We propose a simple yet powerful Landmark guided Generative Adversarial Network (LandmarkGAN) for the facial expression-to-expression translation using a single image, which is an important and challenging task in computer vision since the expression-to-expression translation is a non-linear and non-aligned problem. Moreover, it requires a high-level semantic understanding between the input and output images since the objects in images can have arbitrary poses, sizes, locations, backgrounds, and self-occlusions. To tackle this problem, we propose utilizing facial landmark information explicitly. Since it is a challenging problem, we split it into two sub-tasks, (i) category-guided landmark generation, and (ii) landmark-guided expression-to-expression translation. Two sub-tasks are trained in an end-to-end fashion that aims to enjoy the mutually improved benefits from the generated landmarks and expressions. Compared with current keypoint-guided approaches, the proposed LandmarkGAN only needs a single facial image to generate various expressions. Extensive experimental results on four public datasets demonstrate that the proposed LandmarkGAN achieves better results compared with state-of-the-art approaches only using a single image. The code is available at https://github.com/Ha0Tang/LandmarkGAN.

The United Nations Sustainable Development Goals (SDGs) have become an important guideline for both governmental and non-governmental organizations to monitor and plan their contributions to social, economic, and environmental transformations. The 17 SDGs cover large areas of application, from ending poverty and improving health, to fostering economic growth and preserving natural resources. As the latest UN report (UN, 2022) attests, the availability of high-quality data is still lacking in many of these areas and progress is needed in identifying data sources that can help monitor work on these goals. Monitoring of SDGs has typically been based on economic and health data (e.g.,

We are seeking an Engineering Manager to join Meta Reality Labs, an organization focused on productizing novel technologies in AR and VR devices. In this role, your job will be to both manage and partner with groups working across the full spectrum from research to product development, managing our technical investment portfolio supporting multiple products across different timelines. You will oversee and be responsible for a broad array of state-of-the-art technology areas, spanning Eye Tracking, Computer Vision and Machine Learning, and designed to run on low-power client devices. Prospective candidates should have sufficient technical depth and breadth in the associated set of technologies to make portfolio management, resourcing and roadmap decisions. Minimum Qualifications: • BS degree in Engineering, Physics, Computer Science or equivalent • 2 years of people management experience in multi-disciplinary global teams at the intersection of tech and product, including building performing teams and organization • 2 years of experience supporting an engineering and/or research organization through technical leadership • Demonstrated experience in recruiting and managing technical teams, including performance management • Experience in managing teams productizing Computer Vision or AI/Machine Learning technologies from conception to end • Leadership and interpersonal communication experience in working across many disciplines, driving best engineering practices, and mentoring team members • Technical experience in leading teams/projects in one or more of the technical domains of machine perception (e.g., machine vision, deep learning, sensors and robotics) • Flexibility and resilience in a dynamic environment Preferred Qualifications: • PhD in Computer Vision, Computer Graphics, AI/Machine Learning or related field • Experience managing joint hardware-software development and associated rapid prototyping projects • Experience in leading teams developing technologies such as eye tracking, face tracking or body tracking • Experience in leading teams interfacing with HW teams (e.g., sensors, silicon) in setting requirements and product tradeoffs Facebook is proud to be an Equal Opportunity and Affirmative Action employer.

Question answering systems are recognized as popular and frequently effective means of information seeking on the web. In such systems, information seekers can receive a concise response to their query by presenting their questions in natural language. Interactive question answering is a recently proposed and increasingly popular solution that resides at the intersection of question answering and dialogue systems. On the one hand, the user can ask questions in normal language and locate the actual response to her inquiry; on the other hand, the system can prolong the question-answering session into a dialogue if there are multiple probable replies, very few, or ambiguities in the initial request. By permitting the user to ask more questions, interactive question answering enables users to dynamically interact with the system and receive more precise results. This survey offers a detailed overview of the interactive question-answering methods that are prevalent in current literature. It begins by explaining the foundational principles of question-answering systems, hence defining new notations and taxonomies to combine all identified works inside a unified framework. The reviewed published work on interactive question-answering systems is then presented and examined in terms of its proposed methodology, evaluation approaches, and dataset/application domain. We also describe trends surrounding specific tasks and issues raised by the community, so shedding light on the future interests of scholars. Our work is further supported by a GitHub page with a synthesis of all the major topics covered in this literature study. https://sisinflab.github.io/interactive-question-answering-systems-survey/

HumanaPharmacy is a leader committed to the health and wellbeing of members through mail-order delivery of maintenance and specialty medicines as well as diabetic supplies. The Senior Cloud Architect leads the planning, design, and engineering of enterprise-level infrastructure and platforms related to cloud computing. The Senior Cloud Architect work assignments involve moderately complex to complex issues where the analysis of situations or data requires an in-depth evaluation of variable factors. The Senior Cloud Architect performs technical planning, architecture development and modification of specifications for cloud computing environments. Develops specifications for new IT cloud computing products and service offerings. Assesses the compatibility and integration of products/services proposed as standards in order to ensure an integrated architecture across interdependent technologies. Begins to influence department's strategy. Makes decisions on moderately complex to complex issues regarding technical approach for project components, and work is performed without direction. Responsibilities • Advocate and define architecture vision from a strategic perspective, including internal and external platforms, tools, and systems. Required Qualifications • Bachelor's degree • 5 or more years of technical experience • Must be passionate about contributing to an organization focused on continuously improving consumer experiences Preferred Qualifications • Experience in SFCC Additional Information Humana and its subsidiaries require vaccinated associates who work outside of their home to submit proof of vaccination, including COVID-19 boosters. Associates who remain unvaccinated must either undergo weekly negative COVID testing OR wear a mask at all times while in a Humana facility or while working in the field.

Software has been the star of high tech over the past few decades, and it's easy to understand why. With PCs and mobile phones, the game-changing innovations that defined this era, the architecture and software layers of the technology stack enabled several important advances. In this environment, semiconductor companies were in a difficult position. Although their innovations in chip design and fabrication enabled next-generation devices, they received only a small share of the value coming from the technology stack--about 20 to 30 percent with PCs and 10 to 20 percent with mobile. But the story for semiconductor companies could be different with the growth of artificial intelligence (AI)--typically defined as the ability of a machine to perform cognitive functions associated with human minds, such as perceiving, reasoning, and learning. Many AI applications have already gained a wide following, including virtual assistants that manage our homes and facial-recognition programs that track criminals. What will this development mean for semiconductor sales and revenues?

In this paper, we present a density estimation framework based on tree tensor-network states. The proposed method consists of determining the tree topology with Chow-Liu algorithm, and obtaining a linear system of equations that defines the tensor-network components via sketching techniques. Novel choices of sketch functions are developed in order to consider graphical models that contain loops. Sample complexity guarantees are provided and further corroborated by numerical experiments.

The task of link prediction aims to solve the problem of incomplete knowledge caused by the difficulty of collecting facts from the real world. GCNs-based models are widely applied to solve link prediction problems due to their sophistication, but GCNs-based models are suffering from two problems in the structure and training process. 1) The transformation methods of GCN layers become increasingly complex in GCN-based knowledge representation models; 2) Due to the incompleteness of the knowledge graph collection process, there are many uncollected true facts in the labeled negative samples. Therefore, this paper investigates the characteristic of the information aggregation coefficient (self-attention) of adjacent nodes and redesigns the self-attention mechanism of the GAT structure. Meanwhile, inspired by human thinking habits, we designed a semi-supervised self-training method over pre-trained models. Experimental results on the benchmark datasets FB15k-237 and WN18RR show that our proposed self-attention mechanism and semi-supervised self-training method can effectively improve the performance of the link prediction task. If you look at FB15k-237, for example, the proposed method improves Hits@1 by about 30%.

Generating unsafe sub-requirements from a partitioned input space to support verification-guided test cases for formal verification of black-box models is a challenging problem for researchers. The size of the search space makes exhaustive search computationally impractical. This paper investigates a meta-heuristic approach to search for unsafe candidate sub-requirements in partitioned input space. We present a Negative Selection Algorithm (NSA) for identifying the candidates' unsafe regions within given safety properties. The Meta-heuristic capability of the NSA algorithm made it possible to estimate vast unsafe regions while validating a subset of these regions. We utilize a parallel execution of partitioned input space to produce safe areas. The NSA based on the prior knowledge of the safe regions is used to identify candidate unsafe region areas and the Marabou framework is then used to validate the NSA results. Our preliminary experimentation and evaluation show that the procedure finds candidate unsafe sub-requirements when validated with the Marabou framework with high precision.

Deep generative models have the potential to fundamentally change the way we create high-fidelity digital content but are often hard to control. Prompting a generative model is a promising recent development that in principle enables end-users to creatively leverage zero-shot and few-shot learning to assign new tasks to an AI ad-hoc, simply by writing them down. However, for the majority of end-users writing effective prompts is currently largely a trial and error process. To address this, we discuss the key opportunities and challenges for interactive creative applications that use prompting as a new paradigm for Human-AI interaction. Based on our analysis, we propose four design goals for user interfaces that support prompting. We illustrate these with concrete UI design sketches, focusing on the use case of creative writing. The research community in HCI and AI can take these as starting points to develop adequate user interfaces for models capable of zero- and few-shot learning.