Abstract

Multi-view Detection (MVD) is highly effective for occlusion reasoning in a crowded environment. While recent works using deep learning have made significant advances in the field, they have overlooked the generalization aspect, which makes them impractical for real-world deployment. The key novelty of our work is to formalize three critical forms of generalization and propose experiments to evaluate them: generalization with i) a varying number of cameras, ii) varying camera positions, and finally, iii) to new scenes. We find that existing state-of-the-art models show poor generalization by overfitting to a single scene and camera configuration. To address the concerns: (a) we propose a novel Generalized MVD (GMVD) dataset, assimilating diverse scenes with changing day- time, camera configurations, varying number of cameras, and (b) we discuss the properties essential to bring generalization to MVD and propose a barebones model to incorporate them. We perform a comprehensive set of experiments on the WildTrack, MultiViewX and the GMVD datasets to motivate the necessity to evaluate generalization abilities of MVD methods and to demonstrate the efficacy of the proposed approach. The code and the proposed dataset can be found at https://github.com/jeetv/GMVD

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

Artificial-delay control is a method in which state and input measurements collected at an immediate past time instant (i.e., artificially delayed) are used to compensate the uncertain dynamics affecting the system at the current time. This article formulates an artificial-delay control method with adaptive gains in the presence of nonlinear (Euler–Lagrange) underactuation. The appeal of studying Euler–Lagrange dynamics is to capture many robotics applications of practical interest, as demonstrated via stability and robustness analysis and via robotic ship and robotic aerial vehicle test cases.

Abstract

The structure of invariant regions and globally attracting regions is fundamental to understanding the dynamical properties of reaction network models. We describe an explicit construction of the minimal invariant regions and minimal globally attracting regions for dynamical systems consisting of two reversible reactions, where the rate constants are allowed to vary in time within a bounded interval.

Abstract

We have established a novel method to detect non-Markovian indivisible quantum channels using structural physical approximation. We have shown that this method can be used to detect eternal non -Markovian operations. We have further established that harnessing eternal non-Markovianity, we can device a protocol to detect quantum entanglement.

Abstract

The popularity of egocentric cameras and their always-on nature has lead to the abundance of day long first-person videos. The highly redundant nature of these videos and extreme camera-shakes make them difficult to watch from beginning to end. These videos require efficient summarization tools for consumption. However, traditional summarization techniques developed for static surveillance videos or highly curated sports videos and movies are either not suitable or simply do not scale for such hours long videos in the wild. On the other hand, specialized summarization techniques developed for egocentric videos limit their focus to important objects and people. This paper presents a novel unsupervised reinforcement learning framework to summarize egocentric videos both in terms of length and the content. The proposed framework facilitates incorporating various prior preferences such as faces, places, or …

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

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

The emergence of vehicle connectivity technologies and associated applications have paved the way for increased consumer interest in connected vehicles. These modern day vehicles are now capable of sending/receiving vast amounts of data and offloading computation (which is one possible service) to servers thereby improving safety, comfort, driving experience, etc. In the early stages of connectivity, all the data communication and computation offloading happened between the cloud server and the vehicles. However, this is not feasible in scenarios having strict timing requirements and bandwidth cost constraints. Vehicular Edge Computing (VEC) demonstrated an efficient way to tackle the above problem. In order to optimally utilize the resources of the edge servers for data delivery, an efficient edge resource allocation framework needs to be developed. In a recent work, data/service delivery to connected vehicles assumed a worst-case scenario that all vehicles with routes passing through an edge appear in the edge coverage region simultaneously. However, this worst-case scenario is very pessimistic, which results in overestimation of edge resources. We address this by precisely computing the set of vehicles which simultaneously appear in the coverage region of an edge (which we call vehicle overlaps). In this work, we first propose an optimization framework for edge resource allocation that minimizes the bandwidth cost of data delivery to connected vehicles while considering the traffic flow and vehicle overlaps. Then, we propose an efficient heuristic to deliver data based on minimizing global edge bandwidth cost gradient under vehicle overlaps. We demonstrate the improvement in resource allocation considering vehicle overlaps. Using real world traffic data, we also demonstrate reduction in data delivery times using the proposed heuristic.

Abstract

A processor-implemented method for generating a lip-sync for a face to a target speech of a live session to a speech in one or more languages in-sync with improved visual quality using a machine learning model and a pre-trained lip-sync model is provided. The method includes (i) determining a visual representation of the face and an audio representation, the visual representation includes crops of the face; (ii) modifying the crops of the face to obtain masked crops; (iii) obtaining a reference frame from the visual representation at a second timestamp; (iv) combining the masked crops at the first timestamp with the reference to obtain lower half crops; (v) training the machine learning model by providing historical lower half crops and historical audio representations as training data; (vi) generating lip-synced frames for the face to the target speech, and (vii) generating an in-sync lip-synced frames by the pre-trained lip-sync model.