Zobrazeno 1 - 10
of 488
pro vyhledávání: '"Duan, Jinming"'
Deep image registration has demonstrated exceptional accuracy and fast inference. Recent advances have adopted either multiple cascades or pyramid architectures to estimate dense deformation fields in a coarse-to-fine manner. However, due to the casc
Externí odkaz:
http://arxiv.org/abs/2407.13426
Autor:
Geng, Tiantian, Wang, Teng, Zhang, Yanfu, Duan, Jinming, Guan, Weili, Zheng, Feng, shao, Ling
Video localization tasks aim to temporally locate specific instances in videos, including temporal action localization (TAL), sound event detection (SED) and audio-visual event localization (AVEL). Existing methods over-specialize on each task, overl
Externí odkaz:
http://arxiv.org/abs/2404.03179
Autor:
Rendell, Sean, Duan, Jinming
Diffeomorphic image registration is a commonly used method to deform one image to resemble another. While warping a single image to another is useful, it can be advantageous to warp multiple images simultaneously, such as in tracking the motion of th
Externí odkaz:
http://arxiv.org/abs/2403.16240
Autor:
Zhang, Yuting, Liu, Boyang, Bunting, Karina V., Brind, David, Thorley, Alexander, Karwath, Andreas, Lu, Wenqi, Zhou, Diwei, Wang, Xiaoxia, Mobley, Alastair R., Tica, Otilia, Gkoutos, Georgios, Kotecha, Dipak, Duan, Jinming
The echocardiographic measurement of left ventricular ejection fraction (LVEF) is fundamental to the diagnosis and classification of patients with heart failure (HF). In order to quantify LVEF automatically and accurately, this paper proposes a new p
Externí odkaz:
http://arxiv.org/abs/2403.12152
This paper introduces the concept of uniform classification, which employs a unified threshold to classify all samples rather than adaptive threshold classifying each individual sample. We also propose the uniform classification accuracy as a metric
Externí odkaz:
http://arxiv.org/abs/2403.07289
In unsupervised medical image registration, the predominant approaches involve the utilization of a encoder-decoder network architecture, allowing for precise prediction of dense, full-resolution displacement fields from given paired images. Despite
Externí odkaz:
http://arxiv.org/abs/2402.03585
The Alternating Direction Method of Multipliers (ADMM) has gained significant attention across a broad spectrum of machine learning applications. Incorporating the over-relaxation technique shows potential for enhancing the convergence rate of ADMM.
Externí odkaz:
http://arxiv.org/abs/2401.00657
Sample-to-class-based face recognition models can not fully explore the cross-sample relationship among large amounts of facial images, while sample-to-sample-based models require sophisticated pairing processes for training. Furthermore, neither met
Externí odkaz:
http://arxiv.org/abs/2311.02523
Autor:
Hao, Luoying, Hu, Yan, Lin, Wenjun, Wang, Qun, Li, Heng, Fu, Huazhu, Duan, Jinming, Liu, Jiang
Recognition and localization of surgical detailed actions is an essential component of developing a context-aware decision support system. However, most existing detection algorithms fail to provide high-accuracy action classes even having their loca
Externí odkaz:
http://arxiv.org/abs/2310.03377
U-Net style networks are commonly utilized in unsupervised image registration to predict dense displacement fields, which for high-resolution volumetric image data is a resource-intensive and time-consuming task. To tackle this challenge, we first pr
Externí odkaz:
http://arxiv.org/abs/2307.02997