{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,7]],"date-time":"2026-11-07T07:37:22Z","timestamp":1794037042942,"version":"4.8.0"},"reference-count":53,"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\/iccv51701.2025.00308","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"3215-3224","source":"Crossref","is-referenced-by-count":8,"title":["MISSRAG: Addressing the Missing Modality Challenge in Multimodal Large Language Models"],"prefix":"10.1109","author":[{"given":"Vittorio","family":"Pipoli","sequence":"first","affiliation":[{"name":"University of Modena and Reggio Emilia,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alessia","family":"Saporita","sequence":"additional","affiliation":[{"name":"University of Modena and Reggio Emilia,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Federico","family":"Bolelli","sequence":"additional","affiliation":[{"name":"University of Modena and Reggio Emilia,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marcella","family":"Cornia","sequence":"additional","affiliation":[{"name":"University of Modena and Reggio Emilia,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lorenzo","family":"Baraldi","sequence":"additional","affiliation":[{"name":"University of Modena and Reggio Emilia,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Costantino","family":"Grana","sequence":"additional","affiliation":[{"name":"University of Modena and Reggio Emilia,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rita","family":"Cucchiara","sequence":"additional","affiliation":[{"name":"University of Modena and Reggio Emilia,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Elisa","family":"Ficarra","sequence":"additional","affiliation":[{"name":"University of Modena and Reggio Emilia,Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text","volume-title":"NeurIPS","author":"Akbari","year":"2021"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p18-1208"},{"key":"ref4","article-title":"Qwen2.5-VL Technical Report","author":"Bai","year":"2025","journal-title":"arxiv preprint arxiv"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/IPAS.2018.8708893"},{"key":"ref6","article-title":"Visual RAG: Expanding MLLM visual knowledge without fine-tuning","author":"Bonomo","year":"2025","journal-title":"arxiv preprint arxiv"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00493"},{"key":"ref8","article-title":"Language Models are Few-Shot Learners","volume-title":"NeurIPS","author":"Brown","year":"2020"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00867"},{"key":"ref10","article-title":"X-LLM: Bootstrapping Advanced Large Language Models by Treating Multi-Modalities as Foreign Languages","author":"Chen","year":"2023","journal-title":"arxiv preprint arxiv"},{"key":"ref11","article-title":"VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset","author":"Chen","year":"2023","journal-title":"arxiv preprint arxiv"},{"key":"ref12","article-title":"BEATs: Audio Pre-Training with Acoustic Tokenizers","volume-title":"ICML","author":"Chen","year":"2023"},{"key":"ref13","article-title":"VideoLLaMA 2: Advancing SpatialTemporal Modeling and Audio Understanding in VideoLLMs","author":"Cheng","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref14","article-title":"Contrastive Chain-of-Thought Prompting","author":"Chia","year":"2023","journal-title":"arxiv preprint arxiv"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1036\/1097-8542.731800"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.707"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00210"},{"key":"ref18","article-title":"VITA: Towards OpenSource Interactive Omni Multimodal LLM","author":"Fu","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref19","article-title":"Multi-Modal Fusion Transformer for Video Retrieval","volume-title":"ECCV","author":"Gabeur","year":"2020"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref21","article-title":"ImageBind-LLM: Multi-modality Instruction Tuning","author":"Han","year":"2023","journal-title":"arxiv preprint arxiv"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02510"},{"key":"ref23","article-title":"Perceiver: General Perception with Iterative Attention","volume-title":"ICML","author":"Jaegle","year":"2021"},{"key":"ref24","article-title":"VILT: Vision-and-Language Transformer Without Convolution or Region Supervision","volume-title":"ICML","author":"Kim","year":"2021"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01435"},{"key":"ref26","article-title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","volume-title":"NeurIPS","author":"Lewis","year":"2020"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01852"},{"key":"ref28","article-title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","volume-title":"NeurIPS","author":"Li","year":"2021"},{"key":"ref29","article-title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","volume-title":"ICML","author":"Li","year":"2022"},{"key":"ref30","volume-title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","author":"Li","year":"2023"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3610661.3617602"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16330"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01764"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00798"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-industry.98"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00486"},{"key":"ref38","article-title":"IMFuse: A Mamba-based Fusion Block for Brain Tumor Segmentation with Incomplete Modalities","volume-title":"MICCAI","author":"Pipoli","year":"2025"},{"key":"ref39","article-title":"Language models are unsupervised multitask learners","volume-title":"Open-AI blog","author":"Radford","year":"2019"},{"key":"ref40","article-title":"Learning Transferable Visual Models From Natural Language Supervision","volume-title":"ICML","author":"Radford","year":"2021"},{"key":"ref41","first-page":"1316","article-title":"InContext Retrieval-Augmented Language Models","volume-title":"TACL","volume":"11","author":"Ram","year":"2023"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-032-05060-1_20"},{"key":"ref43","article-title":"Charades-Ego: A LargeScale Dataset of Paired Third and First Person Videos","author":"Sigurdsson","year":"2018","journal-title":"arxiv preprint arxiv"},{"key":"ref44","article-title":"LLaMA: Open and Efficient Foundation Language Models","author":"Touvron","year":"2023","journal-title":"arxiv preprint arxiv"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref46","article-title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","volume-title":"NeurIPS","author":"Wei","year":"2022"},{"key":"ref47","article-title":"Qwen2.5-Omni Technical Report","author":"Xu","year":"2025","journal-title":"arxiv preprint arxiv"},{"key":"ref48","article-title":"Qwen2 technical report","author":"Yang","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref49","article-title":"ReAct: Synergizing Reasoning and Acting in Language Models","volume-title":"ICLR","author":"Yao","year":"2023"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2016.94"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3532064"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.203"},{"key":"ref53","article-title":"ChatBridge: Bridging Modalities with Large Language Model as a Language Catalyst","author":"Zhao","year":"2023","journal-title":"arxiv preprint arxiv"}],"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\/11444435.pdf?arnumber=11444435","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:46:11Z","timestamp":1777531571000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444435\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00308","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}