{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T13:22:09Z","timestamp":1778851329824,"version":"3.51.4"},"reference-count":53,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,9,1]],"date-time":"2024-09-01T00:00:00Z","timestamp":1725148800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Project of Science and Technology Research and Development Plan of China Railway Corporation","award":["N2023J044"],"award-info":[{"award-number":["N2023J044"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2024,9]]},"DOI":"10.1109\/tnnls.2024.3385436","type":"journal-article","created":{"date-parts":[[2024,4,23]],"date-time":"2024-04-23T19:18:44Z","timestamp":1713899924000},"page":"11872-11883","source":"Crossref","is-referenced-by-count":5,"title":["Relation-Aware Heterogeneous Graph Network for Learning Intermodal Semantics in Textbook Question Answering"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8972-2824","authenticated-orcid":false,"given":"Sai","family":"Zhang","sequence":"first","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunjie","family":"Wu","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3931-3886","authenticated-orcid":false,"given":"Xiaowang","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8158-7453","authenticated-orcid":false,"given":"Zhiyong","family":"Feng","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5501-9575","authenticated-orcid":false,"given":"Liang","family":"Wan","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0081-1703","authenticated-orcid":false,"given":"Zhiqiang","family":"Zhuang","sequence":"additional","affiliation":[{"name":"College of Intelligence and Computing, Tianjin University, Tianjin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Retrieving and reading: A comprehensive survey on open-domain question answering","author":"Zhu","year":"2101","journal-title":"arXiv:2101.00774"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.74"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.571"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2018.8486468"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3294991"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109441"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00385"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1347"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3089140"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3231463"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1907.11692"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.441"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86380-7_8"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109588"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3180563"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330961"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2019.00203"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380027"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_28"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.1400"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3105284"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25169"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109337"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20068-7_31"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02318"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s44196-023-00233-6"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612850"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108153"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3104937"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-11018-5_9"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2023.111174"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098036"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3190922"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3232709"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26283"},{"key":"ref37","article-title":"Visual ChatGPT: Talking, drawing and editing with visual foundation models","author":"Wu","year":"2023","journal-title":"arXiv:2303.04671"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.ijcnlp-main.45"},{"key":"ref39","article-title":"HuggingGPT: Solving AI tasks with ChatGPT and its friends in hugging face","author":"Shen","year":"2023","journal-title":"arXiv:2303.17580"},{"key":"ref40","first-page":"19822","article-title":"Cogview: Mastering text-to-image generation via transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Ding"},{"key":"ref41","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"arXiv:2301.12597"},{"key":"ref42","article-title":"Language is not all you need: Aligning perception with language models","author":"Huang","year":"2023","journal-title":"arXiv:2302.14045"},{"key":"ref43","article-title":"Grounding language models to images for multimodal inputs and outputs","author":"Koh","year":"2023","journal-title":"arXiv:2301.13823"},{"key":"ref44","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Alayrac"},{"key":"ref45","article-title":"LLaMA-adapter: Efficient fine-tuning of language models with zero-init attention","author":"Zhang","year":"2023","journal-title":"arXiv:2303.16199"},{"key":"ref46","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv:2302.13971"},{"key":"ref47","article-title":"Sparks of artificial general intelligence: Early experiments with GPT-4","author":"Bubeck","year":"2023","journal-title":"arXiv:2303.12712"},{"key":"ref48","article-title":"Enhancing textbook question answering task with large language models and retrieval augmented generation","author":"Alawwad","year":"2024","journal-title":"arXiv:2402.05128"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9533575"},{"key":"ref50","first-page":"557","article-title":"CPM-Nets: Cross partial multi-view networks","volume-title":"Proc. NIPS","author":"Zhang"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_15"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10663876\/10506973.pdf?arnumber=10506973","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T18:13:40Z","timestamp":1725473620000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10506973\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9]]},"references-count":53,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2024.3385436","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9]]}}}