{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T15:14:43Z","timestamp":1769181283804,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":31,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819556816","type":"print"},{"value":"9789819556823","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-981-95-5682-3_36","type":"book-chapter","created":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T21:14:33Z","timestamp":1769116473000},"page":"514-527","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["FASAM2-Ego: Feature-Augmented Segment Anything 2 for\u00a0Egocentric Hand-Object Interactive Segmentation"],"prefix":"10.1007","author":[{"given":"Ming","family":"Jiang","sequence":"first","affiliation":[]},{"given":"Jie","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Yao","family":"Lu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,1,23]]},"reference":[{"key":"36_CR1","doi-asserted-by":"crossref","unstructured":"Zhang, L., Zhou, S., Stent, S., Shi, J.: Fine-grained egocentric hand-object segmentation: dataset, model, and applications. In: European Conference on Computer Vision (ECCV), pp. 127\u2013145. Springer (2022)","DOI":"10.1007\/978-3-031-19818-2_8"},{"key":"36_CR2","doi-asserted-by":"crossref","unstructured":"Jain, J., Li, J., Chiu, M. T., Hassani, A., Orlov, N., Shi, H.: OneFormer: one transformer to rule universal image segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2989\u20132998 (2023)","DOI":"10.1109\/CVPR52729.2023.00292"},{"key":"36_CR3","doi-asserted-by":"crossref","unstructured":"Zhang, C., Zhang, Q., Wu, J.: Rethinking camouflaged object detection via foreground-background interactive learning. In: Proceedings of the ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 1\u20135 (2025)","DOI":"10.1109\/ICASSP49660.2025.10889016"},{"key":"36_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"432","DOI":"10.1007\/978-3-030-01228-1_26","volume-title":"Computer Vision \u2013 ECCV 2018","author":"T Xiao","year":"2018","unstructured":"Xiao, T., Liu, Y., Zhou, B., Jiang, Y., Sun, J.: Unified perceptual parsing for scene understanding. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11209, pp. 432\u2013448. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01228-1_26"},{"key":"36_CR5","doi-asserted-by":"publisher","unstructured":"Kirillov, A., et al.: Segment anything. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 3992\u20134003 (2023). https:\/\/doi.org\/10.1109\/iccv51070.2023.00371","DOI":"10.1109\/iccv51070.2023.00371"},{"key":"36_CR6","unstructured":"Chen, P., et al.: SAM-CP: Marrying SAM with Composable Prompts for Versatile Segmentation. arXiv preprint arXiv:2407.16682 (2024)"},{"key":"36_CR7","unstructured":"Ravi, N., et al.: SAM 2: Segment Anything in Images and Videos. arXiv preprint arXiv:2408.00714 (2024)"},{"key":"36_CR8","doi-asserted-by":"crossref","unstructured":"Su, Y., Wang, Y., Chau, L.: CaRe-Ego: Contact-aware Relationship Modeling for Egocentric Interactive Hand-object Segmentation (2025)","DOI":"10.1016\/j.eswa.2025.129148"},{"key":"36_CR9","unstructured":"Oquab, M., et al.: DINOv2: Learning Robust Visual Features Without Supervision. arXiv preprint arXiv:2304.07193 (2023)"},{"key":"36_CR10","unstructured":"Ryali, C., et al.: Hiera: a hierarchical vision transformer without the bells-and-whistles. In: Proceedings of the 40th International Conference on Machine Learning (ICML), pp. 29441\u201329454. PMLR (2023)"},{"key":"36_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"key":"36_CR12","doi-asserted-by":"publisher","unstructured":"Chen, T., et al.: SAM-adapter: adapting segment anything in underperformed scenes. In: 2023 IEEE\/CVF International Conference on Computer Vision Workshops (ICCVW), pp. 3359\u20133367 (2023). https:\/\/doi.org\/10.1109\/ICCVW60793.2023.00361","DOI":"10.1109\/ICCVW60793.2023.00361"},{"key":"36_CR13","doi-asserted-by":"crossref","unstructured":"Xiong, X., et al.: SAM2-UNet: segment anything 2 makes strong encoder for natural and medical image segmentation. Model. Simul. 14(337) (2025)","DOI":"10.1007\/s44267-025-00106-w"},{"key":"36_CR14","doi-asserted-by":"publisher","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 10012\u201310022 (2021). https:\/\/doi.org\/10.1109\/ICCV48922.2021.00986","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"36_CR15","doi-asserted-by":"crossref","unstructured":"Xu, Y., Yang, F., Xu, B.: DSU-Net: An Improved U-Net Model Based on DINOv2 and SAM2 with Multi-scale Cross-model Feature Enhancement. arXiv preprint arXiv:2503.21187 (2025)","DOI":"10.1109\/ICAIBD64986.2025.11081979"},{"key":"36_CR16","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: 9th International Conference on Learning Representations (ICLR). OpenReview (2021)"},{"key":"36_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"263","DOI":"10.1007\/978-3-030-59725-2_26","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2020","author":"D-P Fan","year":"2020","unstructured":"Fan, D.-P., et al.: PraNet: parallel reverse attention network for polyp segmentation. In: Martel, A.L., et al. (eds.) MICCAI 2020. LNCS, vol. 12266, pp. 263\u2013273. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-59725-2_26"},{"key":"36_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"404","DOI":"10.1007\/978-3-030-01252-6_24","volume-title":"Computer Vision \u2013 ECCV 2018","author":"S Liu","year":"2018","unstructured":"Liu, S., Huang, D., Wang, Y.: Receptive field block net for accurate and fast object detection. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11215, pp. 404\u2013419. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01252-6_24"},{"key":"36_CR19","doi-asserted-by":"publisher","unstructured":"Dumoulin, V., Visin, F.: A guide to convolution arithmetic for deep learning. arXiv preprint (2016). https:\/\/doi.org\/10.48550\/arXiv.1603.07285","DOI":"10.48550\/arXiv.1603.07285"},{"key":"36_CR20","doi-asserted-by":"publisher","first-page":"1002","DOI":"10.1109\/TIP.2024.3354108","volume":"33","author":"Z Chen","year":"2023","unstructured":"Chen, Z., He, Z., Lu, Z.-M.: DEA-Net: single image dehazing based on detail-enhanced convolution and content-guided attention. IEEE Trans. Image Process. 33, 1002\u20131015 (2023). https:\/\/doi.org\/10.1109\/TIP.2024.3354108","journal-title":"IEEE Trans. Image Process."},{"key":"36_CR21","doi-asserted-by":"publisher","unstructured":"Wei, J., Wang, S., Huang, Q.: F3Net: fusion, feedback and focus for salient object detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, no. 7, pp. 12321\u201312328 (2019). https:\/\/doi.org\/10.1609\/aaai.v34i07.6916","DOI":"10.1609\/aaai.v34i07.6916"},{"key":"36_CR22","unstructured":"Grauman, K., et al.: Ego4D: Around the World in 3,000 Hours of Egocentric Video. arXiv preprint arXiv:2110.07058 (2021)"},{"key":"36_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"716","DOI":"10.1007\/978-3-030-01225-0_42","volume-title":"Computer Vision \u2013 ECCV 2018","author":"J Wang","year":"2018","unstructured":"Wang, J., Cherian, A.: Learning discriminative video representations using adversarial perturbations. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11208, pp. 716\u2013733. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01225-0_42"},{"key":"36_CR24","doi-asserted-by":"publisher","unstructured":"Tang, Y., Tian, Y., Lu, J., Feng, J., Zhou, J.: Action recognition in RGB-D egocentric videos. In: 2017 IEEE International Conference on Image Processing (ICIP), pp. 3410\u20133414. IEEE (2017). https:\/\/doi.org\/10.1109\/ICIP.2017.8296942","DOI":"10.1109\/ICIP.2017.8296942"},{"key":"36_CR25","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: 5th International Conference on Learning Representations (ICLR) (2017)"},{"key":"36_CR26","first-page":"12077","volume":"34","author":"E Xie","year":"2021","unstructured":"Xie, E., Wang, W., Yu, Z., Anandkumar, A., Alvarez, J.M., Luo, P.: SegFormer: simple and efficient design for semantic segmentation with transformers. Adv. Neural. Inf. Process. Syst. 34, 12077\u201312090 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"36_CR27","doi-asserted-by":"crossref","unstructured":"Xu, Z., Wu, D., Yu, C., Chu, X., Sang, N., Gao, C.: SCTNet: single-branch CNN with transformer semantic information for real-time segmentation. In: Proceedings of the 38th AAAI Conference on Artificial Intelligence (AAAI), vol. 38, pp. 6378\u20136386 (2024)","DOI":"10.1609\/aaai.v38i6.28457"},{"key":"36_CR28","doi-asserted-by":"publisher","unstructured":"Strudel, R., Garcia, R., Laptev, I., Schmid, C.: Segmenter: transformer for semantic segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 7262\u20137272 (2021). https:\/\/doi.org\/10.1109\/ICCV48922.2021.00718","DOI":"10.1109\/ICCV48922.2021.00718"},{"key":"36_CR29","unstructured":"Cheng, B., Schwing, A., Kirillov, A.: Per-pixel classification is not all you need for semantic segmentation. In: Advances in Neural Information Processing Systems, vol. 34, pp. 17864\u201317875 (2021)"},{"key":"36_CR30","doi-asserted-by":"publisher","unstructured":"Cheng, B., Misra, I., Schwing, A. G., Kirillov, A., Girdhar, R.: Masked-attention mask transformer for universal image segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1290\u20131299 (2022). https:\/\/doi.org\/10.1109\/CVPR52688.2022.00135","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"36_CR31","doi-asserted-by":"crossref","unstructured":"Koonce, B.: ResNet 50. In: Convolutional Neural Networks with Swift for TensorFlow: Image Recognition and Dataset Categorization, pp. 63\u201372. Apress, Berkeley, CA (2021)","DOI":"10.1007\/978-1-4842-6168-2_6"}],"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\/978-981-95-5682-3_36","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T21:14:36Z","timestamp":1769116476000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-5682-3_36"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819556816","9789819556823"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-5682-3_36","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"23 January 2026","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":"Shanghai","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":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2025.prcv.cn\/index.asp","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}