WELCOME TO VinSPACEVinSpace is an open access institutional repository provided by VinUniversity Library for scholarly research produced by members of the VinUniversity community. It enables members of the VinUniversity community to post, organize, preserve and disseminate their research and publication online.
Please check if your publisher allows self-archiving at SHERPA/RoMEo's publisher copyright policies
Community in VinSpace
Select a community to browse its collections.
Multimodal Unrolled Robust PCA for Background Foreground Separation
Background foreground separation (BFS) is a popular computer vision problem where dynamic foreground objects are separated from the static background of a scene. Typically, this is performed using consumer cameras because of their low cost, human interpretability, and high resolution. Yet, cameras and the BFS algorithms that process their data have common failure modes due to lighting changes, highly reflective surfaces, and occlusion. One solution is to incorporate an additional sensor modality that provides robustness to such failure modes. In this paper, we explore the ability of a cost-effective radar system to augment the popular Robust PCA technique for BFS. We apply the emerging technique of algorithm unrolling to yield real-time computation, feedforward inference, and strong generalization in comparison with traditional deep learning methods. We benchmark on the RaDICaL dataset to demonstrate both quantitative improvements of incorporating radar data and qualitative improvements that confirm robustness to common failure modes of image-based methods.
Multimodal Fusion Using Sparse Cca For Breast Cancer Survival Prediction
Effective understanding of a disease such as cancer requires fusing multiple sources of information captured across physical scales by multimodal data. In this work, we propose a novel feature embedding module that derives from canonical correlation analyses to account for intra-modality and inter-modality correlations. Experiments on simulated and real data demonstrate how our proposed module can learn well-correlated multi-dimensional embeddings. These embeddings perform competitively on one-year survival classification of TCGA-BRCA breast cancer patients, yielding average F1 scores up to 58.69% under 5-fold cross-validation.
Migrant and refugee youth perspectives on sexual and reproductive health rights in Australia: a systematic review protocol
Background: Migrant and refugee youth (MRY) in Australia face specific experiences that inform their sexual and reproductive health and rights. Migrant and refugee communities experience poorer health outcomes, have lower health service uptake and have culturally-informed understandings of sexual health. Additionally, youth are particularly vulnerable to poor sexual health. This paper details a study protocol for a systematic review of evidence on how Australian MRY understand and construct sexual and reproductive health and rights. Methods: A systematic review of available literature will be conducted and reported as per Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. A systematic search of nine databases – Medline, EMBASE, CINAHL, APAIS, ProQuest, PsycInfo, Web of Science, SCOPUS, and PubMed – from January 2000 onwards will be undertaken. Hand searches for further relevant studies, including grey literature, will be conducted. Two reviewers will independently screen titles, abstracts and full-text articles against selection criteria. The Mixed Method Appraisal Tool (MMAT) will be used to assess the quality of included studies. Thematic synthesis methods will be used for data extraction and synthesis, aided by QSR NVivo 12. Discussion: The proposed systematic review will synthesize evidence on how Australian migrant and refugee youth construct and understand sexual and reproductive health and rights, as well as the factors shaping these constructions. The synthesis will fill existing gaps in understandings of how migrant and refugee youth make decisions and understand their rights. In examining Australian migrant and refugee youth, the review will have specific relevance to the Asia-Pacific region. Gaining youth perspectives will provide crucial information on how practice and policy can be improved to deliver to this population.
Lipstick ain’t enough: Beyond Color Matching for In-the-Wild Makeup Transfer
Makeup transfer is the task of applying on a source face the makeup style from a reference image. Real-life makeups are diverse and wild, which cover not only color-changing but also patterns, such as stickers, blushes, and jewelries. However, existing works overlooked the latter components and confined makeup transfer to color manipulation, focusing only on light makeup styles. In this work, we propose a holistic makeup transfer framework that can handle all the mentioned makeup components. It consists of an improved color transfer branch and a novel pattern transfer branch to learn all makeup properties, including color, shape, texture, and location. To train and evaluate such a system, we also introduce new makeup datasets for real and synthetic extreme makeup. Experimental results show that our framework achieves the state of the art performance on both light and extreme makeup styles. Code is available at https://github.com/VinAIResearch/CPM.
Interpreting chest X-rays via CNNs that exploit hierarchical disease dependencies and uncertainty labels
Chest radiography is one of the most common types of diagnostic radiology exams, which is critical for screening and diagnosis of many different thoracic diseases. Specialized algorithms have been developed to detect several specific pathologies such as lung nodules or lung cancer. However, accurately detecting the presence of multiple diseases from chest X-rays (CXRs) is still a challenging task. This paper presents a supervised multi-label classification framework based on deep convolutional neural networks (CNNs) for predicting the presence of 14 common thoracic diseases and observations. We tackle this problem by training state-of-the-art CNNs that exploit hierarchical dependencies among abnormality labels. We also propose to use the label smoothing technique for a better handling of uncertain samples, which occupy a significant portion of many CXR datasets. Our model is trained on over 200,000 CXRs of the recently released CheXpert dataset and achieves a mean area under the curve (AUC) of 0.940 in predicting 5 selected pathologies from the validation set. This is the highest AUC score yet reported to date. The proposed method is also evaluated on the independent test set of the CheXpert competition, which is composed of 500 CXR studies annotated by a panel of 5 experienced radiologists. The performance is on average better than 2.6 out of 3 other individual radiologists with a mean AUC of 0.930, which ranks first on the CheXpert leaderboard at the time of writing this paper.