{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T16:19:27Z","timestamp":1764260367636,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":38,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819787043"},{"type":"electronic","value":"9789819787050"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-981-97-8705-0_2","type":"book-chapter","created":{"date-parts":[[2025,2,7]],"date-time":"2025-02-07T14:37:16Z","timestamp":1738939036000},"page":"17-30","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Affordance Perception by\u00a0a\u00a0Knowledge-Guided Vision-Language Model with\u00a0Efficient Error Correction"],"prefix":"10.1007","author":[{"given":"Gertjan J.","family":"Burghouts","sequence":"first","affiliation":[]},{"given":"Marianne","family":"Schaaphok","sequence":"additional","affiliation":[]},{"given":"Michael","family":"van Bekkum","sequence":"additional","affiliation":[]},{"given":"Wouter","family":"Meijer","sequence":"additional","affiliation":[]},{"given":"Fieke","family":"Hillerstr\u00fcm","sequence":"additional","affiliation":[]},{"given":"Jell","family":"van Mil","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,2,8]]},"reference":[{"key":"2_CR1","unstructured":"Ahn, M., et al.: Do as i can, not as i say: grounding language in robotic affordances. In: Conference on Robotic Learning (2022)"},{"key":"2_CR2","unstructured":"Ardon, P., Pairet, E., Lohan, K.S., Ramamoorthy, S., Petrick, R.: Affordances in robotic tasks \u2013 a survey. arXiv:2004.07400 [cs] (2022)"},{"key":"2_CR3","doi-asserted-by":"crossref","unstructured":"Ardon, P., Pairet, E., Lohan, K.S., Ramamoorthy, S., Petrick, R.P.: Building affordance relations for robotic agents - a review. In: Proceedings of the Thirtieth Joint Conference on Artificial Intelligence IJCAI-21 - Survey Track (2021)","DOI":"10.24963\/ijcai.2021\/590"},{"key":"2_CR4","doi-asserted-by":"publisher","first-page":"2425","DOI":"10.3233\/FAIA200374","volume":"325","author":"D Be\u00dfler","year":"2020","unstructured":"Be\u00dfler, D., Porzel, R., Pomarlan, M., Beetz, M., Malaka, R., Bateman, J.: A formal model of affordances for flexible robotic task execution. Front. Artif. Intell. Appl. 325, 2425\u20132432 (2020). https:\/\/doi.org\/10.3233\/FAIA200374","journal-title":"Front. Artif. Intell. Appl."},{"key":"2_CR5","doi-asserted-by":"crossref","unstructured":"Bugliarello, E., Sartran, L., Agrawal, A., Hendricks, L.A., Nematzadeh, A.: Measuring progress in fine-grained vision-and-language understanding (2023)","DOI":"10.18653\/v1\/2023.acl-long.87"},{"key":"2_CR6","unstructured":"Burghouts, G.J., Hillerstr\u00f6m, F., Walraven, E., van Bekkum, M., Ruis, F., Sijs, J.: Anomaly detection in an open world by a neuro-symbolic program on zero-shot symbols. In: IROS 2022 Workshop Probabilistic Robotics in the Age of Deep Learning (2022)"},{"key":"2_CR7","unstructured":"Burghouts, G.J., et al.: Improved zero-shot object localization using contextualized prompts and objects in context. In: ICRA2023 Workshop on Pretraining for Robotics (PT4R) (2023)"},{"issue":"6","key":"2_CR8","doi-asserted-by":"publisher","first-page":"1458","DOI":"10.1109\/TBDATA.2023.3291558","volume":"9","author":"D Chen","year":"2023","unstructured":"Chen, D., Kong, D., Li, J., Wang, S., Yin, B.: A survey of visual affordance recognition based on deep learning. IEEE Trans. Big Data 9(6), 1458\u20131476 (2023). https:\/\/doi.org\/10.1109\/TBDATA.2023.3291558","journal-title":"IEEE Trans. Big Data"},{"key":"2_CR9","doi-asserted-by":"publisher","first-page":"271","DOI":"10.1109\/TCDS.2016.2543839","volume":"8","author":"F Cruz","year":"2016","unstructured":"Cruz, F., Magg, S., Weber, C., Wermter, S.: Training agents with interactive reinforcement learning and contextual affordances. IEEE Trans. Cogn. Dev. Syst. 8, 271\u2013284 (2016)","journal-title":"IEEE Trans. Cogn. Dev. Syst."},{"key":"2_CR10","doi-asserted-by":"publisher","unstructured":"Gaver, W.W.: Technology affordances. In: Conference on Human Factors in Computing Systems - Proceedings, pp. 79\u201384 (1991). https:\/\/doi.org\/10.1145\/108844.108856","DOI":"10.1145\/108844.108856"},{"key":"2_CR11","unstructured":"Gibson, J.J.: The Ecological Approach to Visual Perception. Psychology Press Classic Editions (1979)"},{"key":"2_CR12","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1177\/1059712321999421","volume":"4","author":"D Graves","year":"2022","unstructured":"Graves, D., G\u00fcnther, J., Luo, J.: Affordance as general value function: a computational model. Adapt. Behav. 4, 307\u2013327 (2022)","journal-title":"Adapt. Behav."},{"key":"2_CR13","unstructured":"Gu, X., Lin, T.Y., Kuo, W., Cui, Y.: Open-vocabulary detection via vision and language knowledge distillation. arXiv preprint arXiv:2104.13921 (2021)"},{"key":"2_CR14","doi-asserted-by":"crossref","unstructured":"Hart, S., Quispe, A.H., Lanighan, M.W., Gee, S.: Generalized affordance templates for mobile manipulation. In: 2022 International Conference on Robotics and Automation (ICRA), pp. 6240\u20136246 (2022)","DOI":"10.1109\/ICRA46639.2022.9812082"},{"key":"2_CR15","doi-asserted-by":"publisher","unstructured":"Hart, S., Dinh, P., Hambuchen, K.: The affordance template ROS package for robot task programming. In: 2015 IEEE International Conference on Robotics and Automation (ICRA), pp. 6227\u20136234 (2015). https:\/\/doi.org\/10.1109\/ICRA.2015.7140073","DOI":"10.1109\/ICRA.2015.7140073"},{"key":"2_CR16","unstructured":"Ho, S.B.: A general framework for the representation of function and affordance: a cognitive, causal, and grounded approach, and a step toward AGI (2022)"},{"key":"2_CR17","unstructured":"Huang, J., et al.: Scallop: from probabilistic deductive databases to scalable differentiable reasoning. In: Advances in Neural Information Processing Systems, vol.\u00a034, pp. 25134\u201325145 (2021)"},{"key":"2_CR18","unstructured":"Kommineni, V.K., K\u00f6nig-Ries, B., Samuel, S.: From human experts to machines: an LLM supported approach to ontology and knowledge graph construction (2024)"},{"key":"2_CR19","doi-asserted-by":"crossref","unstructured":"Li, L.H., et al.: Grounded language-image pre-training. In: CVPR (2022)","DOI":"10.1109\/CVPR52729.2023.02240"},{"key":"2_CR20","unstructured":"Li, P., et al.: TOIST: task oriented instance segmentation transformer with noun-pronoun distillation. In: Advances in Neural Information Processing Systems, vol.\u00a035, pp. 17597\u201317611 (2022)"},{"key":"2_CR21","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., et al.: Microsoft COCO: common objects in context. In: Computer Vision\u2013ECCV 2014: 13th European Conference, Part V, Zurich, Switzerland, 6\u201312 September 2014, pp. 740\u2013755. Springer (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"2_CR22","doi-asserted-by":"crossref","unstructured":"Montesano, L., Lopes, M., Bernardino, A., Santos-Victor., J.: Modeling affordances using Bayesian networks. In: IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 4102\u20134107 (2007)","DOI":"10.1109\/IROS.2007.4399511"},{"key":"2_CR23","unstructured":"Van\u00a0der Maaten, L., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9(11) (2008)"},{"issue":"4","key":"2_CR24","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1109\/TCDS.2016.2614992","volume":"8","author":"H Min","year":"2016","unstructured":"Min, H., Yi, C., Luo, R., Zhu, J., Bi, S.: Affordance research in developmental robotics: a survey. IEEE Trans. Cogn. Dev. Syst. 8(4), 237\u2013255 (2016). https:\/\/doi.org\/10.1109\/TCDS.2016.2614992","journal-title":"IEEE Trans. Cogn. Dev. Syst."},{"key":"2_CR25","unstructured":"Minderer, M., et al.: Simple open-vocabulary object detection with vision transformers. arXiv preprint arXiv:2205.06230 (2022)"},{"key":"2_CR26","volume-title":"The Design of Everyday Things","author":"DA Norman","year":"2013","unstructured":"Norman, D.A.: The Design of Everyday Things, 2nd edn. Basic Books, New York (2013)","edition":"2"},{"key":"2_CR27","unstructured":"OpenAI: ChatGPT (2023). Accessed 21 Apr 2023"},{"key":"2_CR28","unstructured":"OpenAI: GPT-4 technical report (2023)"},{"key":"2_CR29","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"key":"2_CR30","doi-asserted-by":"crossref","unstructured":"Sawatzky, J., Souri, Y., Grund, C., Gall, J.: What object should i use?-task driven object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7605\u20137614 (2019)","DOI":"10.1109\/CVPR.2019.00779"},{"key":"2_CR31","unstructured":"Speer, R., Havasi, C.: Representing general relational knowledge in concept net 5. In: Proceedings of the 8th International Conference on Language Resources and Evaluation, LREC 2012, pp. 3679\u20133686 (2012)"},{"key":"2_CR32","doi-asserted-by":"crossref","unstructured":"Tang, J., Zheng, G., Yu, J., Yang, S.: CotDet: affordance knowledge prompting for task driven object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3068\u20133078 (2023)","DOI":"10.1109\/ICCV51070.2023.00285"},{"key":"2_CR33","unstructured":"Vaticle: The polymorphic database powered by types (2023). https:\/\/typedb.com\/"},{"key":"2_CR34","doi-asserted-by":"crossref","unstructured":"Vo, D.M., Chen, H., Sugimoto, A., Nakayama, H.: NOC-REK: novel object captioning with retrieved vocabulary from external knowledge. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 17979\u201317987. IEEE (2022)","DOI":"10.1109\/CVPR52688.2022.01747"},{"issue":"19\u201320","key":"2_CR35","doi-asserted-by":"publisher","first-page":"1086","DOI":"10.1080\/01691864.2017.1394912","volume":"31","author":"N Yamanobe","year":"2017","unstructured":"Yamanobe, N., et al.: A brief review of affordance in robotic manipulation research. Adv. Robot. 31(19\u201320), 1086\u20131101 (2017). https:\/\/doi.org\/10.1080\/01691864.2017.1394912","journal-title":"Adv. Robot."},{"issue":"5","key":"2_CR36","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1177\/1059712317726357","volume":"25","author":"P Zech","year":"2017","unstructured":"Zech, P., Haller, S., Lakani, S.R., Ridge, B., Ugur, E., Piater, J.: Computational models of affordance in robotics: a taxonomy and systematic classification. Adapt. Behav. 25(5), 235\u2013271 (2017). https:\/\/doi.org\/10.1177\/1059712317726357","journal-title":"Adapt. Behav."},{"key":"2_CR37","unstructured":"Zhang, H., et al.: GLIPv2: Unifying localization and vision-language understanding (2022)"},{"key":"2_CR38","doi-asserted-by":"publisher","DOI":"10.1177\/1059712307084689","author":"E \u015eahin","year":"2007","unstructured":"\u015eahin, E., \u00c7akmak, M., Do\u011far, M.R., U\u011fur, E., \u00dc\u00e7oluk, G.: To afford or not to afford: a new formalization of affordances toward affordance-based robot control. Adapt. Behav. (2007). https:\/\/doi.org\/10.1177\/1059712307084689","journal-title":"Adapt. Behav."}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-8705-0_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,7]],"date-time":"2025-02-07T14:37:43Z","timestamp":1738939063000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-8705-0_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819787043","9789819787050"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-8705-0_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"8 February 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPRAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition and Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Jeju Island","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Korea (Republic of)","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 June 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 June 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icprai2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/brain.korea.ac.kr\/icprai2024\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}