{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,2]],"date-time":"2025-12-02T03:35:59Z","timestamp":1764646559454,"version":"3.40.5"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62325206","61936005","62306150"],"award-info":[{"award-number":["62325206","61936005","62306150"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Research and Development Program of Jiangsu Province","award":["BE2023016-4"],"award-info":[{"award-number":["BE2023016-4"]}]},{"name":"Natural Science Research Start-up Foundation of Recruiting Talents of Nanjing University of Posts and Telecommunications","award":["NY222115"],"award-info":[{"award-number":["NY222115"]}]},{"name":"Postgraduate Research and Practice Innovation Program of Jiangsu Province","award":["KYCX21_0735"],"award-info":[{"award-number":["KYCX21_0735"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2024.3521725","type":"journal-article","created":{"date-parts":[[2024,12,24]],"date-time":"2024-12-24T19:21:58Z","timestamp":1735068118000},"page":"2221-2231","source":"Crossref","is-referenced-by-count":1,"title":["Relation Inference Enhancement Network for Visual Commonsense Reasoning"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9183-3267","authenticated-orcid":false,"given":"Mengqi","family":"Yuan","sequence":"first","affiliation":[{"name":"Nanjing University of Posts and Telecommunications, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0513-138X","authenticated-orcid":false,"given":"Gengyun","family":"Jia","sequence":"additional","affiliation":[{"name":"Nanjing University of Posts and Telecommunications, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5956-831X","authenticated-orcid":false,"given":"Bing-Kun","family":"Bao","sequence":"additional","affiliation":[{"name":"Nanjing University of Posts and Telecommunications, Nanjing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00688"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612395"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475328"},{"issue":"PMLR","key":"ref4","first-page":"1931","article-title":"Unifying vision-and-language tasks via text generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Cho","year":"2021"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref6","first-page":"13","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume":"32","author":"Lu","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref7","first-page":"1","article-title":"VL-BERT: Pre-training of generic visual-linguistic representations","volume-title":"Proc. Int. Conf. Learn. Representations (ICLR)","author":"Su","year":"2020"},{"key":"ref8","first-page":"6616","article-title":"Large-scale adversarial training for vision-and-language representation learning","volume":"33","author":"Gan","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3275874"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3286259"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-15934-3_13"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3091882"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i5.20536"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3475731.3484957"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2021.107408"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.3390\/s21092911"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2991866"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612222"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3097171"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3330070"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3301279"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2883743"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3310042"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16428"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01234"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3137752"},{"key":"ref28","first-page":"839","article-title":"Rubi: Reducing unimodal biases for visual question answering","volume":"32","author":"Cadene","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/98"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/151"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3290012"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.317"},{"key":"ref33","first-page":"3784","article-title":"Debiased visual question answering from feature and sample perspectives","volume":"34","author":"Wen","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3269429"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3278992"},{"key":"ref36","first-page":"1","article-title":"Generalization through memorization: Nearest neighbor language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Khandelwal","year":"2020"},{"key":"ref37","first-page":"1","article-title":"Memorizing transformers","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wu","year":"2022"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00282"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01337"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01890"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.107823"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6715"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548022"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0987-1"},{"key":"ref46","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_44"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref49","first-page":"1","article-title":"Hadamard product for low-rank bilinear pooling","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kim","year":"2017"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.285"},{"key":"ref51","first-page":"2765","article-title":"Heterogeneous graph learning for visual commonsense reasoning","volume":"32","author":"Yu","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref52","first-page":"5670","article-title":"Connective cognition network for directional visual commonsense reasoning","volume":"32","author":"Wu","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref53","first-page":"15589","article-title":"TAB-VCR: Tags and attributes based VCR baselines","volume":"32","author":"Lin","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3279691"},{"article-title":"Gemini in reasoning: Unveiling commonsense in multimodal large language models","year":"2023","author":"Wang","key":"ref55"},{"article-title":"GPT-4 technical report","year":"2023","author":"Achiam","key":"ref56"},{"article-title":"GPT4RoI: Instruction tuning large language model on Region-of-Interest","year":"2023","author":"Zhang","key":"ref57"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01589"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.202"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/10814063.pdf?arnumber=10814063","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,13]],"date-time":"2025-05-13T17:47:40Z","timestamp":1747158460000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10814063\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/tmm.2024.3521725","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"type":"print","value":"1520-9210"},{"type":"electronic","value":"1941-0077"}],"subject":[],"published":{"date-parts":[[2025]]}}}