在过去的几年中，无人驾驶汽车（UAV）的领域已经达到了高水平的成熟度。因此，将此类平台从封闭的实验室带到与人类的日常互动对于无人机的商业化很重要。本文的一种特殊人类企业感兴趣的方案是有效载荷切换计划，无人机应要求人将有效载荷移交给人类的有效载荷。在此范围内，本文提出了一种新型的实时人类UAV相互作用检测方法，其中开发了基于短期记忆（LSTM）的神经网络，以检测由人类相互作用动态导致的状态概况。提出了一种新的数据预处理技术；该技术利用培训和测试无人机的估计过程参数来构建动态不变测试数据。提出的检测算法是轻量级的，因此可以使用Off Shelf UAV平台实时部署；此外，它仅取决于任何经典无人机平台上存在的惯性和位置测量。提出的方法是在多电动无人机和人类之间的有效载荷切换任务上证明的。使用实时实验收集培训和测试数据。检测方法的准确性为96 \％，即使存在外部风干扰，也没有误报，并且在两种不同的无人机上进行部署和测试时。

太空探索目睹了毅力漫游者登陆火星表面，并展示了火星直升机超越地球以外的第一次飞行。在他们在火星上的任务中，毅力漫游者和Ingenuity合作探索了火星表面，Ingenuity侦察员地形信息为Rover的安全穿越。因此，确定两个平台之间的相对姿势对于此任务的成功至关重要。在这种必要性的驱动下，这项工作提出了基于基于神经形态视觉测量（NVBM）和惯性测量的融合的强大相对定位系统。神经形态视觉的出现引发了计算机视觉社区的范式转变，这是由于其独特的工作原理由现场发生的光强度变化触发的异步事件所划定。这意味着由于照明不变性而无法在静态场景中获取观察结果。为了规避这一限制，在场景中插入了高频活动地标，以确保一致的事件射击。这些地标被用作促进相对定位的显着特征。开发了一种新型的基于事件的地标识别算法，使用高斯混合模型（GMM），用于匹配我们NVBM的地标对应。 NVBM与提议的状态估计器中的惯性测量，地标跟踪Kalman滤波器（LTKF）和翻译解耦的Kalman Filter（TDKF）分别用于地标跟踪和相对定位。该系统在各种实验中进行了测试，并且在准确性和范围方面具有优于最先进的方法。

神经形态的愿景是一种生物启发技术，它已经引发了计算机视觉界的范式转变，并作为众多应用的关键推动器。该技术提供了显着的优势，包括降低功耗，降低处理需求和通信加速。然而，神经形态摄像机患有大量的测量噪声。这种噪声恶化了基于神经形态事件的感知和导航算法的性能。在本文中，我们提出了一种新的噪声过滤算法来消除不代表观察场景中的实际记录强度变化的事件。我们采用图形神经网络（GNN） - 驱动的变压器算法，称为GNN变换器，将原始流中的每个活动事件像素分类为实木强度变化或噪声。在GNN中，传递一个名为EventConv的消息传递框架，以反映事件之间的时空相关性，同时保留它们的异步性质。我们还介绍了在各种照明条件下生成事件流的近似地面真理标签（KogT1）方法。 Kogtl用于生成标记的数据集，从记录在充满挑战的照明条件下进行的实验。这些数据集用于培训和广泛测试我们所提出的算法。在取消检测的数据集上测试时，所提出的算法在过滤精度方面优于现有方法12％。还对公共数据集进行了额外的测试，以展示在存在照明变化和不同运动动态的情况下所提出的算法的泛化能力。与现有解决方案相比，定性结果验证了所提出的算法的卓越能力，以消除噪音，同时保留有意义的场景事件。

We present 3D Highlighter, a technique for localizing semantic regions on a mesh using text as input. A key feature of our system is the ability to interpret "out-of-domain" localizations. Our system demonstrates the ability to reason about where to place non-obviously related concepts on an input 3D shape, such as adding clothing to a bare 3D animal model. Our method contextualizes the text description using a neural field and colors the corresponding region of the shape using a probability-weighted blend. Our neural optimization is guided by a pre-trained CLIP encoder, which bypasses the need for any 3D datasets or 3D annotations. Thus, 3D Highlighter is highly flexible, general, and capable of producing localizations on a myriad of input shapes. Our code is publicly available at https://github.com/threedle/3DHighlighter.

We present a neural technique for learning to select a local sub-region around a point which can be used for mesh parameterization. The motivation for our framework is driven by interactive workflows used for decaling, texturing, or painting on surfaces. Our key idea is to incorporate segmentation probabilities as weights of a classical parameterization method, implemented as a novel differentiable parameterization layer within a neural network framework. We train a segmentation network to select 3D regions that are parameterized into 2D and penalized by the resulting distortion, giving rise to segmentations which are distortion-aware. Following training, a user can use our system to interactively select a point on the mesh and obtain a large, meaningful region around the selection which induces a low-distortion parameterization. Our code and project page are currently available.

There is no settled universal 3D representation for geometry with many alternatives such as point clouds, meshes, implicit functions, and voxels to name a few. In this work, we present a new, compelling alternative for representing shapes using a sequence of cross-sectional closed loops. The loops across all planes form an organizational hierarchy which we leverage for autoregressive shape synthesis and editing. Loops are a non-local description of the underlying shape, as simple loop manipulations (such as shifts) result in significant structural changes to the geometry. This is in contrast to manipulating local primitives such as points in a point cloud or a triangle in a triangle mesh. We further demonstrate that loops are intuitive and natural primitive for analyzing and editing shapes, both computationally and for users.

We propose RANA, a relightable and articulated neural avatar for the photorealistic synthesis of humans under arbitrary viewpoints, body poses, and lighting. We only require a short video clip of the person to create the avatar and assume no knowledge about the lighting environment. We present a novel framework to model humans while disentangling their geometry, texture, and also lighting environment from monocular RGB videos. To simplify this otherwise ill-posed task we first estimate the coarse geometry and texture of the person via SMPL+D model fitting and then learn an articulated neural representation for photorealistic image generation. RANA first generates the normal and albedo maps of the person in any given target body pose and then uses spherical harmonics lighting to generate the shaded image in the target lighting environment. We also propose to pretrain RANA using synthetic images and demonstrate that it leads to better disentanglement between geometry and texture while also improving robustness to novel body poses. Finally, we also present a new photorealistic synthetic dataset, Relighting Humans, to quantitatively evaluate the performance of the proposed approach.

Continuous behavioural authentication methods add a unique layer of security by allowing individuals to verify their unique identity when accessing a device. Maintaining session authenticity is now feasible by monitoring users' behaviour while interacting with a mobile or Internet of Things (IoT) device, making credential theft and session hijacking ineffective. Such a technique is made possible by integrating the power of artificial intelligence and Machine Learning (ML). Most of the literature focuses on training machine learning for the user by transmitting their data to an external server, subject to private user data exposure to threats. In this paper, we propose a novel Federated Learning (FL) approach that protects the anonymity of user data and maintains the security of his data. We present a warmup approach that provides a significant accuracy increase. In addition, we leverage the transfer learning technique based on feature extraction to boost the models' performance. Our extensive experiments based on four datasets: MNIST, FEMNIST, CIFAR-10 and UMDAA-02-FD, show a significant increase in user authentication accuracy while maintaining user privacy and data security.

We propose a novel deep neural network architecture to learn interpretable representation for medical image analysis. Our architecture generates a global attention for region of interest, and then learns bag of words style deep feature embeddings with local attention. The global, and local feature maps are combined using a contemporary transformer architecture for highly accurate Gallbladder Cancer (GBC) detection from Ultrasound (USG) images. Our experiments indicate that the detection accuracy of our model beats even human radiologists, and advocates its use as the second reader for GBC diagnosis. Bag of words embeddings allow our model to be probed for generating interpretable explanations for GBC detection consistent with the ones reported in medical literature. We show that the proposed model not only helps understand decisions of neural network models but also aids in discovery of new visual features relevant to the diagnosis of GBC. Source-code and model will be available at https://github.com/sbasu276/RadFormer

In this paper, we increase the availability and integration of devices in the learning process to enhance the convergence of federated learning (FL) models. To address the issue of having all the data in one location, federated learning, which maintains the ability to learn over decentralized data sets, combines privacy and technology. Until the model converges, the server combines the updated weights obtained from each dataset over a number of rounds. The majority of the literature suggested client selection techniques to accelerate convergence and boost accuracy. However, none of the existing proposals have focused on the flexibility to deploy and select clients as needed, wherever and whenever that may be. Due to the extremely dynamic surroundings, some devices are actually not available to serve as clients in FL, which affects the availability of data for learning and the applicability of the existing solution for client selection. In this paper, we address the aforementioned limitations by introducing an On-Demand-FL, a client deployment approach for FL, offering more volume and heterogeneity of data in the learning process. We make use of the containerization technology such as Docker to build efficient environments using IoT and mobile devices serving as volunteers. Furthermore, Kubernetes is used for orchestration. The Genetic algorithm (GA) is used to solve the multi-objective optimization problem due to its evolutionary strategy. The performed experiments using the Mobile Data Challenge (MDC) dataset and the Localfed framework illustrate the relevance of the proposed approach and the efficiency of the on-the-fly deployment of clients whenever and wherever needed with less discarded rounds and more available data.