Abstract

Although current deep models for face tasks surpass human performance on some benchmarks, we do not understand how they work. Thus, we cannot predict how it will react to novel inputs, resulting in catastrophic failures and unwanted biases in the algorithms. Explainable AI helps bridge the gap, but currently, there are very few visualization algorithms designed for faces. This work undertakes a first-of-its-kind meta-analysis of explainability algorithms in the face domain. We explore the nuances and caveats of adapting general-purpose visualization algorithms to the face domain, illustrated by computing visualizations on popular face models. We review existing face explainability works and reveal valuable insights into the structure and hierarchy of face networks. We also determine the design considerations for practical face visualizations accessible to AI practitioners by conducting a user study on the utility of various explainability algorithms.

Abstract

Embodiments herein provide a system and a method for automatically generating at least one synthetic talking head video using a machine learning model. The method includes (i) extracting features from each frame of a video that is extracted from data sources,(ii) analyzing, using a face-detection model, the video to determine a driving face video if a number of identities, and faces of speakers are equal to one in all frames of the video,(iii) generating, using a text to speech model, synthetic speech utterances by automatically selecting a vocabulary of words and sentences from the data sources,(iv) modifying lip movements that are originally present in the driving face video corresponding to the synthetic speech utterances, and (v) generating, using machine learning model, synthetic talking head video based on the lip movements that are modified corresponding to the synthetic speech utterances.

Abstract

Universal Semantic Representation (USR) captures how the speaker intends to view a situation. The representation is aimed at being language-independent. The theoretical model, Universal Semantic Grammar (USG), that has been adopted for the task is based on Indian Grammatical Tradition (IGT henceforth) and Pāṇini's grammatical model. USR is not limited to just presenting “who is doing what to whom and when and where” in a sentence. It is about capturing a speaker’s vivakṣā, how the speaker views a situation. The way the speaker views a situation or an event, accordingly he/she selects kāraka roles for the participants of an event, tense-aspect-modility features on the verb, sentence structure by foregrounding and backgrounding information, also various discourse elements such as particles, connectives, co-referencing and so on. USR is a text-based data structure that is close to the Attribute Value matrix (AVM) representation. It is easier to read and write manually, as well as process computationally. This document describes the theoretical foundation of USR and the strategies that have been adopted for USR annotation

Abstract

In this paper we show an effective means of integrating data driven frameworks to sampling based optimal control to vastly reduce the compute time for easy adoption and adaptation to real time applications such as on-road autonomous driving in the presence of dynamic actors. Presented with training examples, a spatio-temporal CNN learns to predict the optimal mean control over a finite horizon that precludes further resampling, an iterative process that makes sampling based optimal control formulations difficult to adopt in real time settings. Generating control samples around the network-predicted optimal mean retains the advantage of sample diversity while enabling real time rollout of trajectories that avoids multiple dynamic obstacles in an on-road navigation setting. Further the 3D CNN architecture implicitly learns the future trajectories of the dynamic agents in the scene resulting in successful collision free …

Abstract

This work proposes a resource efficient robust control scheme for missile-target engagement scenarios subjected to external disturbances. The robustness is achieved by using an annular event-triggered artificial time-delayed control (ET-TDC) methodology with input saturation. The ET-TDC philosophy uses the TDC strategy through a dynamic predefined triggering mechanism which overcomes the requirement to update the control periodically for every sampling instant, unlike conventional TDC and other robust control schemes. Thus, the proposed methodology, can tackle uncertainties with minimal a priori knowledge while significantly reducing the over-utilization of system resources. In addition, the adopted event triggered mechanism facilitates further conservation of energy which might be crucial for mid-to-long range engagement scenarios. The closed-loop stability is derived analytically and the simulation

Abstract

Climate classification simplifies the representation of expected climate conditions by eliminating the need to describe each climatic parameter. Climate classification is frequently used as a basis for recommendations through codes and standards for buildings because a given climate has nearly similar design conditions. Furthermore, building energy efficiency programmes are designed based on the climatic classification to determine appropriate design strategies to eliminate the under-design or over-design of buildings for similar climatic regions. This necessitates the use of realistic and reliable climate classifications. Over the past two decades, numerous research studies have proposed climate classification methods. However, there is a lack of universal acceptance of climate classification methodology to balance complexity and accuracy. This research provides an overview of various climate classification …

Abstract

This study investigates the impact of loss-framing and individual risk attitude on willingness- to purchase insurance products utilizing a game-like interface as choice architecture. The application presents events as experienced in real life. Both financial and emotional loss-framing events are followed by choices to purchase insurance. The participant cohorts considered were undergraduate students and older participants; the latter group was further subdivided by income and education. The within-subject analysis reveals that the loss framing effect on insurance consumption is higher in the younger population, though contingent on the insurance product type. Health and accident insurance shows a negative correlation with risk attitudes for younger participants and a positive correlation with accident insurance for older participants. Risk attitude and life insurance products showed no dependency. The findings elucidate the role of age, income, family responsibilities, and risk attitude in purchasing insurance products. Importantly, it confirms the heuristics of framing/nudging.

Abstract

Music listening is a dynamic process that entails complex interactions between sensory, cognitive, and emotional processes. The naturalistic paradigm provides a means to investigate these processes in an ecologically valid manner by allowing experimental settings that mimic real-life musical experiences. In this paper, we highlight the importance of the naturalistic paradigm in studying dynamic music processing and discuss how it allows for investigating both the segregation and integration of brain processes using model-based and model-free methods. We further suggest that studying individual difference-modulated music processing in this paradigm can provide insights into the mechanisms of brain plasticity, which can have implications for the development of interventions and therapies in a personalized way. Finally, despite the challenges that the naturalistic paradigm poses, we end with a discussion on future prospects of music and neuroscience research, especially with the continued development and refinement of naturalistic paradigms and the adoption of open science practices.

Abstract

Safe autonomous driving critically depends on how well the ego-vehicle can predict the trajectories of neighboring vehicles. To this end, several trajectory prediction algorithms have been presented in the existing literature. Many of these approaches output a multi-modal distribution of obstacle trajectories instead of a single deterministic prediction to account for the underlying uncertainty. However, existing planners cannot handle the multi-modality based on just sample-level information of the predictions. With this motivation, this paper proposes a trajectory optimizer that can leverage the distributional aspects of the prediction in a computationally tractable and sample-efficient manner. Our optimizer can work with arbitrarily complex distributions and thus can be used with output distribution represented as a deep neural network. The core of our approach is built on embedding distribution in Reproducing Kernel Hilbert Space (RKHS), which we leverage in two ways. First, we propose an RKHS embedding approach to select probable samples from the obstacle trajectory distribution. Second, we rephrase chance-constrained optimization as distribution matching in RKHS and propose a novel sampling-based optimizer for its solution. We validate our approach with hand-crafted and neural network-based predictors trained on real-world datasets and show improvement over the existing stochastic optimization approaches in safety metrics.

Abstract

In this article, a novel adaptive controller is designed for Euler-Lagrangian systems under predefined time-varying state constraints. The proposed controller could achieve this objective without a priori knowledge of system parameters and, crucially, of state-dependent uncertainties. The closed-loop stability is verified using the Lyapunov method, while the overall efficacy of the proposed scheme is verified using a simulated robotic arm compared to the state of the art.