{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,11]],"date-time":"2026-01-11T12:06:30Z","timestamp":1768133190995,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":36,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819785100","type":"print"},{"value":"9789819785117","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"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\/978-981-97-8511-7_34","type":"book-chapter","created":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T05:10:51Z","timestamp":1730524251000},"page":"481-495","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["MIT: Multi-cue Injected Transformer for Two-Stage HOI Detection"],"prefix":"10.1007","author":[{"given":"Weilong","family":"Peng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qingfeng","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Keke","family":"Tang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhihao","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meng","family":"Xing","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meie","family":"Fang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,3]]},"reference":[{"key":"34_CR1","doi-asserted-by":"crossref","unstructured":"Cai, J., Liu, H., Ding, R., Li, W., Wu, J., Ban, M.: Htnet: Human topology aware network for 3d human pose estimation. In: IEEE International Conference on Acoustics, Speech and Signal Processing, pp.\u00a01\u20135. IEEE (2023)","DOI":"10.1109\/ICASSP49357.2023.10095949"},{"key":"34_CR2","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: European Conference on Computer Vision, pp. 213\u2013229. Springer (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"34_CR3","doi-asserted-by":"crossref","unstructured":"Chao, Y.W., Liu, Y., Liu, X., Zeng, H., Deng, J.: Learning to detect human-object interactions. In: Winter Conference on Applications of Computer Vision, pp. 381\u2013389. IEEE (2018)","DOI":"10.1109\/WACV.2018.00048"},{"key":"34_CR4","doi-asserted-by":"crossref","unstructured":"Dong, L., Li, Z., Xu, K., Zhang, Z., Yan, L., Zhong, S., Zou, X.: Category-aware transformer network for better human-object interaction detection. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19538\u201319547 (2022)","DOI":"10.1109\/CVPR52688.2022.01893"},{"key":"34_CR5","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"34_CR6","doi-asserted-by":"crossref","unstructured":"Du, R., Chang, D., Bhunia, A.K., Xie, J., Ma, Z., Song, Y.Z., Guo, J.: Fine-grained visual classification via progressive multi-granularity training of jigsaw patches. In: European Conference on Computer Vision, pp. 153\u2013168. Springer (2020)","DOI":"10.1007\/978-3-030-58565-5_10"},{"key":"34_CR7","unstructured":"Gao, C., Zou, Y., Huang, J.B.: ICAN: Instance-centric attention network for human-object interaction detection. In: British Machine Vision Conference (Jan 2018)"},{"key":"34_CR8","doi-asserted-by":"crossref","unstructured":"Girshick, R.: Fast r-cnn. In: IEEE International Conference on Computer Vision, pp. 1440\u20131448 (2015)","DOI":"10.1109\/ICCV.2015.169"},{"key":"34_CR9","unstructured":"Gupta, S., Malik, J.: Visual semantic role labeling. arXiv preprint arXiv:1505.04474 (2015)"},{"key":"34_CR10","doi-asserted-by":"crossref","unstructured":"Iftekhar, A.S.M., Chen, H., Kundu, K., Li, X., Tighe, J., Modolo, D.: What to look at and where: semantic and spatial refined transformer for detecting human-object interactions. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5353\u20135363. Springer (2022)","DOI":"10.1109\/CVPR52688.2022.00528"},{"key":"34_CR11","doi-asserted-by":"crossref","unstructured":"Kim, B., Choi, T., Kang, J., Kim, H.J.: Uniondet: Union-level detector towards real-time human-object interaction detection. In: European Conference on Computer Vision, pp. 498\u2013514. Springer (2020)","DOI":"10.1007\/978-3-030-58555-6_30"},{"key":"34_CR12","doi-asserted-by":"crossref","unstructured":"Kim, B., Lee, J., Kang, J., Kim, E.S., Kim, H.J.: Hotr: End-to-end human-object interaction detection with transformers. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 74\u201383 (2021)","DOI":"10.1109\/CVPR46437.2021.00014"},{"key":"34_CR13","doi-asserted-by":"crossref","unstructured":"Li, Y.L., Liu, X., Lu, H., Wang, S., Liu, J., Li, J., Lu, C.: Detailed 2d-3d joint representation for human-object interaction. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10166\u201310175 (2020)","DOI":"10.1109\/CVPR42600.2020.01018"},{"key":"34_CR14","first-page":"5011","volume":"33","author":"YL Li","year":"2020","unstructured":"Li, Y.L., Liu, X., Wu, X., Li, Y., Lu, C.: Hoi analysis: integrating and decomposing human-object interaction. Adv. Neural. Inf. Process. Syst. 33, 5011\u20135022 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"34_CR15","doi-asserted-by":"crossref","unstructured":"Liao, Y., Liu, S., Wang, F., Chen, Y., Qian, C., Feng, J.: Ppdm: Parallel point detection and matching for real-time human-object interaction detection. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 482\u2013490 (2020)","DOI":"10.1109\/CVPR42600.2020.00056"},{"key":"34_CR16","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: IEEE International Conference on Computer Vision, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"34_CR17","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., Zitnick, C.L.: Microsoft coco: common objects in context. In: European Conference on Computer Vision, pp. 740\u2013755. Springer (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"34_CR18","doi-asserted-by":"crossref","unstructured":"Liu, X., Li, Y.L., Wu, X., Tai, Y.W., Lu, C., Tang, C.K.: Interactiveness field in human-object interactions. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20113\u201320122 (2022)","DOI":"10.1109\/CVPR52688.2022.01948"},{"key":"34_CR19","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"34_CR20","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: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 23507\u201323517. Springer (2023)","DOI":"10.1109\/CVPR52729.2023.02251"},{"key":"34_CR21","doi-asserted-by":"crossref","unstructured":"Park, J., Park, J.W., Lee, J.S.: Viplo: Vision transformer based pose-conditioned self-loop graph for human-object interaction detection. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition. Springer (2023)","DOI":"10.1109\/CVPR52729.2023.01645"},{"issue":"16","key":"34_CR22","doi-asserted-by":"publisher","first-page":"2841","DOI":"10.3390\/math10162841","volume":"10","author":"W Peng","year":"2022","unstructured":"Peng, W., Li, C., Tang, K., Liu, X., Fang, M.: Home: 3d human-object mesh topology-enhanced interaction recognition in images. Mathematics 10(16), 2841 (2022)","journal-title":"Mathematics"},{"key":"34_CR23","doi-asserted-by":"crossref","unstructured":"Qi, S., Wang, W., Jia, B., Shen, J., Zhu, S.C.: Learning human-object interactions by graph parsing neural networks. In: European Conference on Computer Vision, pp. 401\u2013417 (2018)","DOI":"10.1007\/978-3-030-01240-3_25"},{"issue":"6","key":"34_CR24","doi-asserted-by":"publisher","first-page":"7559","DOI":"10.1109\/TPAMI.2022.3222871","volume":"45","author":"X Shu","year":"2023","unstructured":"Shu, X., Xu, B., Zhang, L., Tang, J.: Multi-granularity anchor-contrastive representation learning for semi-supervised skeleton-based action recognition. IEEE Trans. Pattern Anal. Mach. Intell. 45(6), 7559\u20137576 (2023). https:\/\/doi.org\/10.1109\/TPAMI.2022.3222871","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"34_CR25","doi-asserted-by":"crossref","unstructured":"Tamura, M., Ohashi, H., Yoshinaga, T.: Qpic: Query-based pairwise human-object interaction detection with image-wide contextual information. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10410\u201310419 (2021)","DOI":"10.1109\/CVPR46437.2021.01027"},{"key":"34_CR26","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3196129","author":"K Tang","year":"2022","unstructured":"Tang, K., Ma, Y., Miao, D., Song, P., Gu, Z., Tian, Z., Wang, W.: Decision fusion networks for image classification. IEEE Trans. Neural Netw. Learn. Syst. (2022). https:\/\/doi.org\/10.1109\/TNNLS.2022.3196129","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"34_CR27","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., Polosukhin, I.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"34_CR28","doi-asserted-by":"crossref","unstructured":"Wan, B., Zhou, D., Liu, Y., Li, R., He, X.: Pose-aware multi-level feature network for human object interaction detection. In: IEEE\/CVF International Conference on Computer Vision, pp. 9469\u20139478 (2019)","DOI":"10.1109\/ICCV.2019.00956"},{"key":"34_CR29","doi-asserted-by":"crossref","unstructured":"Wang, T., Yang, T., Danelljan, M., Khan, F.S., Zhang, X., Sun, J.: Learning human-object interaction detection using interaction points. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4116\u20134125 (2020)","DOI":"10.1109\/CVPR42600.2020.00417"},{"key":"34_CR30","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.107953","volume":"116","author":"M Xing","year":"2021","unstructured":"Xing, M., Feng, Z., Su, Y., Peng, W., Zhang, J.: Ventral & dorsal stream theory based zero-shot action recognition. Pattern Recogn. 116, 107953 (2021)","journal-title":"Pattern Recogn."},{"key":"34_CR31","first-page":"17209","volume":"34","author":"A Zhang","year":"2021","unstructured":"Zhang, A., Liao, Y., Liu, S., Lu, M., Wang, Y., Gao, C., Li, X.: Mining the benefits of two-stage and one-stage hoi detection. Adv. Neural. Inf. Process. Syst. 34, 17209\u201317220 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"34_CR32","doi-asserted-by":"crossref","unstructured":"Zhang, F.Z., Campbell, D., Gould, S.: Spatially conditioned graphs for detecting human-object interactions. In: IEEE\/CVF International Conference on Computer Vision, pp. 13319\u201313327 (2021)","DOI":"10.1109\/ICCV48922.2021.01307"},{"key":"34_CR33","doi-asserted-by":"crossref","unstructured":"Zhang, F.Z., Campbell, D., Gould, S.: Efficient two-stage detection of human-object interactions with a novel unary-pairwise transformer. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20104\u201320112 (2022)","DOI":"10.1109\/CVPR52688.2022.01947"},{"key":"34_CR34","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Pan, Y., Yao, T., Huang, R., Mei, T., Chen, C.W.: Exploring structure-aware transformer over interaction proposals for human-object interaction detection. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19548\u201319557 (2022)","DOI":"10.1109\/CVPR52688.2022.01894"},{"key":"34_CR35","doi-asserted-by":"crossref","unstructured":"Zhou, W., Du, D., Zhang, L., Luo, T., Wu, Y.: Multi-granularity alignment domain adaptation for object detection. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9581\u20139590. Springer (2022)","DOI":"10.1109\/CVPR52688.2022.00936"},{"key":"34_CR36","doi-asserted-by":"crossref","unstructured":"Zou, Z., Tang, W.: Modulated graph convolutional network for 3d human pose estimation. In: IEEE\/CVF International Conference on Computer Vision, pp. 11477\u201311487 (2021)","DOI":"10.1109\/ICCV48922.2021.01128"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-8511-7_34","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T05:14:43Z","timestamp":1730524483000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-8511-7_34"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,3]]},"ISBN":["9789819785100","9789819785117"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-8511-7_34","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,3]]},"assertion":[{"value":"3 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Urumqi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2024.prcv.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}