Abstract

Doubles play an indispensable role in the movie industry. They take the place of the actors in dangerous stunt scenes or scenes where the same actor plays multiple characters. The double’s face is later replaced with the actor’s face and expressions manually using expensive CGI technology, costing millions of dollars and taking months to complete. An automated, inexpensive, and fast way can be to use face-swapping techniques that aim to swap an identity from a source face video (or an image) to a target face video. However, such methods cannot preserve the source expressions of the actor important for the scene’s context. *Equal contribution To tackle this challenge, we introduce video-to-video (V2V) face-swapping, a novel task of face-swapping that can preserve (1) the identity and expressions of the source (actor) face video and (2) the background and pose of the target (double) video. We propose FaceOff, a V2V face-swapping system that operates by learning a robust blending operation to merge two face videos following the constraints above. It reduces the videos to a quantized latent space and then blends them in the reduced space. FaceOff is trained in a self-supervised manner and robustly tackles the nontrivial challenges of V2V face-swapping. As shown in the experimental section, FaceOff significantly outperforms alternate approaches qualitatively and quantitatively.

Abstract

Respiratory diseases contribute to a majority of deaths worldwide every year. Diseases such as asthma, bronchitis and pneumonia also adversely impact a person’s social and economic conditions. They can seriously threaten their health if left undiagnosed and untreated. Techniques such as auscultation are used in the diagnosis of most respiratory diseases. However, using such techniques requires an experienced physician and the diagnosis is subjective. To overcome these challenges, in this work, a portable handheld system has been proposed and a proof of concept implemented to detect and classify respiratory diseases automatically through the use of convolutional neural networks (CNN) running on mobile platforms. Mel spectrograms are generated from the audio signals and fed to the CNN for classification. This work makes use of the publicly available HF Lung dataset. The classification accuracy achieved by the current implementation using a Raspberry Pi for processing is 80.55% with a sensitivity of 95.65% and specificity of 98.80% on the HF Lung dataset.

Abstract

The increase of IoT devices and the emergence of smart cities have revolutionized urban development, offering numerous benefits while addressing environmental concerns. This has caused an increase in the usage of IoT frameworks, and the need for efficient architecture and standardized ontology is imminent. In this regard, we propose a distributed, multi-layered data platform architecture comprising the Data Monitoring Layer (DML), Data Storage Layer (DSL), Data Enhancement Layer (DEnL), and Data Exchange Layer (DEL). Our architecture achieves interoperability, facilitates data transfer between nodes, enables telemetry data retrieval, and ensures cross-platform and cross-device compatibility. It addresses the challenges of handling increased sensor data and user demands by providing high throughput and scalability support. We investigated Smart City Living Lab at IIIT Hyderabad an existing large-scale system deployed within a 66-acre campus. This system consists of 291 nodes. By studying this deployed system, we were able to gather valuable real-world data, allowing us to analyze the challenges and potential solutions related to data architecture. Our results show improvements of up to 41.23\% in throughput and a decrease in latency by 29.19\% for data insertion from the sensor nodes. The retrieval by the data client gives an increase of over 800\% in both throughput and number of requests through DENL. These metrics are compared to a centralised data platform architecture. We conclude by discussing the implications of our findings and suggesting future work.

Abstract

Due to their complex nonlinear dynamics and batch-to-batch variability, batch processes pose a challenge for process control. Due to the absence of accurate models and resulting plant-model mismatch, these problems become harder to address for advanced model-based control strategies. Reinforcement Learning (RL), wherein an agent learns the policy by directly interacting with the environment, offers a potential alternative in this context. RL frameworks with actor-critic architecture have recently become popular for controlling systems where state and action spaces are continuous. It has been shown that an ensemble of actor and critic networks further helps the agent learn better policies due to the enhanced exploration due to simultaneous policy learning. To this end, the current study proposes a stochastic actor-critic RL algorithm, termed Twin Actor Soft Actor-Critic (TASAC), by incorporating an ensemble of actors for learning, in a maximum entropy framework, for batch process control.

Abstract

This paper proposes deep architectures for learning instance-specific abstain (reject) option multiclass classifiers. The proposed approach uses novel bounded multiclass abstention loss for multiclass classification as a performance measure. This approach uses rejection cost as the rejection parameter in con- trast to coverage-based approaches. To show the effectiveness of the proposed approach, we experiment with several real-world datasets and compare them with state-of-the-art coverage-based and cost-of-rejection-based techniques. The ex- perimental results show that the proposed method improves performance over the state-of-the-art approaches.

Abstract

A smart thermal patch for adaptive thermotherapy is provided. In an embodiment, the patch can be a stretchable, non-polymeric, conductive thin film flexible and non-invasive body integrated mobile thermal heater with wireless control capabilities that can be used to provide adaptive thermotherapy. The patch can be geometrically and spatially tunable on various pain locations. Adaptability allows the amount of heating to be tuned based on the temperature of the treated portion.

Abstract

We consider a generalization of the recently proposed gradient coding framework where a large dataset is divided across n workers and each worker transmits to a master node one or more linear combinations of the gradients over the data subsets assigned to it. Unlike the conventional framework which requires the master node to recover the sum of the gradients over all the data subsets in the presence of s straggler workers, we relax the goal of the master node to computing the sum of at least some α fraction of the gradients. The broad goal of our work is to study the optimal computation and communication load per worker for this approximate gradient coding framework. We begin by deriving a lower bound on the computation load of any feasible scheme and also propose a strategy which achieves this lower bound, albeit at the cost of high communication load and a number of data partitions which can be polynomial in the number of workers n. We then restrict attention to schemes which utilize a number of data partitions equal to n and propose schemes based on cyclic assignment which have a lower communication load. When each worker transmits a single linear combination, we also prove lower bounds on the computation load of any scheme using n data partitions.

Abstract

Maximally recoverable codes are a class of codes which recover from all potentially recoverable erasure patterns given the locality constraints of the code. In earlier works, these codes have been studied in the context of codes with locality. The notion of locality has been extended to hierarchical locality, which allows for locality to gradually increase in levels with the increase in the number of erasures. We consider the locality constraints imposed by codes with two-level hierarchical locality and define maximally recoverable codes with data-local and local hierarchical locality. We derive certain properties related to their punctured codes and minimum distance. We give a procedure to construct hierarchical data-local MRCs from hierarchical local MRCs. We provide a construction of hierarchical local MRCs for all parameters. We also give constructions of MRC with hierarchical locality for some parameters, whose field size is smaller than that of known constructions for general parameters. We also derive a field size lower bound on MRC with hierarchical locality.

Abstract

We introduce Action-GPT, a plug and play framework for incorporating Large Language Models (LLMs) into textbased action generation models. Action phrases in current motion capture datasets contain minimal and to-the-point information. By carefully crafting prompts for LLMs, we generate richer and fine-grained descriptions of the action. We show that utilizing these detailed descriptions instead of the original action phrases leads to better alignment of text and motion spaces. Our experiments show qualitative and quantitative improvement in the quality of synthesized motions produced by recent text-to-motion models. Code, pretrained models and sample videos will be made avail

Abstract

Stuttering is a prevalent speech disorder that affects millions of people worldwide. In this Show and Tell presentation, we demonstrate a novel platform that takes speech samples in English and Kannada to detect and analyze stuttering in patients. The user-friendly interface includes demographic details and speech samples, generating comprehensive reports for different stuttering disfluencies. The platform has four different user types, providing full read-only access for admins and full write access for super admins. Our platform provides valuable assistance for speechlanguage pathologists to evaluate speech samples. The proposed platform supports both live and recorded speech samples and presents a flexible approach to stuttering detection and analysis. Our research demonstrates the potential of technology to improve speech-language pathology for stuttering. Used F-score as a metric for evaluating the models for the stutter detection task.