{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T22:31:58Z","timestamp":1769639518996,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":55,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819609598","type":"print"},{"value":"9789819609604","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,12,8]],"date-time":"2024-12-08T00:00:00Z","timestamp":1733616000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,8]],"date-time":"2024-12-08T00:00:00Z","timestamp":1733616000000},"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\/978-981-96-0960-4_5","type":"book-chapter","created":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T07:36:47Z","timestamp":1733557007000},"page":"71-88","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["FG-CXR: A Radiologist-Aligned Gaze Dataset for\u00a0Enhancing Interpretability in\u00a0Chest X-Ray Report Generation"],"prefix":"10.1007","author":[{"given":"Trong Thang","family":"Pham","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ngoc-Vuong","family":"Ho","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nhat-Tan","family":"Bui","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Thinh","family":"Phan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Patel","family":"Brijesh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Donald","family":"Adjeroh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gianfranco","family":"Doretto","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anh","family":"Nguyen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Carol C.","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hien","family":"Nguyen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ngan","family":"Le","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,8]]},"reference":[{"key":"5_CR1","doi-asserted-by":"crossref","unstructured":"Bigolin\u00a0Lanfredi, R., Zhang, M., et\u00a0al.: Reflacx, a dataset of reports and eye-tracking data for localization of abnormalities in chest x-rays. Scientific data (2022)","DOI":"10.1038\/s41597-022-01441-z"},{"key":"5_CR2","doi-asserted-by":"crossref","unstructured":"Bustos, A., Pertusa, A., Salinas, J.M., de\u00a0la Iglesia-Vay\u00e1, M.: Padchest: A large chest x-ray image dataset with multi-label annotated reports. Medical image analysis (2020)","DOI":"10.1016\/j.media.2020.101797"},{"key":"5_CR3","doi-asserted-by":"crossref","unstructured":"Chen, Z., Shen, Y., Song, Y., Wan, X.: Cross-modal memory networks for radiology report generation. arXiv preprint arXiv:2204.13258 (2022)","DOI":"10.18653\/v1\/2021.acl-long.459"},{"key":"5_CR4","doi-asserted-by":"crossref","unstructured":"Chen, Z., Song, Y., Chang, T.H., Wan, X.: Generating radiology reports via memory-driven transformer. arXiv preprint arXiv:2010.16056 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.112"},{"key":"5_CR5","unstructured":"Coffman, E., Clark, R., Bui, N.T., Pham, T.T., Kegley, B., Powell, J.G., Zhao, J., Le, N.: Cattleface-rgbt: Rgb-t cattle facial landmark benchmark. arXiv preprint arXiv:2406.03431 (2024)"},{"key":"5_CR6","doi-asserted-by":"crossref","unstructured":"Cornia, M., Stefanini, M., Baraldi, L., Cucchiara, R.: Meshed-Memory Transformer for Image Captioning. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"5_CR7","doi-asserted-by":"crossref","unstructured":"Datta, S., Roberts, K.: A dataset of chest x-ray reports annotated with spatial role labeling annotations. Data in Brief (2020)","DOI":"10.1016\/j.dib.2020.106056"},{"key":"5_CR8","doi-asserted-by":"crossref","unstructured":"Demner-Fushman, D., Kohli, M.D., Rosenman, M.B., Shooshan, S.E., Rodriguez, L., Antani, S., Thoma, G.R., McDonald, C.J.: Preparing a collection of radiology examinations for distribution and retrieval. Journal of the American Medical Informatics Association (2016)","DOI":"10.1093\/jamia\/ocv080"},{"key":"5_CR9","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: A large-scale hierarchical image database. In: CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"5_CR10","doi-asserted-by":"crossref","unstructured":"Filice, R.W., Stein, A., et\u00a0al.: Crowdsourcing pneumothorax annotations using machine learning annotations on the nih chest x-ray dataset. Journal of digital imaging (2020)","DOI":"10.1007\/s10278-019-00299-9"},{"key":"5_CR11","doi-asserted-by":"crossref","unstructured":"Geis, J.R., Brady, A.P., Wu, C.C., Spencer, J., Ranschaert, E., Jaremko, J.L., Langer, S.G., Borondy Kitts, A., Birch, J., Shields, W.F., et al.: Ethics of artificial intelligence in radiology: summary of the joint european and north american multisociety statement. Radiology 293(2), 436\u2013440 (2019)","DOI":"10.1148\/radiol.2019191586"},{"issue":"5","key":"5_CR12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3236009","volume":"51","author":"R Guidotti","year":"2018","unstructured":"Guidotti, R., Monreale, A., Ruggieri, S., Turini, F., Giannotti, F., Pedreschi, D.: A survey of methods for explaining black box models. ACM computing surveys (CSUR) 51(5), 1\u201342 (2018)","journal-title":"ACM computing surveys (CSUR)"},{"key":"5_CR13","doi-asserted-by":"crossref","unstructured":"Irvin, J., Rajpurkar, P., Ko, M., Yu, Y., Ciurea-Ilcus, S., Chute, C., Marklund, H., Haghgoo, B., Ball, R., Shpanskaya, K., et\u00a0al.: Chexpert: A large chest radiograph dataset with uncertainty labels and expert comparison. In: AAAI (2019)","DOI":"10.1609\/aaai.v33i01.3301590"},{"key":"5_CR14","unstructured":"Jaeger, S., Candemir, S., Antani, S., W\u00e1ng, Y.X.J., Lu, P.X., Thoma, G.: Two public chest x-ray datasets for computer-aided screening of pulmonary diseases. Quantitative imaging in medicine and surgery (2014)"},{"key":"5_CR15","doi-asserted-by":"crossref","unstructured":"Jing, B., Wang, Z., Xing, E.: Show, describe and conclude: On exploiting the structure information of chest x-ray reports. arXiv preprint arXiv:2004.12274 (2020)","DOI":"10.18653\/v1\/P19-1657"},{"key":"5_CR16","doi-asserted-by":"crossref","unstructured":"Johnson, A.E., Pollard, T.J., Berkowitz, S.J., et\u00a0al.: Mimic-cxr, a de-identified publicly available database of chest radiographs with free-text reports. Scientific data (2019)","DOI":"10.1038\/s41597-019-0322-0"},{"key":"5_CR17","unstructured":"Karargyris, A., Kashyap, S., Lourentzou, I., Wu, J., Tong, M., Sharma, A., Abedin, S., Beymer, D., Mukherjee, V., Krupinski, E., et\u00a0al.: Eye gaze data for chest x-rays. PhysioNet (2020)"},{"key":"5_CR18","doi-asserted-by":"crossref","unstructured":"Kashyap, S., Karargyris, A., Wu, J., Gur, Y., Sharma, A., Wong, K.C., Moradi, M., Syeda-Mahmood, T.: Looking in the right place for anomalies: Explainable ai through automatic location learning. In: ISBI (2020)","DOI":"10.1109\/ISBI45749.2020.9098370"},{"key":"5_CR19","doi-asserted-by":"crossref","unstructured":"Khan, S., Naseer, M., Hayat, M., Zamir, S.W., Khan, F.S., Shah, M.: Transformers in vision: A survey. ACM computing surveys (CSUR) 54(10s), 1\u201341 (2022)","DOI":"10.1145\/3505244"},{"key":"5_CR20","unstructured":"Kim, B., Wattenberg, M., et\u00a0al.: Interpretability beyond feature attribution: Quantitative testing with concept activation vectors (tcav). In: ICML (2018)"},{"key":"5_CR21","doi-asserted-by":"crossref","unstructured":"Le, M.Q., Graikos, A., Yellapragada, S., Gupta, R., Saltz, J., Samaras, D.: $$\\infty $$-brush: Controllable large image synthesis with diffusion models in infinite dimensions. arXiv preprint arXiv:2407.14709 (2024)","DOI":"10.1007\/978-3-031-73411-3_22"},{"key":"5_CR22","doi-asserted-by":"crossref","unstructured":"Le, N., Pham, T., Do, T., Tjiputra, E., Tran, Q.D., Nguyen, A.: Music-driven group choreography. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 8673\u20138682 (2023)","DOI":"10.1109\/CVPR52729.2023.00838"},{"key":"5_CR23","doi-asserted-by":"crossref","unstructured":"Lei, B., Huang, S., et\u00a0al.: Self-co-attention neural network for anatomy segmentation in whole breast ultrasound. Medical image analysis (2020)","DOI":"10.1016\/j.media.2020.101753"},{"key":"5_CR24","unstructured":"Li, Y., Liang, X., Hu, Z., Xing, E.P.: Hybrid retrieval-generation reinforced agent for medical image report generation. Advances in neural information processing systems (2018)"},{"key":"5_CR25","doi-asserted-by":"crossref","unstructured":"Liu, F., Wu, X., Ge, S., Fan, W., Zou, Y.: Exploring and distilling posterior and prior knowledge for radiology report generation. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01354"},{"key":"5_CR26","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: ICLR (2019)"},{"key":"5_CR27","doi-asserted-by":"crossref","unstructured":"Miller, T.: Explanation in artificial intelligence: Insights from the social sciences. Artif. Intell. 267, 1\u201338 (2019)","DOI":"10.1016\/j.artint.2018.07.007"},{"key":"5_CR28","doi-asserted-by":"crossref","unstructured":"Nauta, M., Schl\u00f6tterer, J., van Keulen, M., Seifert, C.: Pip-net: Patch-based intuitive prototypes for interpretable image classification. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00269"},{"key":"5_CR29","doi-asserted-by":"crossref","unstructured":"Nguyen, T.P., Pham, T.T., Nguyen, T., Le, H., Nguyen, D., Lam, H., Nguyen, P., Fowler, J., Tran, M.T., Le, N.: Embryosformer: Deformable transformer and collaborative encoding-decoding for embryos stage development classification. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision. pp. 1981\u20131990 (2023)","DOI":"10.1109\/WACV56688.2023.00202"},{"key":"5_CR30","doi-asserted-by":"crossref","unstructured":"Nguyen, V.D., Khaldi, K., Nguyen, D., Mantini, P., Shah, S.: Contrastive viewpoint-aware shape learning for long-term person re-identification. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision. pp. 1041\u20131049 (2024)","DOI":"10.1109\/WACV57701.2024.00108"},{"key":"5_CR31","doi-asserted-by":"crossref","unstructured":"Nguyen, V.D., Mantini, P., Shah, S.K.: Occluded cloth-changing person re-identification via occlusion-aware appearance and shape reasoning. In: 2024 IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS). pp.\u00a01\u20138. IEEE (2024)","DOI":"10.1109\/AVSS61716.2024.10672564"},{"key":"5_CR32","doi-asserted-by":"crossref","unstructured":"Nguyen, V.D., Mirza, S., Zakeri, A., Gupta, A., Khaldi, K., Aloui, R., Mantini, P., Shah, S.K., Merchant, F.: Tackling domain shifts in person re-identification: A survey and analysis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 4149\u20134159 (2024)","DOI":"10.1109\/CVPRW63382.2024.00418"},{"key":"5_CR33","doi-asserted-by":"crossref","unstructured":"Nicolson, A., Dowling, J., Koopman, B.: Improving chest X-ray report generation by leveraging warm starting. Artificial Intelligence in Medicine (2023)","DOI":"10.1016\/j.artmed.2023.102633"},{"key":"5_CR34","doi-asserted-by":"crossref","unstructured":"Pham, T.T., Brecheisen, J., Nguyen, A., Nguyen, H., Le, N.: I-ai: A controllable & interpretable ai system for decoding radiologists\u2019 intense focus for accurate cxr diagnoses. In: WACV (2024)","DOI":"10.1109\/WACV57701.2024.00767"},{"key":"5_CR35","doi-asserted-by":"crossref","unstructured":"Pham, T.T., Do, T., Le, N., Le, N., Nguyen, H., Tjiputra, E., Tran, Q., Nguyen, A.: Style transfer for 2d talking head generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 7500\u20137509 (2024)","DOI":"10.1109\/CVPRW63382.2024.00745"},{"key":"5_CR36","unstructured":"Radford, A., Wu, J., et\u00a0al.: Language models are unsupervised multitask learners. OpenAI blog (2019)"},{"key":"5_CR37","doi-asserted-by":"crossref","unstructured":"Rudin, C.: Stop explaining black box machine learning models for high stakes decisions and use interpretable models instead. Nature machine intelligence (2019)","DOI":"10.1038\/s42256-019-0048-x"},{"key":"5_CR38","doi-asserted-by":"crossref","unstructured":"Rudin, C., Chen, C., Chen, Z., Huang, H., Semenova, L., Zhong, C.: Interpretable machine learning: Fundamental principles and 10 grand challenges. Statistics Surveys (2022)","DOI":"10.1214\/21-SS133"},{"key":"5_CR39","unstructured":"Sanh, V., Debut, L., Chaumond, J., Wolf, T.: Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108 (2019)"},{"key":"5_CR40","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., et\u00a0al.: Grad-cam: Visual explanations from deep networks via gradient-based localization. In: CVPR (2017)","DOI":"10.1109\/ICCV.2017.74"},{"key":"5_CR41","doi-asserted-by":"crossref","unstructured":"Shetty, R., Rohrbach, M., Anne\u00a0Hendricks, L., Fritz, M., Schiele, B.: Speaking the same language: Matching machine to human captions by adversarial training. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.445"},{"key":"5_CR42","doi-asserted-by":"crossref","unstructured":"Shih, G., Wu, C.C., et al.: Augmenting the national institutes of health chest radiograph dataset with expert annotations of possible pneumonia. Artificial Intelligence, Radiology (2019)","DOI":"10.1148\/ryai.2019180041"},{"key":"5_CR43","doi-asserted-by":"crossref","unstructured":"Tanida, T., M\u00fcller, P., Kaissis, G., Rueckert, D.: Interactive and explainable region-guided radiology report generation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00718"},{"key":"5_CR44","doi-asserted-by":"crossref","unstructured":"Tanida, T., M\u00fcller, P., Kaissis, G., Rueckert, D.: Interactive and explainable region-guided radiology report generation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00718"},{"key":"5_CR45","doi-asserted-by":"crossref","unstructured":"Team, P.P., Gohagan, J.K., Prorok, P.C., Hayes, R.B., Kramer, B.S.: The prostate, lung, colorectal and ovarian (plco) cancer screening trial of the national cancer institute: history, organization, and status. Controlled clinical trials (2000)","DOI":"10.1016\/S0197-2456(00)00097-0"},{"key":"5_CR46","doi-asserted-by":"crossref","unstructured":"Tran, M.T., Nguyen, T.V., Hoang, T.H., Le, T.N., Nguyen, K.T., Dinh, D.T., Nguyen, T.A., Nguyen, H.D., Hoang, X.N., Nguyen, T.T., et\u00a0al.: itask-intelligent traffic analysis software kit. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops. pp. 612\u2013613 (2020)","DOI":"10.1109\/CVPRW50498.2020.00314"},{"key":"5_CR47","doi-asserted-by":"crossref","unstructured":"Ullah, I., Ali, F., Shah, B., El-Sappagh, S., Abuhmed, T., Park, S.H.: A deep learning based dual encoder\u2013decoder framework for anatomical structure segmentation in chest x-ray images. Scientific Reports (2023)","DOI":"10.1038\/s41598-023-27815-w"},{"key":"5_CR48","doi-asserted-by":"crossref","unstructured":"Vo, K., Pham, T.T., Yamazaki, K., Tran, M., Le, N.: Dna: Deformable neural articulations network for template-free dynamic 3d human reconstruction from monocular rgb-d video. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 3676\u20133685 (2023)","DOI":"10.1109\/CVPRW59228.2023.00375"},{"key":"5_CR49","doi-asserted-by":"crossref","unstructured":"Wang, X., Peng, Y., Lu, L., Lu, Z., Bagheri, M., Summers, R.M.: Chestx-ray8: Hospital-scale chest x-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.369"},{"key":"5_CR50","doi-asserted-by":"crossref","unstructured":"Wu, H., Xiao, B., Codella, N., Liu, M., Dai, X., Yuan, L., Zhang, L.: Cvt: Introducing convolutions to vision transformers. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"5_CR51","unstructured":"Wu, J.T., Agu, N.N., Lourentzou, I., Sharma, A., Paguio, J.A., Yao, J.S., Dee, E.C., Mitchell, W., Kashyap, S., Giovannini, A., et\u00a0al.: Chest imagenome dataset (version 1.0. 0). PhysioNet (2021)"},{"key":"5_CR52","doi-asserted-by":"crossref","unstructured":"Xiong, Y., Dai, B., Lin, D.: Move forward and tell: A progressive generator of video descriptions. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01252-6_29"},{"key":"5_CR53","doi-asserted-by":"crossref","unstructured":"You, D., Liu, F., Ge, S., Xie, X., Zhang, J., Wu, X.: Aligntransformer: Hierarchical alignment of visual regions and disease tags for medical report generation. In: MICCAI (2021)","DOI":"10.1007\/978-3-030-87199-4_7"},{"key":"5_CR54","unstructured":"Zhang, S., Xu, Y., et\u00a0al.: Biomedclip: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs. arXiv preprint arXiv:2303.00915 (2023)"},{"key":"5_CR55","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Wang, X., Xu, Z., Yu, Q., Yuille, A., Xu, D.: When radiology report generation meets knowledge graph. In: AAAI (2020)","DOI":"10.1609\/aaai.v34i07.6989"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-0960-4_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T08:31:22Z","timestamp":1733560282000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-0960-4_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,8]]},"ISBN":["9789819609598","9789819609604"],"references-count":55,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-0960-4_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,8]]},"assertion":[{"value":"8 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hanoi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vietnam","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":"8 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}