{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:00:58Z","timestamp":1777654858084,"version":"3.51.4"},"publisher-location":"Cham","reference-count":65,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031730382","type":"print"},{"value":"9783031730399","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"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\/978-3-031-73039-9_2","type":"book-chapter","created":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T14:57:07Z","timestamp":1730300227000},"page":"18-34","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["INTRA: Interaction Relationship-Aware Weakly Supervised Affordance Grounding"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-6310-8262","authenticated-orcid":false,"given":"Ji Ha","family":"Jang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9053-2224","authenticated-orcid":false,"given":"Hoigi","family":"Seo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8739-8960","authenticated-orcid":false,"given":"Se Young","family":"Chun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,31]]},"reference":[{"key":"2_CR1","unstructured":"Achiam, J., et\u00a0al.: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"2_CR2","unstructured":"Ahn, M., et al.: Do as I can and not as I say: grounding language in robotic affordances. arXiv:2204.01691 (2022)"},{"key":"2_CR3","unstructured":"Ahn, M., et\u00a0al.: Do as I can, not as I say: grounding language in robotic affordances. arXiv:2204.01691 (2022)"},{"key":"2_CR4","unstructured":"Amir, S., Gandelsman, Y., Bagon, S., Dekel, T.: Deep ViT features as dense visual descriptors. arXiv:2112.05814 (2021)"},{"key":"2_CR5","unstructured":"Ard\u00f3n, P., Pairet, \u00c8., Lohan, K.S., Ramamoorthy, S., Petrick, R.: Affordances in robotic tasks\u2013a survey. arXiv:2004.07400 (2020)"},{"key":"2_CR6","doi-asserted-by":"crossref","unstructured":"Ard\u00f3n, P., Pairet, E., Petrick, R.P., Ramamoorthy, S., Lohan, K.S.: Learning grasp affordance reasoning through semantic relations. RA-L, 4571\u20134578 (2019)","DOI":"10.1109\/LRA.2019.2933815"},{"key":"2_CR7","doi-asserted-by":"crossref","unstructured":"Bahl, S., Mendonca, R., Chen, L., Jain, U., Pathak, D.: Affordances from human videos as a versatile representation for robotics. In: CVPR, pp. 13778\u201313790 (2023)","DOI":"10.1109\/CVPR52729.2023.01324"},{"key":"2_CR8","doi-asserted-by":"crossref","unstructured":"Burke, C.J., Tobler, P.N., Baddeley, M., Schultz, W.: Neural mechanisms of observational learning. PNAS, 14431\u201314436 (2010)","DOI":"10.1073\/pnas.1003111107"},{"key":"2_CR9","doi-asserted-by":"crossref","unstructured":"Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: ICCV, pp. 9650\u20139660 (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"2_CR10","doi-asserted-by":"crossref","unstructured":"Chen, J., Gao, D., Lin, K.Q., Shou, M.Z.: Affordance grounding from demonstration video to target image. In: CVPR, pp. 6799\u20136808 (2023)","DOI":"10.1109\/CVPR52729.2023.00657"},{"key":"2_CR11","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: ICML, pp. 1597\u20131607 (2020)"},{"key":"2_CR12","doi-asserted-by":"crossref","unstructured":"Chen, X., He, K.: Exploring simple Siamese representation learning. In: CVPR, pp. 15750\u201315758 (2021)","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"2_CR13","doi-asserted-by":"crossref","unstructured":"Cornia, M., Baraldi, L., Serra, G., Cucchiara, R.: A deep multi-level network for saliency prediction. In: ICPR, pp. 3488\u20133493 (2016)","DOI":"10.1109\/ICPR.2016.7900174"},{"key":"2_CR14","doi-asserted-by":"crossref","unstructured":"Fang, K., Wu, T.L., Yang, D., Savarese, S., Lim, J.J.: Demo2Vec: reasoning object affordances from online videos. In: CVPR, pp. 2139\u20132147 (2018)","DOI":"10.1109\/CVPR.2018.00228"},{"key":"2_CR15","doi-asserted-by":"crossref","unstructured":"Gao, W., et al.: TS-CAM: token semantic coupled attention map for weakly supervised object localization. In: ICCV, pp. 2886\u20132895 (2021)","DOI":"10.1109\/ICCV48922.2021.00288"},{"key":"2_CR16","doi-asserted-by":"crossref","unstructured":"Geng, Y., An, B., Geng, H., Chen, Y., Yang, Y., Dong, H.: RLAfford: end-to-end affordance learning for robotic manipulation. In: ICRA, pp. 5880\u20135886 (2023)","DOI":"10.1109\/ICRA48891.2023.10161571"},{"key":"2_CR17","unstructured":"Gibson, J.: The Ecological Approach to Visual Perception. Resources for ecological psychology, Lawrence Erlbaum Associates (1986)"},{"key":"2_CR18","unstructured":"Hadjivelichkov, D., Zwane, S., Agapito, L., Deisenroth, M.P., Kanoulas, D.: One-shot transfer of affordance regions? AffCorrs! In: CoRL, pp. 550\u2013560 (2023)"},{"key":"2_CR19","doi-asserted-by":"crossref","unstructured":"Hou, Z., Yu, B., Qiao, Y., Peng, X., Tao, D.: Affordance transfer learning for human-object interaction detection. In: CVPR, pp. 495\u2013504 (2021)","DOI":"10.1109\/CVPR46437.2021.00056"},{"key":"2_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"789","DOI":"10.1007\/978-3-030-01225-0_46","volume-title":"Computer Vision \u2013 ECCV 2018","author":"Y Huang","year":"2018","unstructured":"Huang, Y., Cai, M., Li, Z., Sato, Y.: Predicting gaze in egocentric video by learning task-dependent attention transition. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11208, pp. 789\u2013804. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01225-0_46"},{"key":"2_CR21","unstructured":"Khosla, P., et al.: Supervised contrastive learning. In: NeurIPS, vol. 33, pp. 18661\u201318673 (2020)"},{"key":"2_CR22","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv:1412.6980 (2014)"},{"key":"2_CR23","doi-asserted-by":"crossref","unstructured":"K\u00fcmmerer, M., Wallis, T.S., Bethge, M.: DeepGaze II: reading fixations from deep features trained on object recognition. arXiv:1610.01563 (2016)","DOI":"10.1167\/17.10.1147"},{"key":"2_CR24","doi-asserted-by":"crossref","unstructured":"Li, F., et al.: Mask DINO: towards a unified transformer-based framework for object detection and segmentation. In: CVPR, pp. 3041\u20133050 (2023)","DOI":"10.1109\/CVPR52729.2023.00297"},{"key":"2_CR25","doi-asserted-by":"crossref","unstructured":"Li, G., Jampani, V., Sun, D., Sevilla-Lara, L.: LOCATE: localize and transfer object parts for weakly supervised affordance grounding. In: CVPR, pp. 10922\u201310931 (2023)","DOI":"10.1109\/CVPR52729.2023.01051"},{"key":"2_CR26","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv:2301.12597 (2023)"},{"key":"2_CR27","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: BLIP: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: ICML, pp. 12888\u201312900 (2022)"},{"key":"2_CR28","unstructured":"Li, J., Selvaraju, R., Gotmare, A., Joty, S., Xiong, C., Hoi, S.C.H.: Align before fuse: vision and language representation learning with momentum distillation. In: NeurIPS, pp. 9694\u20139705 (2021)"},{"key":"2_CR29","doi-asserted-by":"crossref","unstructured":"Liang, J., et al.: Code as policies: language model programs for embodied control. In: ICRA, pp. 9493\u20139500 (2023)","DOI":"10.1109\/ICRA48891.2023.10160591"},{"key":"2_CR30","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: NeurIPS (2023)"},{"key":"2_CR31","doi-asserted-by":"crossref","unstructured":"Luo, H., Zhai, W., Zhang, J., Cao, Y., Tao, D.: Grounded affordance from exocentric view. arXiv:2208.13196 (2022)","DOI":"10.1007\/s11263-023-01962-z"},{"key":"2_CR32","doi-asserted-by":"crossref","unstructured":"Luo, H., Zhai, W., Zhang, J., Cao, Y., Tao, D.: Learning affordance grounding from exocentric images. In: CVPR, pp. 2252\u20132261 (2022)","DOI":"10.1109\/CVPR52688.2022.00229"},{"key":"2_CR33","doi-asserted-by":"crossref","unstructured":"Luo, H., Zhai, W., Zhang, J., Cao, Y., Tao, D.: Learning visual affordance grounding from demonstration videos. IEEE Trans. Neural Netw. Learn. Syst. (2023)","DOI":"10.1109\/TNNLS.2023.3298638"},{"key":"2_CR34","unstructured":"Van\u00a0der Maaten, L., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. (2008)"},{"key":"2_CR35","unstructured":"MacQueen, J., et\u00a0al.: Some methods for classification and analysis of multivariate observations. In: Proceedings of the fifth Berkeley Symposium on Mathematical Statistics and Probability, vol.\u00a01, pp. 281\u2013297, Oakland, CA, USA (1967)"},{"key":"2_CR36","doi-asserted-by":"crossref","unstructured":"Mai, J., Yang, M., Luo, W.: Erasing integrated learning: a simple yet effective approach for weakly supervised object localization. In: CVPR, pp. 8766\u20138775 (2020)","DOI":"10.1109\/CVPR42600.2020.00879"},{"key":"2_CR37","doi-asserted-by":"crossref","unstructured":"Mees, O., Borja-Diaz, J., Burgard, W.: Grounding language with visual affordances over unstructured data. In: ICRA, pp. 11576\u201311582 (2023)","DOI":"10.1109\/ICRA48891.2023.10160396"},{"key":"2_CR38","unstructured":"Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. In: ICLR (2013)"},{"key":"2_CR39","doi-asserted-by":"crossref","unstructured":"Miller, G.A.: WordNet: a lexical database for English. Commun. ACM, 39\u201341 (1995)","DOI":"10.1145\/219717.219748"},{"key":"2_CR40","doi-asserted-by":"crossref","unstructured":"Myers, A., Teo, C.L., Ferm\u00fcller, C., Aloimonos, Y.: Affordance detection of tool parts from geometric features. In: ICRA, pp. 1374\u20131381 (2015)","DOI":"10.1109\/ICRA.2015.7139369"},{"key":"2_CR41","doi-asserted-by":"crossref","unstructured":"Nagarajan, T., Feichtenhofer, C., Grauman, K.: Grounded human-object interaction hotspots from video. In: ICCV, pp. 8688\u20138697 (2019)","DOI":"10.1109\/ICCV.2019.00878"},{"key":"2_CR42","doi-asserted-by":"crossref","unstructured":"Nguyen, A., Kanoulas, D., Caldwell, D.G., Tsagarakis, N.G.: Detecting object affordances with convolutional neural networks. In: IROS, pp. 2765\u20132770 (2016)","DOI":"10.1109\/IROS.2016.7759429"},{"key":"2_CR43","doi-asserted-by":"crossref","unstructured":"Nguyen, A., Kanoulas, D., Caldwell, D.G., Tsagarakis, N.G.: Object-based affordances detection with convolutional neural networks and dense conditional random fields. In: IROS, pp. 5908\u20135915 (2017)","DOI":"10.1109\/IROS.2017.8206484"},{"key":"2_CR44","doi-asserted-by":"crossref","unstructured":"Nguyen, T., et al.: Open-vocabulary affordance detection in 3D point clouds. In: IROS, pp. 5692\u20135698 (2023)","DOI":"10.1109\/IROS55552.2023.10341553"},{"key":"2_CR45","doi-asserted-by":"crossref","unstructured":"Ning, S., Qiu, L., Liu, Y., He, X.: HOICLIP: efficient knowledge transfer for HOI detection with vision-language models. In: CVPR, pp. 23507\u201323517 (2023)","DOI":"10.1109\/CVPR52729.2023.02251"},{"key":"2_CR46","unstructured":"Oquab, M., et\u00a0al.: DINOv2: learning robust visual features without supervision. arXiv:2304.07193 (2023)"},{"key":"2_CR47","unstructured":"Pan, J., et al.: SalGAN: visual saliency prediction with generative adversarial networks. arXiv:1701.01081 (2017)"},{"key":"2_CR48","doi-asserted-by":"crossref","unstructured":"Pan, X., et al.: Unveiling the potential of structure preserving for weakly supervised object localization. In: CVPR, pp. 11642\u201311651 (2021)","DOI":"10.1109\/CVPR46437.2021.01147"},{"key":"2_CR49","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.D.: GloVe: global vectors for word representation. In: EMNLP, pp. 1532\u20131543 (2014)","DOI":"10.3115\/v1\/D14-1162"},{"key":"2_CR50","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML, pp. 8748\u20138763 (2021)"},{"key":"2_CR51","unstructured":"Rana, K., Haviland, J., Garg, S., Abou-Chakra, J., Reid, I., Suenderhauf, N.: SayPlan: grounding large language models using 3D scene graphs for scalable task planning. In: CoRL (2023)"},{"key":"2_CR52","unstructured":"Rashid, A., et al.: Language embedded radiance fields for zero-shot task-oriented grasping. In: CoRL (2023)"},{"key":"2_CR53","doi-asserted-by":"crossref","unstructured":"Sawatzky, J., Srikantha, A., Gall, J.: Weakly supervised affordance detection. In: CVPR, pp. 2795\u20132804 (2017)","DOI":"10.1109\/CVPR.2017.552"},{"key":"2_CR54","doi-asserted-by":"crossref","unstructured":"Singh, I., et al.: ProgPrompt: generating situated robot task plans using large language models. In: ICRA, pp. 11523\u201311530 (2023)","DOI":"10.1109\/ICRA48891.2023.10161317"},{"key":"2_CR55","doi-asserted-by":"crossref","unstructured":"Tang, J., Zheng, G., Yu, J., Yang, S.: CoTDet: affordance knowledge prompting for task driven object detection. In: ICCV, pp. 3068\u20133078 (2023)","DOI":"10.1109\/ICCV51070.2023.00285"},{"key":"2_CR56","doi-asserted-by":"crossref","unstructured":"Wan, B., Tuytelaars, T.: Exploiting CLIP for zero-shot HOI detection requires knowledge distillation at multiple levels. In: WACV, pp. 1805\u20131815 (2024)","DOI":"10.1109\/WACV57701.2024.00182"},{"key":"2_CR57","doi-asserted-by":"crossref","unstructured":"Warren, W.: Perceiving affordances: visual guidance of stair climbing. J. Exp. Psychol. Hum. Percept. Perform., 683\u2013703 (1984)","DOI":"10.1037\/\/0096-1523.10.5.683"},{"key":"2_CR58","doi-asserted-by":"crossref","unstructured":"Xu, R., Chu, F.J., Tang, C., Liu, W., Vela, P.A.: An affordance keypoint detection network for robot manipulation. IEEE RA-L, 2870\u20132877 (2021)","DOI":"10.1109\/LRA.2021.3062560"},{"key":"2_CR59","unstructured":"Xue, Y., Gan, E., Ni, J., Joshi, S., Mirzasoleiman, B.: Investigating the benefits of projection head for representation learning. In: ICLR (2024)"},{"key":"2_CR60","doi-asserted-by":"crossref","unstructured":"Yu, S., Seo, P.H., Son, J.: Zero-shot referring image segmentation with global-local context features. In: CVPR, pp. 19456\u201319465 (2023)","DOI":"10.1109\/CVPR52729.2023.01864"},{"key":"2_CR61","unstructured":"Zhang, J., et al.: A tale of two features: stable diffusion complements DINO for zero-shot semantic correspondence. arXiv:2305.15347 (2023)"},{"key":"2_CR62","unstructured":"Zhang, X., et al.: Affordance-driven next-best-view planning for robotic grasping. In: CoRL (2023)"},{"key":"2_CR63","doi-asserted-by":"crossref","unstructured":"Zhao, X., Li, M., Weber, C., Hafez, M.B., Wermter, S.: Chat with the environment: interactive multimodal perception using large language models. arXiv:2303.08268 (2023)","DOI":"10.1109\/IROS55552.2023.10342363"},{"key":"2_CR64","doi-asserted-by":"crossref","unstructured":"Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., Torralba, A.: Learning deep features for discriminative localization. In: CVPR, pp. 2921\u20132929 (2016)","DOI":"10.1109\/CVPR.2016.319"},{"key":"2_CR65","unstructured":"Zhu, D., Chen, J., Shen, X., Li, X., Elhoseiny, M.: MiniGPT-4: enhancing vision-language understanding with advanced large language models. arXiv:2304.10592 (2023)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73039-9_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,30]],"date-time":"2024-10-30T15:15:55Z","timestamp":1730301355000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73039-9_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,31]]},"ISBN":["9783031730382","9783031730399"],"references-count":65,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73039-9_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,31]]},"assertion":[{"value":"31 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","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":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}