We propose an improvement to the landmark validity loss. Landmark detection
is widely used in head pose estimation, eyelid shape extraction, as well as
pupil and iris segmentation. There are numerous additional applications where
landmark detection is used to estimate the shape of complex objects. One part
of this process is the accurate and fine-grained detection of the shape. The
other part is the validity or inaccuracy per landmark, which can be used to
detect unreliable areas, where the shape possibly does not fit, and to improve
the accuracy of the entire shape extraction by excluding inaccurate landmarks.
We propose a normalization in the loss formulation, which improves the accuracy
of the entire approach due to the numerical balance of the normalized
inaccuracy. In addition, we propose a margin for the inaccuracy to reduce the
impact of gradients, which are produced by negligible errors close to the
ground truth.

我们提出了一种改进的地标有效性损失，通过归一化来提高准确度，并通过设定不准确性的边界来减少梯度对结果的影响。

基於回歸的眼睛特徵提取中的標準化有效性分數

Normalized Validity Scores for DNNs in Regression based Eye Feature  Extraction

Data Envelopment Analysis (DEA) is a technique used to measure the efficiency
of decision-making units (DMUs). In order to measure the efficiency of DMUs,
the essential requirement is input-output data. Data is usually collected by
humans, machines, or both. Due to human/machine errors, there are chances of
having some missing values or inaccuracy, such as
vagueness/uncertainty/hesitation in the collected data. In this situation, it
will be difficult to measure the efficiencies of DMUs accurately. To overcome
these shortcomings, a method is presented that can deal with missing values and
inaccuracy in the data. To measure the performance efficiencies of DMUs, an
input minimization BCC (IMBCC) model in a fully intuitionistic fuzzy (IF)
environment is proposed. To validate the efficacy of the proposed fully
intuitionistic fuzzy input minimization BCC (FIFIMBCC) model and the technique
to deal with missing values in the data, a real-life application to measure the
performance efficiencies of Indian police stations is presented.

提出了一种使用直觉模糊方法测量具有缺失值的决策单元效率的输入最小化 BCC 模型，以及在印度警察站应用该模型来处理数据缺失和不精确性的技术。

具有缺失数据的完全直觉模糊数据包络分析模型的发展：在印度警察部门的应用

Development of fully intuitionistic fuzzy data envelopment analysis model with missing data: an application to Indian police sector

Scene text image super-resolution (STISR) has been regarded as an important
pre-processing task for text recognition from low-resolution scene text images.
Most recent approaches use the recognizer's feedback as clues to guide
super-resolution. However, directly using recognition clue has two problems: 1)
Compatibility. It is in the form of probability distribution, has an obvious
modal gap with STISR - a pixel-level task; 2) Inaccuracy. it usually contains
wrong information, thus will mislead the main task and degrade super-resolution
performance. In this paper, we present a novel method C3-STISR that jointly
exploits the recognizer's feedback, visual and linguistical information as
clues to guide super-resolution. Here, visual clue is from the images of texts
predicted by the recognizer, which is informative and more compatible with the
STISR task; while linguistical clue is generated by a pre-trained
character-level language model, which is able to correct the predicted texts.
We design effective extraction and fusion mechanisms for the triple cross-modal
clues to generate a comprehensive and unified guidance for super-resolution.
Extensive experiments on TextZoom show that C3-STISR outperforms the SOTA
methods in fidelity and recognition performance. Code is available in
this https URL

该论文提出了一种结合识别器反馈、视觉和语言信息的方法 C3-STISR 来引导超分辨率，通过有效的提取和融合机制，生成了全面和统一的引导， 在 TextZoom 上的实验表明，C3-STISR 在保真度和识别性能方面优于最先进的方法。