{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T03:46:05Z","timestamp":1772682365061,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":86,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3680628","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:27Z","timestamp":1729925967000},"page":"9779-9788","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":12,"title":["<i>\n              P\n              <sup>2<\/sup>\n              SAM:\n            <\/i>\n            Probabilistically Prompted SAMs Are Efficient Segmentator for Ambiguous Medical Images"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-5881-3974","authenticated-orcid":false,"given":"Yuzhi","family":"Huang","sequence":"first","affiliation":[{"name":"School of Informatics, Xiamen University, Xiamen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7146-2200","authenticated-orcid":false,"given":"Chenxin","family":"Li","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong SAR, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1609-1136","authenticated-orcid":false,"given":"Zixu","family":"Lin","sequence":"additional","affiliation":[{"name":"School of Informatics, Xiamen University, Xiamen, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-7965-1402","authenticated-orcid":false,"given":"Hengyu","family":"Liu","sequence":"additional","affiliation":[{"name":"Tianjin University, Hong Kong SAR, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7106-2207","authenticated-orcid":false,"given":"Haote","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Informatics, Xiamen University, Xiamen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9342-9428","authenticated-orcid":false,"given":"Yifan","family":"Liu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong SAR, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3913-9400","authenticated-orcid":false,"given":"Yue","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Informatics, Xiamen University, Xiamen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2288-5287","authenticated-orcid":false,"given":"Xinghao","family":"Ding","sequence":"additional","affiliation":[{"name":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing &amp; School of Informatics, Xiamen University, Xiamen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7190-2429","authenticated-orcid":false,"given":"Xiaotong","family":"Tu","sequence":"additional","affiliation":[{"name":"School of Informatics, Xiamen University, Xiamen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0853-6948","authenticated-orcid":false,"given":"Yixuan","family":"Yuan","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong SAR, Hong Kong"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Vajira Thambawita, et al .","author":"Ali Sharib","year":"2024","unstructured":"Sharib Ali, Noha Ghatwary, Debesh Jha, Ece Isik-Polat, Gorkem Polat, Chen Yang, Wuyang Li, Adrian Galdran, Miguel-\u00c1ngel Gonz\u00e1lez Ballester, Vajira Thambawita, et al . 2024. Assessing generalisability of deep learning-based polyp detection and segmentation methods through a computer vision challenge. Sci. Rep. (2024)."},{"key":"e_1_3_2_1_2_1","volume-title":"et al","author":"Samuel G","year":"2011","unstructured":"Samuel G Armato III, Geoffrey McLennan, Luc Bidaut, Michael F McNitt-Gray, Charles R Meyer, Anthony P Reeves, Binsheng Zhao, Denise R Aberle, Claudia I Henschke, Eric A Hoffman, et al . 2011. The lung image database consortium (LIDC) and image database resource initiative (IDRI): a completed reference database of lung nodules on CT scans. Medical physics 38, 2 (2011), 915--931."},{"key":"e_1_3_2_1_3_1","volume-title":"Phiseg: Capturing uncertainty in medical image segmentation. In Medical Image Computing and Computer Assisted Intervention--MICCAI 2019: 22nd International Conference, Shenzhen, China, October 13--17","author":"Baumgartner Christian F","year":"2019","unstructured":"Christian F Baumgartner, Kerem C Tezcan, Krishna Chaitanya, Andreas M H\u00f6tker, Urs J Muehlematter, Khoschy Schawkat, Anton S Becker, Olivio Donati, and Ender Konukoglu. 2019. Phiseg: Capturing uncertainty in medical image segmentation. In Medical Image Computing and Computer Assisted Intervention--MICCAI 2019: 22nd International Conference, Shenzhen, China, October 13--17, 2019, Proceedings, Part II 22. Springer, 119--127."},{"key":"e_1_3_2_1_4_1","volume-title":"Language Models are Few-Shot Learners. arXiv: Computation and Language,arXiv: Computation and Language (May","author":"Brown T.B.","year":"2020","unstructured":"T.B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Askell Amanda, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Henighan Tom, Rewon Child, A. Ramesh, DanielM. Ziegler, Jeffrey Wu, Clemens Winter, Christopher Hesse, Mark Chen, EricJ. Sigler, Mateusz Litwin, Scott Gray, Chess Benjamin, Jack Clark, Christopher Berner, McCandlish Sam, Alec Radford, Ilya Sutskever, and Dario Amodei. 2020. Language Models are Few-Shot Learners. arXiv: Computation and Language,arXiv: Computation and Language (May 2020)."},{"key":"e_1_3_2_1_5_1","volume-title":"European conference on computer vision. Springer, 205--218","author":"Cao Hu","year":"2022","unstructured":"Hu Cao, Yueyue Wang, Joy Chen, Dongsheng Jiang, Xiaopeng Zhang, Qi Tian, and Manning Wang. 2022. Swin-unet: Unet-like pure transformer for medical image segmentation. In European conference on computer vision. Springer, 205--218."},{"key":"e_1_3_2_1_6_1","first-page":"33302","article-title":"Mix and reason: Reasoning over semantic topology with data mixing for domain generalization","volume":"35","author":"Chen Chaoqi","year":"2022","unstructured":"Chaoqi Chen, Luyao Tang, Feng Liu, Gangming Zhao, Yue Huang, and Yizhou Yu. 2022. Mix and reason: Reasoning over semantic topology with data mixing for domain generalization. Advances in Neural Information Processing Systems 35 (2022), 33302--33315.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_7_1","volume-title":"Medical federated learning with joint graph purification for noisy label learning. MedIA","author":"Chen Zhen","year":"2023","unstructured":"Zhen Chen, Wuyang Li, Xiaohan Xing, and Yixuan Yuan. 2023. Medical federated learning with joint graph purification for noisy label learning. MedIA (2023)."},{"key":"e_1_3_2_1_8_1","volume-title":"Unsupervised Anomaly Segmentation for Brain Lesions Using Dual Semantic-Manifold Reconstruction. In International Conference on Neural In- formation Processing. Springer, 133--144","author":"Ding Zhiyuan","year":"2022","unstructured":"Zhiyuan Ding, Qi Dong, Haote Xu, Chenxin Li, Xinghao Ding, and Yue Huang. 2022. Unsupervised Anomaly Segmentation for Brain Lesions Using Dual Semantic-Manifold Reconstruction. In International Conference on Neural In- formation Processing. Springer, 133--144."},{"key":"e_1_3_2_1_9_1","volume-title":"Modeling Multimodal Aleatoric Uncertainty in Segmentation with Mixture of Stochastic Expert. arXiv preprint arXiv:2212.07328","author":"Gao Zhitong","year":"2022","unstructured":"Zhitong Gao, Yucong Chen, Chuyu Zhang, and Xuming He. 2022. Modeling Multimodal Aleatoric Uncertainty in Segmentation with Mixture of Stochastic Expert. arXiv preprint arXiv:2212.07328 (2022)."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"e_1_3_2_1_11_1","unstructured":"Zhibin He Wuyang Li Tuo Zhang and Yixuan Yuan. 2023. H 2 GM: A Hierarchical Hypergraph Matching Framework for Brain Landmark Alignment. In MICCAI."},{"key":"e_1_3_2_1_12_1","volume-title":"LoRA: Low-Rank Adaptation of Large Language Models. In International Conference on Learning Representations.","author":"Hu Edward J","year":"2021","unstructured":"Edward J Hu, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, et al. 2021. LoRA: Low-Rank Adaptation of Large Language Models. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32245-8_16"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053405"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978--3--319--75238--9_25"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"crossref","unstructured":"Elias Kassapis Georgi Dikov Deepak K Gupta and Cedric Nugteren. 2021. Cali- brated adversarial refinement for stochastic semantic segmentation. In Proceed- ings of the IEEE\/CVF International Conference on Computer Vision. 7057--7067.","DOI":"10.1109\/ICCV48922.2021.00697"},{"key":"e_1_3_2_1_17_1","volume-title":"Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114","author":"Kingma Diederik P","year":"2013","unstructured":"Diederik P Kingma and Max Welling. 2013. Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)."},{"key":"e_1_3_2_1_18_1","unstructured":"Alexander Kirillov Eric Mintun Nikhila Ravi Hanzi Mao Chloe Rolland Laura Gustafson Tete Xiao Spencer Whitehead AlexanderC Berg Wan-Yen Lo Piotr Doll\u00e1r and Ross Girshick. [n. d.]. Segment Anything. ([n. d.])."},{"key":"e_1_3_2_1_19_1","volume-title":"Joseph R Ledsam, Klaus Maier-Hein, SM Eslami, Danilo Jimenez Rezende, and Olaf Ronneberger.","author":"Kohl Simon","year":"2018","unstructured":"Simon Kohl, Bernardino Romera-Paredes, Clemens Meyer, Jeffrey De Fauw, Joseph R Ledsam, Klaus Maier-Hein, SM Eslami, Danilo Jimenez Rezende, and Olaf Ronneberger. 2018. A probabilistic u-net for segmentation of ambiguous images. Advances in neural information processing systems 31 (2018)."},{"key":"e_1_3_2_1_20_1","volume-title":"SM Eslami, Pushmeet Kohli, Andrew Zisser- man, and Olaf Ronneberger.","author":"Kohl Simon AA","year":"2019","unstructured":"Simon AA Kohl, Bernardino Romera-Paredes, Klaus H Maier-Hein, Danilo Jimenez Rezende, SM Eslami, Pushmeet Kohli, Andrew Zisser- man, and Olaf Ronneberger. 2019. A hierarchical probabilistic u-net for modeling multi-scale ambiguities. arXiv preprint arXiv:1905.13077 (2019)."},{"key":"e_1_3_2_1_21_1","volume-title":"The power of scale for parameter-efficient prompt tuning. arXiv preprint arXiv:2104.08691","author":"Lester Brian","year":"2021","unstructured":"Brian Lester, Rami Al-Rfou, and Noah Constant. 2021. The power of scale for parameter-efficient prompt tuning. arXiv preprint arXiv:2104.08691 (2021)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00047"},{"key":"e_1_3_2_1_23_1","volume-title":"EndoSparse: Real-Time Sparse View Synthesis of Endoscopic Scenes using Gaussian Splatting. arXiv preprint arXiv:2407.01029","author":"Li Chenxin","year":"2024","unstructured":"Chenxin Li, Brandon Y Feng, Yifan Liu, Hengyu Liu, Cheng Wang, Weihao Yu, and Yixuan Yuan. 2024. EndoSparse: Real-Time Sparse View Synthesis of Endoscopic Scenes using Gaussian Splatting. arXiv preprint arXiv:2407.01029 (2024)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_2"},{"key":"e_1_3_2_1_25_1","volume-title":"Domain generalization on medical imaging classification using episodic training with task augmentation. Computers in biology and medicine 141","author":"Li Chenxin","year":"2022","unstructured":"Chenxin Li, Xin Lin, Yijin Mao, Wei Lin, Qi Qi, Xinghao Ding, Yue Huang, Dong Liang, and Yizhou Yu. 2022. Domain generalization on medical imaging classification using episodic training with task augmentation. Computers in biology and medicine 141 (2022), 105144."},{"key":"e_1_3_2_1_26_1","volume-title":"GaussianStego: A Generalizable Stenography Pipeline for Generative 3D Gaussians Splatting. arXiv preprint arXiv:2407.01301","author":"Li Chenxin","year":"2024","unstructured":"Chenxin Li, Hengyu Liu, Zhiwen Fan, Wuyang Li, Yifan Liu, Panwang Pan, and Yixuan Yuan. 2024. GaussianStego: A Generalizable Stenography Pipeline for Generative 3D Gaussians Splatting. arXiv preprint arXiv:2407.01301 (2024)."},{"key":"e_1_3_2_1_27_1","volume-title":"Endora: Video Generation Models as Endoscopy Simulators. arXiv preprint arXiv:2403.11050","author":"Li Chenxin","year":"2024","unstructured":"Chenxin Li, Hengyu Liu, Yifan Liu, Brandon Y Feng, Wuyang Li, Xinyu Liu, Zhen Chen, Jing Shao, and Yixuan Yuan. 2024. Endora: Video Generation Models as Endoscopy Simulators. arXiv preprint arXiv:2403.11050 (2024)."},{"key":"e_1_3_2_1_28_1","volume-title":"U-KAN Makes Strong Backbone for Medical Image Segmentation and Generation. arXiv preprint arXiv:2406.02918","author":"Li Chenxin","year":"2024","unstructured":"Chenxin Li, Xinyu Liu, Wuyang Li, Cheng Wang, Hengyu Liu, and Yixuan Yuan. 2024. U-KAN Makes Strong Backbone for Medical Image Segmentation and Generation. arXiv preprint arXiv:2406.02918 (2024)."},{"key":"e_1_3_2_1_29_1","volume-title":"GTP-4o: Modality-prompted Heterogeneous Graph Learning for Omni-modal Biomedical Representation. arXiv preprint arXiv:2407.05540","author":"Li Chenxin","year":"2024","unstructured":"Chenxin Li, Xinyu Liu, Cheng Wang, Yifan Liu, Weihao Yu, Jing Shao, and Yixuan Yuan. 2024. GTP-4o: Modality-prompted Heterogeneous Graph Learning for Omni-modal Biomedical Representation. arXiv preprint arXiv:2407.05540 (2024)."},{"key":"e_1_3_2_1_30_1","unstructured":"Chenxin Li Wenao Ma Liyan Sun Xinghao Ding Yue Huang Guisheng Wang and Yizhou Yu. [n. d.]. Hierarchical deep network with uncertainty-aware semi- supervised learning for vessel segmentation. Neural Computing and Applications ([n. d.]) 1--14."},{"key":"e_1_3_2_1_31_1","volume-title":"Unsupervised anomaly segmentation using image-semantic cycle translation. arXiv preprint arXiv:2103.09094","author":"Li Chenxin","year":"2021","unstructured":"Chenxin Li, Yunlong Zhang, Jiongcheng Li, Yue Huang, and Xinghao Ding. 2021. Unsupervised anomaly segmentation using image-semantic cycle translation. arXiv preprint arXiv:2103.09094 (2021)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP42928.2021.9506148"},{"key":"e_1_3_2_1_33_1","volume-title":"Htd: Heterogeneous task decoupling for two-stage object detection. TIP","author":"Li Wuyang","year":"2021","unstructured":"Wuyang Li, Zhen Chen, Baopu Li, Dingwen Zhang, and Yixuan Yuan. 2021. Htd: Heterogeneous task decoupling for two-stage object detection. TIP (2021)."},{"key":"e_1_3_2_1_34_1","unstructured":"Wuyang Li Xiaoqing Guo and Yixuan Yuan. 2023. Novel Scenes & Classes: Towards Adaptive Open-set Object Detection. In ICCV. 15780--15790."},{"key":"e_1_3_2_1_35_1","volume-title":"Scan: Enhanced semantic conditioned adaptation for domain adaptive object detection. TMM","author":"Li Wuyang","year":"2022","unstructured":"Wuyang Li, Xinyu Liu, and Yixuan Yuan. 2022. Scan: Enhanced semantic conditioned adaptation for domain adaptive object detection. TMM (2022)."},{"key":"e_1_3_2_1_36_1","volume-title":"SIGMA: Semantic-complete Graph Matching for Domain Adaptive Object Detection. In CVPR.","author":"Li Wuyang","year":"2022","unstructured":"Wuyang Li, Xinyu Liu, and Yixuan Yuan. 2022. SIGMA: Semantic-complete Graph Matching for Domain Adaptive Object Detection. In CVPR."},{"key":"e_1_3_2_1_37_1","volume-title":"Sigma: Improved semantic- complete graph matching for domain adaptive object detection. TPAMI","author":"Li Wuyang","year":"2023","unstructured":"Wuyang Li, Xinyu Liu, and Yixuan Yuan. 2023. Sigma: Improved semantic- complete graph matching for domain adaptive object detection. TPAMI (2023)."},{"key":"e_1_3_2_1_38_1","volume-title":"CLIFF: Continual Latent Diffusion for Open-Vocabulary Object Detection. In ECCV.","author":"Li Wuyang","year":"2024","unstructured":"Wuyang Li, Xinyu Liu, and Yixuan Yuan. 2024. CLIFF: Continual Latent Diffusion for Open-Vocabulary Object Detection. In ECCV."},{"key":"e_1_3_2_1_39_1","volume-title":"ISBI Workshop: EndoCV","author":"Li Wuyang","year":"2021","unstructured":"Wuyang Li, Chen Yang, Jie Liu, Xinyu Liu, Xiaoqing Guo, and Yixuan Yuan. 2021. Joint polyp detection and segmentation with heterogeneous endoscopic data. In ISBI Workshop: EndoCV 2021."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482310"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611894"},{"key":"e_1_3_2_1_42_1","volume-title":"AGLLDiff: Guiding Diffusion Models Towards Unsupervised Training-free Real-world Low-light Image En- hancement. arXiv preprint arXiv:2407.14900","author":"Lin Yunlong","year":"2024","unstructured":"Yunlong Lin, Tian Ye, Sixiang Chen, Zhenqi Fu, Yingying Wang, Wenhao Chai, Zhaohu Xing, Lei Zhu, and Xinghao Ding. 2024. AGLLDiff: Guiding Diffusion Models Towards Unsupervised Training-free Real-world Low-light Image En- hancement. arXiv preprint arXiv:2407.14900 (2024)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20054"},{"key":"e_1_3_2_1_44_1","volume-title":"LGS: A Light-weight 4D Gaussian Splatting for Efficient Surgical Scene Reconstruction. arXiv preprint arXiv:2406.16073","author":"Liu Hengyu","year":"2024","unstructured":"Hengyu Liu, Yifan Liu, Chenxin Li, Wuyang Li, and Yixuan Yuan. 2024. LGS: A Light-weight 4D Gaussian Splatting for Efficient Surgical Scene Reconstruction. arXiv preprint arXiv:2406.16073 (2024)."},{"key":"e_1_3_2_1_45_1","first-page":"1","article-title":"Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing","volume":"55","author":"Liu Pengfei","year":"2023","unstructured":"Pengfei Liu, Weizhe Yuan, Jinlan Fu, Zhengbao Jiang, Hiroaki Hayashi, and Graham Neubig. 2023. Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing. Comput. Surveys 55, 9 (2023), 1--35.","journal-title":"Comput. Surveys"},{"key":"e_1_3_2_1_46_1","volume-title":"et al","author":"Liu Shilong","year":"2023","unstructured":"Shilong Liu, Zhaoyang Zeng, Tianhe Ren, Feng Li, Hao Zhang, Jie Yang, Chunyuan Li, Jianwei Yang, Hang Su, Jun Zhu, et al . 2023. Grounding dino: Marrying dino with grounded pre-training for open-set object detection. arXiv preprint arXiv:2303.05499 (2023)."},{"key":"e_1_3_2_1_47_1","volume-title":"Din Ping Tsai, and Mu Ku Chen","author":"Liu Xiaoyuan","year":"2024","unstructured":"Xiaoyuan Liu, Wuyang Li, Takeshi Yamaguchi, Zihan Geng, Takuo Tanaka, Din Ping Tsai, and Mu Ku Chen. 2024. Stereo Vision Meta-Lens-Assisted Driving Vision. ACS Photonics (2024)."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"crossref","unstructured":"Xinyu Liu Wuyang Li and Yixuan Yuan. 2022. Intervention & interaction federated abnormality detection with noisy clients. In MICCAI. 309--319.","DOI":"10.1007\/978-3-031-16452-1_30"},{"key":"e_1_3_2_1_49_1","volume-title":"Decoupled Unbiased Teacher for Source-Free Domain Adaptive Medical Object Detection. TNNLS","author":"Liu Xinyu","year":"2023","unstructured":"Xinyu Liu, Wuyang Li, and Yixuan Yuan. 2023. Decoupled Unbiased Teacher for Source-Free Domain Adaptive Medical Object Detection. TNNLS (2023)."},{"key":"e_1_3_2_1_50_1","volume-title":"DiffRect: Latent Diffusion Label Rectification for Semi-supervised Medical Image Segmentation. arXiv preprint arXiv:2407.09918","author":"Liu Xinyu","year":"2024","unstructured":"Xinyu Liu, Wuyang Li, and Yixuan Yuan. 2024. DiffRect: Latent Diffusion Label Rectification for Semi-supervised Medical Image Segmentation. arXiv preprint arXiv:2407.09918 (2024)."},{"key":"e_1_3_2_1_51_1","volume-title":"EndoGaussian: Gauss- ian Splatting for Deformable Surgical Scene Reconstruction. arXiv preprint arXiv:2401.12561","author":"Liu Yifan","year":"2024","unstructured":"Yifan Liu, Chenxin Li, Chen Yang, and Yixuan Yuan. 2024. EndoGaussian: Gauss- ian Splatting for Deformable Surgical Scene Reconstruction. arXiv preprint arXiv:2401.12561 (2024)."},{"key":"e_1_3_2_1_52_1","volume-title":"GRAB-Net: Graph-based boundary-aware network for medical point cloud segmentation","author":"Liu Yifan","year":"2023","unstructured":"Yifan Liu, Wuyang Li, Jie Liu, Hui Chen, and Yixuan Yuan. 2023. GRAB-Net: Graph-based boundary-aware network for medical point cloud segmentation. IEEE Transactions on Medical Imaging (2023)."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16443-9_10"},{"key":"e_1_3_2_1_54_1","volume-title":"Stochastic Segmentation Networks: Modelling Spatially Correlated Aleatoric Uncertainty","author":"Monteiro Miguel","year":"2020","unstructured":"Miguel Monteiro, LoicLe Folgoc, DanielCoelhode Castro, Nick Pawlowski, Bernardo Marques, Konstantinos Kamnitsas, Markvander Wilk, and Ben Glocker. 2020. Stochastic Segmentation Networks: Modelling Spatially Correlated Aleatoric Uncertainty. Cornell University - arXiv,Cornell University - arXiv (Jun 2020)."},{"key":"e_1_3_2_1_55_1","first-page":"12756","article-title":"Stochastic segmentation networks: Modelling spatially correlated aleatoric uncertainty","volume":"33","author":"Monteiro Miguel","year":"2020","unstructured":"Miguel Monteiro, Lo\u00efc Le Folgoc, Daniel Coelho de Castro, Nick Pawlowski, Bernardo Marques, Konstantinos Kamnitsas, Mark van der Wilk, and Ben Glocker. 2020. Stochastic segmentation networks: Modelling spatially correlated aleatoric uncertainty. Advances in Neural Information Processing Systems 33 (2020), 12756-- 12767.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_56_1","volume-title":"Learning to estimate 6dof pose from limited data: A few- shot, generalizable approach using rgb images. arXiv preprint arXiv:2306.07598","author":"Pan Panwang","year":"2023","unstructured":"Panwang Pan, Zhiwen Fan, Brandon Y Feng, Peihao Wang, Chenxin Li, and Zhangyang Wang. 2023. Learning to estimate 6dof pose from limited data: A few- shot, generalizable approach using rgb images. arXiv preprint arXiv:2306.07598 (2023)."},{"key":"e_1_3_2_1_57_1","volume-title":"Modal Uncertainty Estimation via Discrete Latent Representation. arXiv preprint arXiv:2007.12858","author":"Qiu Di","year":"2020","unstructured":"Di Qiu and Lok Ming Lui. 2020. Modal Uncertainty Estimation via Discrete Latent Representation. arXiv preprint arXiv:2007.12858 (2020)."},{"key":"e_1_3_2_1_58_1","volume-title":"International conference on machine learning. PMLR, 8748--8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748--8763."},{"key":"e_1_3_2_1_59_1","unstructured":"Aimon Rahman JeyaMariaJose Valanarasu Ilker Hacihaliloglu and VishalM Patel. [n. d.]. Ambiguous Medical Image Segmentation using Diffusion Models. ([n. d.])."},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01110"},{"key":"e_1_3_2_1_61_1","volume-title":"Srcd: Semantic reasoning with compound domains for single-domain generalized object detection. arXiv preprint arXiv:2307.01750","author":"Rao Zhijie","year":"2023","unstructured":"Zhijie Rao, Jingcai Guo, Luyao Tang, Yue Huang, Xinghao Ding, and Song Guo. 2023. Srcd: Semantic reasoning with compound domains for single-domain generalized object detection. arXiv preprint arXiv:2307.01750 (2023)."},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"crossref","unstructured":"Olaf Ronneberger Philipp Fischer and Thomas Brox. 2015. U-Net: Convolutional Networks for Biomedical Image Segmentation. 234--241. https:\/\/doi.org\/10.1007\/ 978--3--319--24574--4_28","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-59861-7_9"},{"key":"e_1_3_2_1_65_1","volume-title":"Deep learning in medical image analysis. Annual review of biomedical engineering 19, 1","author":"Shen Dinggang","year":"2017","unstructured":"Dinggang Shen, Guorong Wu, and Heung-Il Suk. 2017. Deep learning in medical image analysis. Annual review of biomedical engineering 19, 1 (2017), 221--248."},{"key":"e_1_3_2_1_66_1","volume-title":"Learning structured output representation using deep conditional generative models. Advances in neural information processing systems 28","author":"Sohn Kihyuk","year":"2015","unstructured":"Kihyuk Sohn, Honglak Lee, and Xinchen Yan. 2015. Learning structured output representation using deep conditional generative models. Advances in neural information processing systems 28 (2015)."},{"key":"e_1_3_2_1_67_1","volume-title":"Learning structured output representation using deep conditional generative models. Neural Information Processing Systems,Neural Information Processing Systems (Dec","author":"Sohn Kihyuk","year":"2015","unstructured":"Kihyuk Sohn, Xinchen Yan, and Honglak Lee. 2015. Learning structured output representation using deep conditional generative models. Neural Information Processing Systems,Neural Information Processing Systems (Dec 2015)."},{"key":"e_1_3_2_1_68_1","volume-title":"Few-shot medical image segmentation using a global correlation network with discriminative embedding. Computers in biology and medicine 140","author":"Sun Liyan","year":"2022","unstructured":"Liyan Sun, Chenxin Li, Xinghao Ding, Yue Huang, Zhong Chen, Guisheng Wang, Yizhou Yu, and John Paisley. 2022. Few-shot medical image segmentation using a global correlation network with discriminative embedding. Computers in biology and medicine 140 (2022), 105067."},{"key":"e_1_3_2_1_69_1","volume-title":"Ruud JG van Sloun, Peter HN de With, and Fons van der Sommen.","author":"Amaan Valiuddin MM","year":"2021","unstructured":"MM Amaan Valiuddin, Christiaan GA Viviers, Ruud JG van Sloun, Peter HN de With, and Fons van der Sommen. 2021. Improving Aleatoric Uncertainty Quantification in Multi-annotated Medical Image Segmentation with Normalizing Flows. In Uncertainty for Safe Utilization of Machine Learning in Medical Imaging, and Perinatal Imaging, Placental and Preterm Image Analysis: 3rd International Workshop, UNSURE 2021, and 6th International Workshop, PIPPI 2021, Held in Conjunction with MICCAI 2021, Strasbourg, France, October 1, 2021, Proceedings 3. Springer, 75--88."},{"key":"e_1_3_2_1_70_1","volume-title":"Attention is all you need. Advances in neural information processing systems 30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_71_1","volume-title":"Images Speak in Images: A Generalist Painter for In-Context Visual Learning. (Dec","author":"Wang Xinlong","year":"2022","unstructured":"Xinlong Wang, Wen Wang, Yue Cao, Chunhua Shen, and Tiejun Huang. 2022. Images Speak in Images: A Generalist Painter for In-Context Visual Learning. (Dec 2022)."},{"key":"e_1_3_2_1_72_1","unstructured":"Xinlong Wang Xiaosong Zhang Yue Cao Wen Wang Chunhua Shen and Tiejun Huang. [n. d.]. SegGPT: Segmenting Everything In Context. ([n. d.])."},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3412683"},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611937"},{"key":"e_1_3_2_1_75_1","volume-title":"Nas-unet: Neural architecture search for medical image segmentation","author":"Weng Yu","year":"2019","unstructured":"Yu Weng, Tianbao Zhou, Yujie Li, and Xiaoyu Qiu. 2019. Nas-unet: Neural architecture search for medical image segmentation. IEEE access 7 (2019), 44247-- 44257."},{"key":"e_1_3_2_1_76_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2024.108135"},{"key":"e_1_3_2_1_77_1","volume-title":"AFSC: Adaptive Fourier Space Compression for Anomaly Detection. arXiv preprint arXiv:2204.07963","author":"Xu Haote","year":"2022","unstructured":"Haote Xu, Yunlong Zhang, Liyan Sun, Chenxin Li, Yue Huang, and Xinghao Ding. 2022. AFSC: Adaptive Fourier Space Compression for Anomaly Detection. arXiv preprint arXiv:2204.07963 (2022)."},{"key":"e_1_3_2_1_78_1","volume-title":"MRM: Masked Relation Modeling for Medical Image Pre-Training with Genetics. In ICCV. 21452-- 21462.","author":"Yang Qiushi","year":"2023","unstructured":"Qiushi Yang, Wuyang Li, Baopu Li, and Yixuan Yuan. 2023. MRM: Masked Relation Modeling for Medical Image Pre-Training with Genetics. In ICCV. 21452-- 21462."},{"key":"e_1_3_2_1_79_1","volume-title":"Inpaint anything: Segment anything meets image inpainting. arXiv preprint arXiv:2304.06790","author":"Yu Tao","year":"2023","unstructured":"Tao Yu, Runseng Feng, Ruoyu Feng, Jinming Liu, Xin Jin, Wenjun Zeng, and Zhibo Chen. 2023. Inpaint anything: Segment anything meets image inpainting. arXiv preprint arXiv:2304.06790 (2023)."},{"key":"e_1_3_2_1_80_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16434-7_23"},{"key":"e_1_3_2_1_81_1","volume-title":"Customized Segment Anything Model for Medical Image Segmentation. (Apr","author":"Zhang Kaidong","year":"2023","unstructured":"Kaidong Zhang and Dong Liu. 2023. Customized Segment Anything Model for Medical Image Segmentation. (Apr 2023)."},{"key":"e_1_3_2_1_82_1","unstructured":"Renrui Zhang Jiaming Han Aojun Zhou Xiangfei Hu Shilin Yan Pan Lu Hong- sheng Li Peng Gao and Yu Qiao. [n. d.]. LLaMA-Adapter: Efficient Fine-tuning of Language Models with Zero-init Attention. ([n. d.])."},{"key":"e_1_3_2_1_83_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548060"},{"key":"e_1_3_2_1_84_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548115"},{"key":"e_1_3_2_1_85_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87231-1_15"},{"key":"e_1_3_2_1_86_1","unstructured":"Xueyan Zou Jianwei Yang Hao Zhang Feng Li Linjie Li Jianfeng Gao YongJae Lee Madison Madison Microsoft Research Redmond Hkust Microsoft Cloud and Ai Ai. [n. d.]. Segment Everything Everywhere All at Once. ([n. d.])."}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680628","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3680628","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:57Z","timestamp":1750295877000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680628"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":86,"alternative-id":["10.1145\/3664647.3680628","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3680628","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}