":["2024 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10685847\/10687354\/10687511.pdf?arnumber=10687511","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T05:56:16Z","timestamp":1727762176000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10687511\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,15]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/icme57554.2024.10687511","relation":{},"subject":[],"published":{"date-parts":[[2024,7,15]]}}}