We present the design of a productionized end-to-end stereo depth sensing system that does pre-processing, online stereo rectification, and stereo depth estimation with a fallback to monocular depth estimation when rectification is unreliable. The output of our depth sensing system is then used in a novel view generation pipeline to create 3D computational photography effects using point-of-view images captured by smart glasses. All these steps are executed on-device on the stringent compute budget of a mobile phone, and because we expect the users can use a wide range of smartphones, our design needs to be general and cannot be dependent on a particular hardware or ML accelerator such as a smartphone GPU. Although each of these steps is well studied, a description of a practical system is still lacking. For such a system, all these steps need to work in tandem with one another and fallback gracefully on failures within the system or less than ideal input data. We show how we handle unforeseen changes to calibration, e.g., due to heat, robustly support depth estimation in the wild, and still abide by the memory and latency constraints required for a smooth user experience. We show that our trained models are fast, and run in less than 1s on a six-year-old Samsung Galaxy S8 phone's CPU. Our models generalize well to unseen data and achieve good results on Middlebury and in-the-wild images captured from the smart glasses.
相關內容
We propose Gated Stereo, a high-resolution and long-range depth estimation technique that operates on active gated stereo images. Using active and high dynamic range passive captures, Gated Stereo exploits multi-view cues alongside time-of-flight intensity cues from active gating. To this end, we propose a depth estimation method with a monocular and stereo depth prediction branch which are combined in a final fusion stage. Each block is supervised through a combination of supervised and gated self-supervision losses. To facilitate training and validation, we acquire a long-range synchronized gated stereo dataset for automotive scenarios. We find that the method achieves an improvement of more than 50 % MAE compared to the next best RGB stereo method, and 74 % MAE to existing monocular gated methods for distances up to 160 m. Our code,models and datasets are available here.
Different with conventional reconfigurable intelligent surface (RIS), simultaneous transmitting and reflecting RIS (STAR-RIS) can reflect and transmit the signals to the receiver. In this paper, to serve more ground users and increase the deployment flexibility, we investigate an unmanned aerial vehicle equipped with a STAR-RIS (STAR-RIS-UAV) aided wireless communications for multi-user networks. Energy splitting (ES) and mode switching (MS) protocols are considered to control the reflection and transmission coefficients of STAR-RIS elements. To maximize the sum rate of the STAR-RIS-UAV aided coordinated multipoint cellular system for multi-user networks, the corresponding beamforming vectors as well as transmitted and reflected coefficients matrices are optimized. Specifically, instead of adopting the alternating optimization, we design an iteration method to optimize all variables for both ES and MS protocols at the same time. Simulation results reveal that STAR-RIS-UAV aided wireless communication system has a much higher sum rate than the system with conventional RIS or without RIS. Furthermore, the proposed structure is more flexible than a fixed STAR-RIS and could greatly promote the sum rate.
Medical dialogue systems aim to provide accurate answers to patients, necessitating specific domain knowledge. Recent advancements in Large Language Models (LLMs) have demonstrated their exceptional capabilities in the medical Q&A domain, indicating a rich understanding of common sense. However, LLMs are insufficient for direct diagnosis due to the absence of diagnostic strategies. The conventional approach to address this challenge involves expensive fine-tuning of LLMs. Alternatively, a more appealing solution is the development of a plugin that empowers LLMs to perform medical conversation tasks. Drawing inspiration from in-context learning, we propose PlugMed, a Plug-and-Play Medical Dialogue System that facilitates appropriate dialogue actions by LLMs through two modules: the prompt generation (PG) module and the response ranking (RR) module. The PG module is designed to capture dialogue information from both global and local perspectives. It selects suitable prompts by assessing their similarity to the entire dialogue history and recent utterances grouped by patient symptoms, respectively. Additionally, the RR module incorporates fine-tuned SLMs as response filters and selects appropriate responses generated by LLMs. Moreover, we devise a novel evaluation method based on intent and medical entities matching to assess the efficacy of dialogue strategies in medical conversations more effectively. Experimental evaluations conducted on three unlabeled medical dialogue datasets, including both automatic and manual assessments, demonstrate that our model surpasses the strong fine-tuning baselines.
In the last decade, the computer vision field has seen significant progress in multimodal data fusion and learning, where multiple sensors, including depth, infrared, and visual, are used to capture the environment across diverse spectral ranges. Despite these advancements, there has been no systematic and comprehensive evaluation of fusing RGB-D and thermal modalities to date. While autonomous driving using LiDAR, radar, RGB, and other sensors has garnered substantial research interest, along with the fusion of RGB and depth modalities, the integration of thermal cameras and, specifically, the fusion of RGB-D and thermal data, has received comparatively less attention. This might be partly due to the limited number of publicly available datasets for such applications. This paper provides a comprehensive review of both, state-of-the-art and traditional methods used in fusing RGB-D and thermal camera data for various applications, such as site inspection, human tracking, fault detection, and others. The reviewed literature has been categorised into technical areas, such as 3D reconstruction, segmentation, object detection, available datasets, and other related topics. Following a brief introduction and an overview of the methodology, the study delves into calibration and registration techniques, then examines thermal visualisation and 3D reconstruction, before discussing the application of classic feature-based techniques as well as modern deep learning approaches. The paper concludes with a discourse on current limitations and potential future research directions. It is hoped that this survey will serve as a valuable reference for researchers looking to familiarise themselves with the latest advancements and contribute to the RGB-DT research field.
The adoption of modern technologies for use in healthcare has become an inevitable change. The emergence of artificial intelligence drives this digital disruption. Artificial intelligence has augmented machine capabilities to act like and interact with human beings. As the healthcare industry adopts technology in most areas, an area in healthcare that is touched by this change is clinical practice. New technologies are being designed to improve healthcare services. One aspect of these technologies is voice user interfaces. This paper reviews applications of voice user interfaces in clinical settings. Several information sources were consulted, and based on eligibility criteria, a search was conducted, and ten papers selected. This study presents findings from the last ten years (2009-2019). The results are categorized based on findings, also they contribute to the discussion and the research gaps identified for future study as regards context-aware voice user interfaces and the appearance of conversational agents from a given set of options.
Learning on graphs is becoming prevalent in a wide range of applications including social networks, robotics, communication, medicine, etc. These datasets belonging to entities often contain critical private information. The utilization of data for graph learning applications is hampered by the growing privacy concerns from users on data sharing. Existing privacy-preserving methods pre-process the data to extract user-side features, and only these features are used for subsequent learning. Unfortunately, these methods are vulnerable to adversarial attacks to infer private attributes. We present a novel privacy-respecting framework for distributed graph learning and graph-based machine learning. In order to perform graph learning and other downstream tasks on the server side, this framework aims to learn features as well as distances without requiring actual features while preserving the original structural properties of the raw data. The proposed framework is quite generic and highly adaptable. We demonstrate the utility of the Euclidean space, but it can be applied with any existing method of distance approximation and graph learning for the relevant spaces. Through extensive experimentation on both synthetic and real datasets, we demonstrate the efficacy of the framework in terms of comparing the results obtained without data sharing to those obtained with data sharing as a benchmark. This is, to our knowledge, the first privacy-preserving distributed graph learning framework.
We propose a two-step Newton's method for refining an approximation of a singular zero whose deflation process terminates after one step, also known as a deflation-one singularity. Given an isolated singular zero of a square analytic system, our algorithm exploits an invertible linear operator obtained by combining the Jacobian and a projection of the Hessian in the direction of the kernel of the Jacobian. We prove the quadratic convergence of the two-step Newton method when it is applied to an approximation of a deflation-one singular zero. Also, the algorithm requires a smaller size of matrices than the existing methods, making it more efficient. We demonstrate examples and experiments to show the efficiency of the method.
In practically every industry today, artificial intelligence is one of the most effective ways for machines to assist humans. Since its inception, a large number of researchers throughout the globe have been pioneering the application of artificial intelligence in medicine. Although artificial intelligence may seem to be a 21st-century concept, Alan Turing pioneered the first foundation concept in the 1940s. Artificial intelligence in medicine has a huge variety of applications that researchers are continually exploring. The tremendous increase in computer and human resources has hastened progress in the 21st century, and it will continue to do so for many years to come. This review of the literature will highlight the emerging field of artificial intelligence in medicine and its current level of development.
Autonomous driving has achieved a significant milestone in research and development over the last decade. There is increasing interest in the field as the deployment of self-operating vehicles on roads promises safer and more ecologically friendly transportation systems. With the rise of computationally powerful artificial intelligence (AI) techniques, autonomous vehicles can sense their environment with high precision, make safe real-time decisions, and operate more reliably without human interventions. However, intelligent decision-making in autonomous cars is not generally understandable by humans in the current state of the art, and such deficiency hinders this technology from being socially acceptable. Hence, aside from making safe real-time decisions, the AI systems of autonomous vehicles also need to explain how these decisions are constructed in order to be regulatory compliant across many jurisdictions. Our study sheds a comprehensive light on developing explainable artificial intelligence (XAI) approaches for autonomous vehicles. In particular, we make the following contributions. First, we provide a thorough overview of the present gaps with respect to explanations in the state-of-the-art autonomous vehicle industry. We then show the taxonomy of explanations and explanation receivers in this field. Thirdly, we propose a framework for an architecture of end-to-end autonomous driving systems and justify the role of XAI in both debugging and regulating such systems. Finally, as future research directions, we provide a field guide on XAI approaches for autonomous driving that can improve operational safety and transparency towards achieving public approval by regulators, manufacturers, and all engaged stakeholders.
Humans perceive the world by concurrently processing and fusing high-dimensional inputs from multiple modalities such as vision and audio. Machine perception models, in stark contrast, are typically modality-specific and optimised for unimodal benchmarks, and hence late-stage fusion of final representations or predictions from each modality (`late-fusion') is still a dominant paradigm for multimodal video classification. Instead, we introduce a novel transformer based architecture that uses `fusion bottlenecks' for modality fusion at multiple layers. Compared to traditional pairwise self-attention, our model forces information between different modalities to pass through a small number of bottleneck latents, requiring the model to collate and condense the most relevant information in each modality and only share what is necessary. We find that such a strategy improves fusion performance, at the same time reducing computational cost. We conduct thorough ablation studies, and achieve state-of-the-art results on multiple audio-visual classification benchmarks including Audioset, Epic-Kitchens and VGGSound. All code and models will be released.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191