{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T07:50:28Z","timestamp":1777017028502,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":31,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12,17]]},"DOI":"10.1145\/3799830.3799842","type":"proceedings-article","created":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T06:45:08Z","timestamp":1777013108000},"page":"106-114","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["SPARK: Scene Prediction Augmented with Relational-Commonsense Knowledge"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-2340-6561","authenticated-orcid":false,"given":"Chaitanya","family":"Garg","sequence":"first","affiliation":[{"name":"Knowledgeable Computing and Reasoning Lab, Indraprastha Institute of Information Technology Delhi, New Delhi, Delhi, India"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-0177-3448","authenticated-orcid":false,"given":"Tanishq","family":"Jain","sequence":"additional","affiliation":[{"name":"Knowledgeable Computing and Reasoning Lab, Indraprastha Institute of Information Technology Delhi, New Delhi, Delhi, India"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1062-8929","authenticated-orcid":false,"given":"Sathyanarayanan","family":"Aakur","sequence":"additional","affiliation":[{"name":"Computer Science Department, Auburn University, Auburn, Alabama, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2421-3935","authenticated-orcid":false,"given":"Raghava","family":"Mutharaju","sequence":"additional","affiliation":[{"name":"Knowledgeable Computing and Reasoning Lab, Indraprastha Institute of Information Technology Delhi, New Delhi, Delhi, India"}]}],"member":"320","published-online":{"date-parts":[[2026,4,23]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00632"},{"key":"e_1_3_3_1_3_2","volume-title":"3rd Conference on Automated Knowledge Base Construction","author":"Chen Yihong","year":"2021","unstructured":"Yihong Chen, Pasquale Minervini, Sebastian Riedel, and Pontus Stenetorp. 2021. Relation Prediction as an Auxiliary Training Objective for Improving Multi-Relational Graph Representations. In 3rd Conference on Automated Knowledge Base Construction. https:\/\/openreview.net\/forum?id=Qa3uS3H7-Le"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4012"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","unstructured":"Yuren Cong Michael\u00a0Ying Yang and Bodo Rosenhahn. 2023. RelTR: Relation Transformer for Scene Graph Generation. IEEE Transactions on Pattern Analysis and Machine Intelligence 45 10 (2023) 11169\u201311183. 10.1109\/TPAMI.2023.3268066","DOI":"10.1109\/TPAMI.2023.3268066"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00207"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"publisher","unstructured":"Sepp Hochreiter and J\u00fcrgen Schmidhuber. 1997. Long short-term memory. Neural Computation 9 8 (1997) 1735\u20131780. 10.1162\/neco.1997.9.8.1735","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-77385-4_41"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"crossref","unstructured":"Xuan Kan Hejie Cui and Carl Yang. 2021. Zero-Shot Scene Graph Relation Prediction through Commonsense Knowledge Integration. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2107.05080 (2021).","DOI":"10.1007\/978-3-030-86520-7_29"},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-06981-9_6"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","unstructured":"Muhammad\u00a0Jaleed Khan John\u00a0G Breslin and Edward Curry. 2023. NeuSyRE: Neuro-Symbolic Visual Understanding and Reasoning Framework Based on Scene Graph Enrichment. Semantic Web (2023). 10.3233\/SW-233510","DOI":"10.3233\/SW-233510"},{"key":"e_1_3_3_1_13_2","volume-title":"International Conference on Learning Representations (ICLR)","author":"Kipf Thomas\u00a0N.","year":"2017","unstructured":"Thomas\u00a0N. Kipf and Max Welling. 2017. Semi-Supervised Classification with Graph Convolutional Networks. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","unstructured":"Ranjay Krishna Yuke Zhu Oliver Groth Justin Johnson Kenji Hata Joshua Kravitz Stephanie Chen Yannis Kalantidis Li-Jia Li David\u00a0A. Shamma Michael\u00a0S. Bernstein and Li Fei-Fei. 2017. Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations. International Journal of Computer Vision 123 1 (2017) 32\u201373. 10.1007\/s11263-016-0981-7","DOI":"10.1007\/s11263-016-0981-7"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"publisher","unstructured":"Yann LeCun L\u00e9on Bottou Yoshua Bengio and Patrick Haffner. 1998. Gradient-based learning applied to document recognition. Proc. IEEE 86 11 (1998) 2278\u20132324. 10.1109\/5.726791","DOI":"10.1109\/5.726791"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00131"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.469"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_51"},{"key":"e_1_3_3_1_19_2","volume-title":"International Conference on Learning Representations (ICLR)","author":"Mao Jiayuan","year":"2019","unstructured":"Jiayuan Mao, Chuang Gan, Pushmeet Kohli, Joshua\u00a0B. Tenenbaum, and Jiajun Wu. 2019. The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences from Natural Supervision. In International Conference on Learning Representations (ICLR). https:\/\/openreview.net\/forum?id=rJgMlhRctm"},{"key":"e_1_3_3_1_20_2","unstructured":"Tomas Mikolov Kai Chen Greg Corrado and Jeffrey Dean. 2013. Efficient Estimation of Word Representations in Vector Space. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1301.3781 (2013)."},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"publisher","unstructured":"George\u00a0A. Miller. 1995. WordNet: A Lexical Database for English. Commun. ACM 38 11 (1995) 39\u201341. 10.1145\/219717.219748","DOI":"10.1145\/219717.219748"},{"key":"e_1_3_3_1_22_2","first-page":"91","volume-title":"Advances in Neural Information Processing Systems","author":"Ren Shaoqing","year":"2015","unstructured":"Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun. 2015. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. In Advances in Neural Information Processing Systems, Vol.\u00a028. 91\u201399."},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","unstructured":"David\u00a0E Rumelhart Geoffrey\u00a0E Hinton and Ronald\u00a0J Williams. 1986. Learning representations by back-propagating errors. Nature 323 6088 (1986) 533\u2013536. 10.1038\/323533a0","DOI":"10.1038\/323533a0"},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"publisher","unstructured":"Franco Scarselli Marco Gori Ah\u00a0Chung Tsoi Markus Hagenbuchner and Gabriele Monfardini. 2009. The Graph Neural Network Model. IEEE Transactions on Neural Networks 20 1 (2009) 61\u201380. 10.1109\/TNN.2008.2005605","DOI":"10.1109\/TNN.2008.2005605"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11164"},{"key":"e_1_3_3_1_26_2","first-page":"5998","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan\u00a0N. Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention Is All You Need. In Advances in Neural Information Processing Systems (NeurIPS). 5998\u20136008."},{"key":"e_1_3_3_1_27_2","unstructured":"Petar Veli\u010dkovi\u0107 Guillem Cucurull Arantxa Casanova Adriana Romero Pietro Li\u00f2 and Yoshua Bengio. 2018. Graph Attention Networks. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1710.10903 (2018)."},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.5555\/3600270.3602662"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.121"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58592-1_36"},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00611"},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"publisher","unstructured":"Hao Zhou Yazhou Yang Tingjin Luo Jun Zhang and Shuohao Li. 2022. A unified deep sparse graph attention network for scene graph generation. Pattern Recognition 123 (2022) 108367. 10.1016\/j.patcog.2021.108367","DOI":"10.1016\/j.patcog.2021.108367"}],"event":{"name":"CODS 2025: 13th ACM IKDD International Conference on Data Science","location":"Pune India","acronym":"CODS 2025"},"container-title":["Proceedings of the 13th ACM IKDD International Conference on Data Science"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3799830.3799842","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T07:21:25Z","timestamp":1777015285000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3799830.3799842"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,17]]},"references-count":31,"alternative-id":["10.1145\/3799830.3799842","10.1145\/3799830"],"URL":"https:\/\/doi.org\/10.1145\/3799830.3799842","relation":{},"subject":[],"published":{"date-parts":[[2025,12,17]]},"assertion":[{"value":"2026-04-23","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}