Matching Items (20)
Filtering by
- All Subjects: Computer Engineering
- All Subjects: Unsupervised Learning
- Genre: Academic theses
- Creators: Jayasuriya, Suren
Description
It is not merely an aggregation of static entities that a video clip carries, but alsoa variety of interactions and relations among these entities. Challenges still remain
for a video captioning system to generate natural language descriptions focusing on
the prominent interest and aligning with the latent aspects beyond observations. This
work presents a Commonsense knowledge Anchored Video cAptioNing (dubbed as
CAVAN) approach. CAVAN exploits inferential commonsense knowledge to assist the
training of video captioning model with a novel paradigm for sentence-level semantic
alignment. Specifically, commonsense knowledge is queried to complement per training
caption by querying a generic knowledge atlas ATOMIC, and form the commonsense-
caption entailment corpus. A BERT based language entailment model trained from
this corpus then serves as a commonsense discriminator for the training of video
captioning model, and penalizes the model from generating semantically misaligned
captions. With extensive empirical evaluations on MSR-VTT, V2C and VATEX
datasets, CAVAN consistently improves the quality of generations and shows higher
keyword hit rate. Experimental results with ablations validate the effectiveness of
CAVAN and reveals that the use of commonsense knowledge contributes to the video
caption generation.
ContributorsShao, Huiliang (Author) / Yang, Yezhou (Thesis advisor) / Jayasuriya, Suren (Committee member) / Xiao, Chaowei (Committee member) / Arizona State University (Publisher)
Created2022
Description
This thesis presents robust and novel solutions using knowledge distillation with geometric approaches and multimodal data that can address the current challenges in deep learning, providing a comprehensive understanding of the learning process involved in knowledge distillation. Deep learning has attained significant success in various applications, such as health and wellness promotion, smart homes, and intelligent surveillance. In general, stacking more layers or increasing the number of trainable parameters causes deep networks to exhibit improved performance. However, this causes the model to become large, resulting in an additional need for computing and power resources for training, storage, and deployment. These are the core challenges in incorporating such models into small devices with limited power and computational resources. In this thesis, robust solutions aimed at addressing the aforementioned challenges are presented. These proposed methodologies and algorithmic contributions enhance the performance and efficiency of deep learning models. The thesis encompasses a comprehensive exploration of knowledge distillation, an approach that holds promise for creating compact models from high-capacity ones, while preserving their performance. This exploration covers diverse datasets, including both time series and image data, shedding light on the pivotal role of augmentation methods in knowledge distillation. The effects of these methods are rigorously examined through empirical experiments. Furthermore, the study within this thesis delves into the efficient utilization of features derived from two different teacher models, each trained on dissimilar data representations, including time-series and image data. Through these investigations, I present novel approaches to knowledge distillation, leveraging geometric techniques for the analysis of multimodal data. These solutions not only address real-world challenges but also offer valuable insights and recommendations for modeling in new applications.
ContributorsJeon, Eunsom (Author) / Turaga, Pavan (Thesis advisor) / Li, Baoxin (Committee member) / Lee, Hyunglae (Committee member) / Jayasuriya, Suren (Committee member) / Arizona State University (Publisher)
Created2023
Description
Computer vision is becoming an essential component of embedded system applications such as smartphones, wearables, autonomous systems and internet-of-things (IoT). These applications are generally deployed into environments with limited energy, memory bandwidth and computational resources. This trend is driving the development of energy-effi cient image processing solutions from sensing to computation. In this thesis, diff erent alternatives are explored to implement energy-efficient computer vision systems. First, I present a fi eld programmable gate array (FPGA) implementation of an adaptive subsampling algorithm for region-of-interest (ROI) -based object tracking. By implementing the computationally intensive sections of this algorithm on an FPGA, I aim to offl oad computing resources from energy-ineffi cient graphics processing units (GPUs) and/or general-purpose central processing units (CPUs). I also present a working system executing this algorithm in near real-time latency implemented on a standalone embedded device. Secondly, I present a neural network-based pipeline to improve the performance of event-based cameras in non-ideal optical conditions. Event-based cameras or dynamic vision sensors (DVS) are bio-inspired sensors that measure logarithmic per-pixel brightness changes in a scene. Their advantages include high dynamic range, low latency and ultra-low power when compared to standard frame-based cameras. Several tasks have been proposed to take advantage of these novel sensors but they rely on perfectly calibrated optical lenses that are in-focus. In this work I propose a methodto reconstruct events captured with an out-of-focus event-camera so they can be fed into an intensity reconstruction task. The network is trained with a dataset generated by simulating defocus blur in sequences from object tracking datasets such as LaSOT and OTB100. I also test the generalization performance of this network in scenes captured with a DAVIS event-based sensor equipped with an out-of-focus lens.
ContributorsTorres Muro, Victor Isaac (Author) / Jayasuriya, Suren (Thesis advisor) / Spanias, Andreas (Committee member) / Seo, Jae-Sun (Committee member) / Arizona State University (Publisher)
Created2022
Description
Realistic lighting is important to improve immersion and make mixed reality applications seem more plausible. To properly blend the AR objects in the real scene, it is important to study the lighting of the environment. The existing illuminationframeworks proposed by Google’s ARCore (Google’s Augmented Reality Software Development Kit) and Apple’s ARKit (Apple’s Augmented Reality Software Development Kit) are computationally expensive and have very slow refresh rates, which make them incompatible for dynamic environments and low-end mobile devices. Recently, there have been other illumination estimation frameworks such as GLEAM, Xihe, which aim at providing better illumination with faster refresh rates. GLEAM is an illumination estimation framework that understands the real scene by collecting pixel data from a reflecting spherical light probe. GLEAM uses this data to form environment cubemaps which are later mapped onto a reflection probe to generate illumination for AR objects.
It is noticed that from a single viewpoint only one half of the light probe can be observed at a time which does not give complete information about the environment. This leads to the idea of having a multi-viewpoint estimation for better performance. This thesis work analyzes the multi-viewpoint capabilities of AR illumination frameworks that use physical light probes to understand the environment. The current work builds networking using TCP and UDP protocols on GLEAM. This thesis work also documents how processor load sharing has been done while networking devices and how that benefits the performance of GLEAM on mobile devices. Some enhancements using multi-threading have also been made to the already existing GLEAM model to improve its performance.
ContributorsGurram, Sahithi (Author) / LiKamWa, Robert (Thesis advisor) / Jayasuriya, Suren (Committee member) / Turaga, Pavan (Committee member) / Arizona State University (Publisher)
Created2022
Description
Machine learning (ML) and deep learning (DL) has become an intrinsic part of multiple fields. The ability to solve complex problems makes machine learning a panacea. In the last few years, there has been an explosion of data generation, which has greatly improvised machine learning models. But this comes with a cost of high computation, which invariably increases power usage and cost of the hardware. In this thesis we explore applications of ML techniques, applied to two completely different fields - arts, media and theater and urban climate research using low-cost and low-powered edge devices. The multi-modal chatbot uses different machine learning techniques: natural language processing (NLP) and computer vision (CV) to understand inputs of the user and accordingly perform in the play and interact with the audience. This system is also equipped with other interactive hardware setups like movable LED systems, together they provide an experiential theatrical play tailored to each user. I will discuss how I used edge devices to achieve this AI system which has created a new genre in theatrical play. I will then discuss MaRTiny, which is an AI-based bio-meteorological system that calculates mean radiant temperature (MRT), which is an important parameter for urban climate research. It is also equipped with a vision system that performs different machine learning tasks like pedestrian and shade detection. The entire system costs around $200 which can potentially replace the existing setup worth $20,000. I will further discuss how I overcame the inaccuracies in MRT value caused by the system, using machine learning methods. These projects although belonging to two very different fields, are implemented using edge devices and use similar ML techniques. In this thesis I will detail out different techniques that are shared between these two projects and how they can be used in several other applications using edge devices.
ContributorsKulkarni, Karthik Kashinath (Author) / Jayasuriya, Suren (Thesis advisor) / Middel, Ariane (Thesis advisor) / Yu, Hongbin (Committee member) / Arizona State University (Publisher)
Created2021
Description
Data mining, also known as big data analysis, has been identified as a critical and challenging process for a variety of applications in real-world problems. Numerous datasets are collected and generated every day to store the information. The rise in the number of data volumes and data modality has resulted in the increased demand for data mining methods and strategies of finding anomalies, patterns, and correlations within large data sets to predict outcomes. Effective machine learning methods are widely adapted to build the data mining pipeline for various purposes like business understanding, data understanding, data preparation, modeling, evaluation, and deployment. The major challenges for effectively and efficiently mining big data include (1) data heterogeneity and (2) missing data. Heterogeneity is the natural characteristic of big data, as the data is typically collected from different sources with diverse formats. The missing value is the most common issue faced by the heterogeneous data analysis, which resulted from variety of factors including the data collecting processing, user initiatives, erroneous data entries, and so on. In response to these challenges, in this thesis, three main research directions with application scenarios have been investigated: (1) Mining and Formulating Heterogeneous Data, (2) missing value imputation strategy in various application scenarios in both offline and online manner, and (3) missing value imputation for multi-modality data. Multiple strategies with theoretical analysis are presented, and the evaluation of the effectiveness of the proposed algorithms compared with state-of-the-art methods is discussed.
Contributorsliu, Xu (Author) / He, Jingrui (Thesis advisor) / Xue, Guoliang (Thesis advisor) / Li, Baoxin (Committee member) / Tong, Hanghang (Committee member) / Arizona State University (Publisher)
Created2021
Description
With the rapid development of both hardware and software, mobile devices with their advantages in mobility, interactivity, and privacy have enabled various applications, including social networking, mixed reality, entertainment, authentication, and etc.In diverse forms such as smartphones, glasses, and watches, the number of mobile devices is expected to increase by 1 billion per year in the future.
These devices not only generate and exchange small data such as GPS data, but also large data including videos and point clouds.
Such massive visual data presents many challenges for processing on mobile devices.
First, continuously capturing and processing high resolution visual data is energy-intensive, which can drain the battery of a mobile device very quickly.
Second, data offloading for edge or cloud computing is helpful, but users are afraid that their privacy can be exposed to malicious developers.
Third, interactivity and user experience is degraded if mobile devices cannot process large scale visual data in real-time such as off-device high precision point clouds. To deal with these challenges, this work presents three solutions towards fine-grained control of visual data in mobile systems, revolving around two core ideas, enabling resolution-based tradeoffs and adopting split-process to protect visual data.In particular, this work introduces: (1) Banner media framework to remove resolution reconfiguration latency in the operating system for enabling seamless dynamic resolution-based tradeoffs;
(2) LesnCap split-process application development framework to protect user's visual privacy against malicious data collection in cloud-based Augmented Reality (AR) applications by isolating the visual processing in a distinct process;
(3) A novel voxel grid schema to enable adaptive sampling at the edge device that can sample point clouds flexibly for interactive 3D vision use cases across mobile devices and mobile networks. The evaluation in several mobile environments demonstrates that, by controlling visual data at a fine granularity, energy efficiency can be improved by 49% switching between resolutions, visual privacy can be protected through split-process with negligible overhead, and point clouds can be delivered at a high throughput meeting various requirements.Thus, this work can enable more continuous mobile vision applications for the future of a new reality.
ContributorsHu, Jinhan (Author) / LiKamWa, Robert (Thesis advisor) / Wu, Carole-Jean (Committee member) / Doupe, Adam (Committee member) / Jayasuriya, Suren (Committee member) / Arizona State University (Publisher)
Created2022
Description
Generating real-world content for VR is challenging in terms of capturing and processing at high resolution and high frame-rates. The content needs to represent a truly immersive experience, where the user can look around in 360-degree view and perceive the depth of the scene. The existing solutions only capture and offload the compute load to the server. But offloading large amounts of raw camera feeds takes longer latencies and poses difficulties for real-time applications. By capturing and computing on the edge, we can closely integrate the systems and optimize for low latency. However, moving the traditional stitching algorithms to battery constrained device needs at least three orders of magnitude reduction in power. We believe that close integration of capture and compute stages will lead to reduced overall system power.
We approach the problem by building a hardware prototype and characterize the end-to-end system bottlenecks of power and performance. The prototype has 6 IMX274 cameras and uses Nvidia Jetson TX2 development board for capture and computation. We found that capturing is bottlenecked by sensor power and data-rates across interfaces, whereas compute is limited by the total number of computations per frame. Our characterization shows that redundant capture and redundant computations lead to high power, huge memory footprint, and high latency. The existing systems lack hardware-software co-design aspects, leading to excessive data transfers across the interfaces and expensive computations within the individual subsystems. Finally, we propose mechanisms to optimize the system for low power and low latency. We emphasize the importance of co-design of different subsystems to reduce and reuse the data. For example, reusing the motion vectors of the ISP stage reduces the memory footprint of the stereo correspondence stage. Our estimates show that pipelining and parallelization on custom FPGA can achieve real time stitching.
We approach the problem by building a hardware prototype and characterize the end-to-end system bottlenecks of power and performance. The prototype has 6 IMX274 cameras and uses Nvidia Jetson TX2 development board for capture and computation. We found that capturing is bottlenecked by sensor power and data-rates across interfaces, whereas compute is limited by the total number of computations per frame. Our characterization shows that redundant capture and redundant computations lead to high power, huge memory footprint, and high latency. The existing systems lack hardware-software co-design aspects, leading to excessive data transfers across the interfaces and expensive computations within the individual subsystems. Finally, we propose mechanisms to optimize the system for low power and low latency. We emphasize the importance of co-design of different subsystems to reduce and reuse the data. For example, reusing the motion vectors of the ISP stage reduces the memory footprint of the stereo correspondence stage. Our estimates show that pipelining and parallelization on custom FPGA can achieve real time stitching.
ContributorsGunnam, Sridhar (Author) / LiKamWa, Robert (Thesis advisor) / Turaga, Pavan (Committee member) / Jayasuriya, Suren (Committee member) / Arizona State University (Publisher)
Created2018
Description
The popularity of social media has generated abundant large-scale social networks, which advances research on network analytics. Good representations of nodes in a network can facilitate many network mining tasks. The goal of network representation learning (network embedding) is to learn low-dimensional vector representations of social network nodes that capture certain properties of the networks. With the learned node representations, machine learning and data mining algorithms can be applied for network mining tasks such as link prediction and node classification. Because of its ability to learn good node representations, network representation learning is attracting increasing attention and various network embedding algorithms are proposed.
Despite the success of these network embedding methods, the majority of them are dedicated to static plain networks, i.e., networks with fixed nodes and links only; while in social media, networks can present in various formats, such as attributed networks, signed networks, dynamic networks and heterogeneous networks. These social networks contain abundant rich information to alleviate the network sparsity problem and can help learn a better network representation; while plain network embedding approaches cannot tackle such networks. For example, signed social networks can have both positive and negative links. Recent study on signed networks shows that negative links have added value in addition to positive links for many tasks such as link prediction and node classification. However, the existence of negative links challenges the principles used for plain network embedding. Thus, it is important to study signed network embedding. Furthermore, social networks can be dynamic, where new nodes and links can be introduced anytime. Dynamic networks can reveal the concept drift of a user and require efficiently updating the representation when new links or users are introduced. However, static network embedding algorithms cannot deal with dynamic networks. Therefore, it is important and challenging to propose novel algorithms for tackling different types of social networks.
In this dissertation, we investigate network representation learning in social media. In particular, we study representative social networks, which includes attributed network, signed networks, dynamic networks and document networks. We propose novel frameworks to tackle the challenges of these networks and learn representations that not only capture the network structure but also the unique properties of these social networks.
Despite the success of these network embedding methods, the majority of them are dedicated to static plain networks, i.e., networks with fixed nodes and links only; while in social media, networks can present in various formats, such as attributed networks, signed networks, dynamic networks and heterogeneous networks. These social networks contain abundant rich information to alleviate the network sparsity problem and can help learn a better network representation; while plain network embedding approaches cannot tackle such networks. For example, signed social networks can have both positive and negative links. Recent study on signed networks shows that negative links have added value in addition to positive links for many tasks such as link prediction and node classification. However, the existence of negative links challenges the principles used for plain network embedding. Thus, it is important to study signed network embedding. Furthermore, social networks can be dynamic, where new nodes and links can be introduced anytime. Dynamic networks can reveal the concept drift of a user and require efficiently updating the representation when new links or users are introduced. However, static network embedding algorithms cannot deal with dynamic networks. Therefore, it is important and challenging to propose novel algorithms for tackling different types of social networks.
In this dissertation, we investigate network representation learning in social media. In particular, we study representative social networks, which includes attributed network, signed networks, dynamic networks and document networks. We propose novel frameworks to tackle the challenges of these networks and learn representations that not only capture the network structure but also the unique properties of these social networks.
ContributorsWang, Suhang (Author) / Liu, Huan (Thesis advisor) / Aggarwal, Charu (Committee member) / Sen, Arunabha (Committee member) / Tong, Hanghang (Committee member) / Arizona State University (Publisher)
Created2018
Description
Many neurological disorders, especially those that result in dementia, impact speech and language production. A number of studies have shown that there exist subtle changes in linguistic complexity in these individuals that precede disease onset. However, these studies are conducted on controlled speech samples from a specific task. This thesis explores the possibility of using natural language processing in order to detect declining linguistic complexity from more natural discourse. We use existing data from public figures suspected (or at risk) of suffering from cognitive-linguistic decline, downloaded from the Internet, to detect changes in linguistic complexity. In particular, we focus on two case studies. The first case study analyzes President Ronald Reagan’s transcribed spontaneous speech samples during his presidency. President Reagan was diagnosed with Alzheimer’s disease in 1994, however my results showed declining linguistic complexity during the span of the 8 years he was in office. President George Herbert Walker Bush, who has no known diagnosis of Alzheimer’s disease, shows no decline in the same measures. In the second case study, we analyze transcribed spontaneous speech samples from the news conferences of 10 current NFL players and 18 non-player personnel since 2007. The non-player personnel have never played professional football. Longitudinal analysis of linguistic complexity showed contrasting patterns in the two groups. The majority (6 of 10) of current players showed decline in at least one measure of linguistic complexity over time. In contrast, the majority (11 out of 18) of non-player personnel showed an increase in at least one linguistic complexity measure.
ContributorsWang, Shuai (Author) / Berisha, Visar (Thesis advisor) / LaCross, Amy (Committee member) / Tong, Hanghang (Committee member) / Arizona State University (Publisher)
Created2016