When answering natural language questions over knowledge bases (KBs), incompleteness in the KB can naturally lead to many questions being unanswerable. While answerability has been explored in other QA settings, it has not been studied for QA over knowledge bases (KBQA). We first identify various forms of KB incompleteness that can result in a question being unanswerable. We then propose GrailQAbility, a new benchmark dataset, which systematically modifies GrailQA (a popular KBQA dataset) to represent all these incompleteness issues. Testing two state-of-the-art KBQA models (trained on original GrailQA as well as our GrailQAbility), we find that both models struggle to detect unanswerable questions, or sometimes detect them for the wrong reasons. Consequently, both models suffer significant loss in performance, underscoring the need for further research in making KBQA systems robust to unanswerability.

Bike sharing systems often suffer from poor capacity management as a result of variable demand. These bike sharing systems would benefit from models to predict demand in order to moderate the number of bikes stored at each station. In this paper, we attempt to apply a graph neural network model to predict bike demand in the New York City, Citi Bike dataset.

Accurate segmentation of live cell images has broad applications in clinical and research contexts. Deep learning methods have been able to perform cell segmentations with high accuracy; however developing machine learning models to do this requires access to high fidelity images of live cells. This is often not available due to resource constraints like limited accessibility to high performance microscopes or due to the nature of the studied organisms. Segmentation on low resolution images of live cells is a difficult task. This paper proposes a method to perform live cell segmentation with low resolution images by performing super-resolution as a pre-processing step in the segmentation pipeline.

The vision community has explored numerous pose guided human editing methods due to their extensive practical applications. Most of these methods still use an image-to-image formulation in which a single image is given as input to produce an edited image as output. However, the problem is ill-defined in cases when the target pose is significantly different from the input pose. Existing methods then resort to in-painting or style transfer to handle occlusions and preserve content. In this paper, we explore the utilization of multiple views to minimize the issue of missing information and generate an accurate representation of the underlying human model. To fuse the knowledge from multiple viewpoints, we design a selector network that takes the pose keypoints and texture from images and generates an interpretable per-pixel selection map. After that, the encodings from a separate network (trained on a single image human reposing task) are merged in the latent space. This enables us to generate accurate, precise, and visually coherent images for different editing tasks. We show the application of our network on 2 newly proposed tasks - Multi-view human reposing, and Mix-and-match human image generation. Additionally, we study the limitations of single-view editing and scenarios in which multi-view provides a much better alternative.

在本文中，我们提出了一种新型的保守性混沌标准MAP驱动的动态DNA编码（编码，加法，减法和解码），用于图像加密。所提出的图像加密算法是一种动态DNA编码算法，即，对于每个像素的加密不同的规则，用于编码，加法/减法，解码等的不同规则是基于伪随机序列随机选择的，该序列是在保守的混乱标准映射的帮助下生成的。我们提出了一种新颖的方式，可以通过保守的混沌标准图生成伪随机序列，并在最严格的伪随机测试套件（NIST Test Suite）中进行严格的测试，然后在提出的图像加密算法中使用它们。我们的图像加密算法结合了一种独特的进纸和反馈机制，以生成和修改动态的一次性像素，这些像素进一步用于加密普通图像的每个像素，因此，在明文上以及对明文以及对明文的敏感性进行了敏感性密文。该算法中使用的所有控制伪序序列都是针对通过混乱图的迭代（在生成过程中）的迭代依赖性的参数的不同值（秘密键的一部分）生成的，因此也具有极端的密钥灵敏度。性能和安全分析已通过直方图分析，相关分析，信息熵分析，基于DNA序列的分析，感知质量分析，关键灵敏度分析，明文灵敏度分析等进行了广泛的执行，结果是有希望的，并证明了证明的鲁棒性针对各种常见的密码分析攻击的算法。

医学成像是现代医学治疗和诊断的基石。但是，对于特定静脉局体任务的成像方式的选择通常涉及使用特定模式的可行性（例如，短期等待时间，低成本，快速获取，辐射/侵入性降低）与临床上的预期性能之间的权衡。任务（例如，诊断准确性，治疗计划的功效和指导）。在这项工作中，我们旨在运用从较不可行但表现更好（优越）模式中学到的知识，以指导利用更可行但表现不佳（劣等）模式，并将其转向提高性能。我们专注于深度学习用于基于图像的诊断。我们开发了一个轻量级的指导模型，该模型在训练仅消耗劣质模式的模型时利用从优越方式中学到的潜在表示。我们在两种临床应用中检查了我们方法的优势：从临床和皮肤镜图像中的多任务皮肤病变分类以及来自多序列磁共振成像（MRI）和组织病理学图像的脑肿瘤分类。对于这两种情况，我们在不需要出色的模态的情况下显示出劣质模式的诊断性能。此外，在脑肿瘤分类的情况下，我们的方法的表现优于在上级模态上训练的模型，同时产生与推理过程中使用两种模态的模型相当的结果。

我们开发了一种自主导航算法，用于在二维环境中运行的机器人杂乱，其具有任意凸形的障碍物。所提出的导航方法依赖于混合反馈，以保证机器人对预定目标位置的全局渐近稳定，同时确保无障碍工作空间的前向不变性。主要思想在于基于机器人相对于最近障碍的接近设计，在移动到目标模式和障碍物避免模式之间设计适当的切换策略。当机器人初始化远离障碍物的边界时，所提出的混合控制器产生连续速度输入轨迹。最后，我们为所提出的混合控制器的基于传感器的实现提供了一种算法过程，并通过一些仿真结果验证其有效性。