Search

Over the last decade, deep learning has shown great success at performing computer vision tasks, including classification, super-resolution, and style transfer. Now, we apply it to data compression to help build the next generation of multimedia codecs. This thesis provides three primary contributions to this new field of learned compression. First, we present an efficient low-complexity entropy model that dynamically adapts the encoding distribution to a specific input by compressing and transmitting the encoding distribution itself as side information. Secondly, we propose a novel lightweight low-complexity point cloud codec that is highly specialized for classification, attaining significant reductions in bitrate compared to non-specialized codecs. Lastly, we explore how motion within the input domain between consecutive video frames is manifested in the corresponding convolutionally-derived latent space., Comment: 65 pages, 21 figures, Master's Thesis, defended in 2023

Recognizing human actions in adverse lighting conditions presents significant challenges in computer vision, with wide-ranging applications in visual surveillance and nighttime driving. Existing methods tackle action recognition and dark enhancement separately, limiting the potential for end-to-end learning of spatiotemporal representations for video action classification. This paper introduces Dark Transformer, a novel video transformer-based approach for action recognition in low-light environments. Dark Transformer leverages spatiotemporal self-attention mechanisms in cross-domain settings to enhance cross-domain action recognition. By extending video transformers to learn cross-domain knowledge, Dark Transformer achieves state-of-the-art performance on benchmark action recognition datasets, including InFAR, XD145, and ARID. The proposed approach demonstrates significant promise in addressing the challenges of action recognition in adverse lighting conditions, offering practical implications for real-world applications., Comment: 8 Figures, 12 Pages

The entropy bottleneck introduced by Ball\'e et al. is a common component used in many learned compression models. It encodes a transformed latent representation using a static distribution whose parameters are learned during training. However, the actual distribution of the latent data may vary wildly across different inputs. The static distribution attempts to encompass all possible input distributions, thus fitting none of them particularly well. This unfortunate phenomenon, sometimes known as the amortization gap, results in suboptimal compression. To address this issue, we propose a method that dynamically adapts the encoding distribution to match the latent data distribution for a specific input. First, our model estimates a better encoding distribution for a given input. This distribution is then compressed and transmitted as an additional side-information bitstream. Finally, the decoder reconstructs the encoding distribution and uses it to decompress the corresponding latent data. Our method achieves a Bj{\o}ntegaard-Delta (BD)-rate gain of -7.10% on the Kodak test dataset when applied to the standard fully-factorized architecture. Furthermore, considering computational complexity, the transform used by our method is an order of magnitude cheaper in terms of Multiply-Accumulate (MAC) operations compared to related side-information methods such as the scale hyperprior., Comment: 7 pages, 5 figures, IEEE ICIP 2024

As urban areas grapple with unprecedented challenges stemming from population growth and climate change, the emergence of urban digital twins offers a promising solution. This paper presents a case study focusing on Sydney's urban digital twin, a virtual replica integrating diverse real-time and historical data, including weather, crime, emissions, and traffic. Through advanced visualization and data analysis techniques, the study explores some applications of this digital twin in urban sustainability, such as spatial ranking of suburbs and automatic identification of correlations between variables. Additionally, the research delves into predictive modeling, employing machine learning to forecast traffic crash risks using environmental data, showcasing the potential for proactive interventions. The contributions of this work lie in the comprehensive exploration of a city-scale digital twin for sustainable urban planning, offering a multifaceted approach to data-driven decision-making.

Commercially impactful quantum algorithms such as quantum chemistry and Shor's algorithm require a number of qubits and gates far beyond the capacity of any existing quantum processor. Distributed architectures, which scale horizontally by networking modules, provide a route to commercial utility and will eventually surpass the capability of any single quantum computing module. Such processors consume remote entanglement distributed between modules to realize distributed quantum logic. Networked quantum computers will therefore require the capability to rapidly distribute high fidelity entanglement between modules. Here we present preliminary demonstrations of some key distributed quantum computing protocols on silicon T centres in isotopically-enriched silicon. We demonstrate the distribution of entanglement between modules and consume it to apply a teleported gate sequence, establishing a proof-of-concept for T centres as a distributed quantum computing and networking platform., Comment: 14 pages, 13 figures

Video anomaly detection (VAD) holds immense importance across diverse domains such as surveillance, healthcare, and environmental monitoring. While numerous surveys focus on conventional VAD methods, they often lack depth in exploring specific approaches and emerging trends. This survey explores deep learning-based VAD, expanding beyond traditional supervised training paradigms to encompass emerging weakly supervised, self-supervised, and unsupervised approaches. A prominent feature of this review is the investigation of core challenges within the VAD paradigms including large-scale datasets, features extraction, learning methods, loss functions, regularization, and anomaly score prediction. Moreover, this review also investigates the vision language models (VLMs) as potent feature extractors for VAD. VLMs integrate visual data with textual descriptions or spoken language from videos, enabling a nuanced understanding of scenes crucial for anomaly detection. By addressing these challenges and proposing future research directions, this review aims to foster the development of robust and efficient VAD systems leveraging the capabilities of VLMs for enhanced anomaly detection in complex real-world scenarios. This comprehensive analysis seeks to bridge existing knowledge gaps, provide researchers with valuable insights, and contribute to shaping the future of VAD research.

The concept of neural correlates of consciousness (NCC), which suggests that specific neural activities are linked to conscious experiences, has gained widespread acceptance. This acceptance is based on a wealth of evidence from experimental studies, brain imaging techniques such as fMRI and EEG, and theoretical frameworks like integrated information theory (IIT) within neuroscience and the philosophy of mind. This paper explores the potential for artificial consciousness by merging neuromorphic design and architecture with brain simulations. It proposes the Neuromorphic Correlates of Artificial Consciousness (NCAC) as a theoretical framework. While the debate on artificial consciousness remains contentious due to our incomplete grasp of consciousness, this work may raise eyebrows and invite criticism. Nevertheless, this optimistic and forward-thinking approach is fueled by insights from the Human Brain Project, advancements in brain imaging like EEG and fMRI, and recent strides in AI and computing, including quantum and neuromorphic designs. Additionally, this paper outlines how machine learning can play a role in crafting artificial consciousness, aiming to realise machine consciousness and awareness in the future., Comment: 13 Pages, 8 Figures

Point cloud processing methods leverage local and global point features %at the feature level to cater to downstream tasks, yet they often overlook the task-level context inherent in point clouds during the encoding stage. We argue that integrating task-level information into the encoding stage significantly enhances performance. To that end, we propose SMTransformer which incorporates task-level information into a vector-based transformer by utilizing a soft mask generated from task-level queries and keys to learn the attention weights. Additionally, to facilitate effective communication between features from the encoding and decoding layers in high-level tasks such as segmentation, we introduce a skip-attention-based up-sampling block. This block dynamically fuses features from various resolution points across the encoding and decoding layers. To mitigate the increase in network parameters and training time resulting from the complexity of the aforementioned blocks, we propose a novel shared position encoding strategy. This strategy allows various transformer blocks to share the same position information over the same resolution points, thereby reducing network parameters and training time without compromising accuracy.Experimental comparisons with existing methods on multiple datasets demonstrate the efficacy of SMTransformer and skip-attention-based up-sampling for point cloud processing tasks, including semantic segmentation and classification. In particular, we achieve state-of-the-art semantic segmentation results of 73.4% mIoU on S3DIS Area 5 and 62.4% mIoU on SWAN dataset, Comment: 14 pages, 8 figures

Due to the limited computational capabilities of edge devices, deep learning inference can be quite expensive. One remedy is to compress and transmit point cloud data over the network for server-side processing. Unfortunately, this approach can be sensitive to network factors, including available bitrate. Luckily, the bitrate requirements can be reduced without sacrificing inference accuracy by using a machine task-specialized codec. In this paper, we present a scalable codec for point-cloud data that is specialized for the machine task of classification, while also providing a mechanism for human viewing. In the proposed scalable codec, the "base" bitstream supports the machine task, and an "enhancement" bitstream may be used for better input reconstruction performance for human viewing. We base our architecture on PointNet++, and test its efficacy on the ModelNet40 dataset. We show significant improvements over prior non-specialized codecs., Comment: 5 pages, 4 figures, 2024 Picture Coding Symposium (PCS)

Deforestation, a major contributor to climate change, poses detrimental consequences such as agricultural sector disruption, global warming, flash floods, and landslides. Conventional approaches to urban street tree inventory suffer from inaccuracies and necessitate specialised equipment. To overcome these challenges, this paper proposes an innovative method that leverages deep learning techniques and mobile phone imaging for urban street tree inventory. Our approach utilises a pair of images captured by smartphone cameras to accurately segment tree trunks and compute the diameter at breast height (DBH). Compared to traditional methods, our approach exhibits several advantages, including superior accuracy, reduced dependency on specialised equipment, and applicability in hard-to-reach areas. We evaluated our method on a comprehensive dataset of 400 trees and achieved a DBH estimation accuracy with an error rate of less than 2.5%. Our method holds significant potential for substantially improving forest management practices. By enhancing the accuracy and efficiency of tree inventory, our model empowers urban management to mitigate the adverse effects of deforestation and climate change., Comment: 8 Pages, 7 figures and 5 Tables

Deep learning is increasingly being used to perform machine vision tasks such as classification, object detection, and segmentation on 3D point cloud data. However, deep learning inference is computationally expensive. The limited computational capabilities of end devices thus necessitate a codec for transmitting point cloud data over the network for server-side processing. Such a codec must be lightweight and capable of achieving high compression ratios without sacrificing accuracy. Motivated by this, we present a novel point cloud codec that is highly specialized for the machine task of classification. Our codec, based on PointNet, achieves a significantly better rate-accuracy trade-off in comparison to alternative methods. In particular, it achieves a 94% reduction in BD-bitrate over non-specialized codecs on the ModelNet40 dataset. For low-resource end devices, we also propose two lightweight configurations of our encoder that achieve similar BD-bitrate reductions of 93% and 92% with 3% and 5% drops in top-1 accuracy, while consuming only 0.470 and 0.048 encoder-side kMACs/point, respectively. Our codec demonstrates the potential of specialized codecs for machine analysis of point clouds, and provides a basis for extension to more complex tasks and datasets in the future., Comment: 6 pages, 4 figures, IEEE MMSP 2023

As AI applications for mobile devices become more prevalent, there is an increasing need for faster execution and lower energy consumption for deep learning model inference. Historically, the models run on mobile devices have been smaller and simpler in comparison to large state-of-the-art research models, which can only run on the cloud. However, cloud-only inference has drawbacks such as increased network bandwidth consumption and higher latency. In addition, cloud-only inference requires the input data (images, audio) to be fully transferred to the cloud, creating concerns about potential privacy breaches. There is an alternative approach: shared mobile-cloud inference. Partial inference is performed on the mobile in order to reduce the dimensionality of the input data and arrive at a compact feature tensor, which is a latent space representation of the input signal. The feature tensor is then transmitted to the server for further inference. This strategy can reduce inference latency, energy consumption, and network bandwidth usage, as well as provide privacy protection, because the original signal never leaves the mobile. Further performance gain can be achieved by compressing the feature tensor before its transmission., Comment: 56 pages, 20 figures, Bachelor's Thesis, defended in 2020

Quantum image computing draws a lot of attention due to storing and processing image data faster than classical. With increasing the image size, the number of connections also increases, leading to the circuit complex. Therefore, efficient quantum image representation and compression issues are still challenging. The encoding of images for representation and compression in quantum systems is different from classical ones. In quantum, encoding of position is more concerned which is the major difference from the classical. In this paper, a novel zero-discarded state connection novel enhance quantum representation (ZSCNEQR) approach is introduced to reduce complexity further by discarding '0' in the location representation information. In the control operational gate, only input '1' contribute to its output thus, discarding zero makes the proposed ZSCNEQR circuit more efficient. The proposed ZSCNEQR approach significantly reduced the required bit for both representation and compression. The proposed method requires 11.76\% less qubits compared to the recent existing method. The results show that the proposed approach is highly effective for representing and compressing images compared to the two relevant existing methods in terms of rate-distortion performance., Comment: 7 figures

A Digital Twin (DT) is a virtual replica of a physical object or system, created to monitor, analyze, and optimize its behavior and characteristics. A Spatial Digital Twin (SDT) is a specific type of digital twin that emphasizes the geospatial aspects of the physical entity, incorporating precise location and dimensional attributes for a comprehensive understanding within its spatial environment. The current body of research on SDTs primarily concentrates on analyzing their potential impact and opportunities within various application domains. As building an SDT is a complex process and requires a variety of spatial computing technologies, it is not straightforward for practitioners and researchers of this multi-disciplinary domain to grasp the underlying details of enabling technologies of the SDT. In this paper, we are the first to systematically analyze different spatial technologies relevant to building an SDT in layered approach (starting from data acquisition to visualization). More specifically, we present the key components of SDTs into four layers of technologies: (i) data acquisition; (ii) spatial database management \& big data analytics systems; (iii) GIS middleware software, maps \& APIs; and (iv) key functional components such as visualizing, querying, mining, simulation and prediction. Moreover, we discuss how modern technologies such as AI/ML, blockchains, and cloud computing can be effectively utilized in enabling and enhancing SDTs. Finally, we identify a number of research challenges and opportunities in SDTs. This work serves as an important resource for SDT researchers and practitioners as it explicitly distinguishes SDTs from traditional DTs, identifies unique applications, outlines the essential technological components of SDTs, and presents a vision for their future development along with the challenges that lie ahead., Comment: 26 pages, 2 figures

As an increasing amount of image and video content will be analyzed by machines, there is demand for a new codec paradigm that is capable of compressing visual input primarily for the purpose of computer vision inference, while secondarily supporting input reconstruction. In this work, we propose a learned compression architecture that can be used to build such a codec. We introduce a novel variational formulation that explicitly takes feature data relevant to the desired inference task as input at the encoder side. As such, our learned scalable image codec encodes and transmits two disentangled latent representations for object detection and input reconstruction. We note that compared to relevant benchmarks, our proposed scheme yields a more compact latent representation that is specialized for the inference task. Our experiments show that our proposed system achieves a bit rate savings of 40.6% on the primary object detection task compared to the current state-of-the-art, albeit with some degradation in performance for the secondary input reconstruction task., Comment: accepted as a paper for DCC 2023

Edges fractal approach in graphene e Defects density gain a b s t r a c t To optimize the technological development together with energy gain, the crucial materials needs to be tailored in a smart way to benefit a maximum from the property-structure relation. Herein we propose the way to increase a defect density in graphene moving from 1D linear edges to fractal edges, also highlight the fractal nature of graphene structures them-self. The tentative oxidation and hydrogenation catalytic etching of few layer graphene results in structures with edges fractals, jaggy edges at graphene periphery or in newly formed etched holes.

Spatial frequency analysis and transforms serve a central role in most engineered image and video lossy codecs, but are rarely employed in neural network (NN)-based approaches. We propose a novel NN-based image coding framework that utilizes forward wavelet transforms to decompose the input signal by spatial frequency. Our encoder generates separate bitstreams for each latent representation of low and high frequencies. This enables our decoder to selectively decode bitstreams in a quality-scalable manner. Hence, the decoder can produce an enhanced image by using an enhancement bitstream in addition to the base bitstream. Furthermore, our method is able to enhance only a specific region of interest (ROI) by using a corresponding part of the enhancement latent representation. Our experiments demonstrate that the proposed method shows competitive rate-distortion performance compared to several non-scalable image codecs. We also showcase the effectiveness of our two-level quality scalability, as well as its practicality in ROI quality enhancement., Comment: Presented at VCIP'22

Quantum computing draws huge attention due to its faster computational capability compared to classical computing to represent and compress the classical image data into the quantum domain. The main idea of quantum domain representation is to convert pixel intensities and their coordinates i.e. state label preparation using quantum bits i.e. Qubits. For a bigger size image, the state label preparation takes more Qubits. To address more Qubits issues, a novel SCMNEQR (State Connection Modification Novel Enhanced Quantum Representation) approach has been proposed that uses fewer qubits to map the arbitrary size of the grayscale image using block-wise state label preparation. The proposed SCMNEQR approach introduces the state connection using a reset gate rather than repeating the use of the Toffoli gate used in the existing approach. The experimental results show that the proposed approach outperforms the existing methods in terms of compression., Comment: 11 pages, 12 figures

Historically, the analysis of stimulus-dependent time-frequency patterns has been the cornerstone of most electroencephalography (EEG) studies. The abnormal oscillations in high-frequency waves associated with psychotic disorders during sensory and cognitive tasks have been studied many times. However, any significant dissimilarity in the resting-state low-frequency bands is yet to be established. Spectral analysis of the alpha and delta band waves shows the effectiveness of stimulus-independent EEG in identifying the abnormal activity patterns of pathological brains. A generalized model incorporating multiple frequency bands should be more efficient in associating potential EEG biomarkers with First-Episode Psychosis (FEP), leading to an accurate diagnosis. We explore multiple machine-learning methods, including random-forest, support vector machine, and Gaussian Process Classifier (GPC), to demonstrate the practicality of resting-state Power Spectral Density (PSD) to distinguish patients of FEP from healthy controls. A comprehensive discussion of our preprocessing methods for PSD analysis and a detailed comparison of different models are included in this paper. The GPC model outperforms the other models with a specificity of 95.78% to show that PSD can be used as an effective feature extraction technique for analyzing and classifying resting-state EEG signals of psychiatric disorders., Comment: 10 Figures, 13 Pages

In the last two decades, functional magnetic resonance imaging (fMRI) has emerged as one of the most effective technologies in clinical research of the human brain. fMRI allows researchers to study healthy and pathological brains while they perform various neuropsychological functions. Beyond task-related activations, the human brain has some intrinsic activity at a task-negative (resting) state that surprisingly consumes a lot of energy to support communication among neurons. Recent neuroimaging research has also seen an increase in modeling and analyzing brain activity in terms of a graph or network. Since graph models facilitate a systems-theoretic explanation of the brain, they have become increasingly relevant with advances in network science and the popularization of complex systems theory. The purpose of this study is to look into the abnormalities in resting brain functions in adults with Attention Deficit Hyperactivity Disorder (ADHD). The primary goal is to investigate resting-state functional connectivity (FC), which can be construed as a significant temporal coincidence in blood-oxygen-level dependent (BOLD) signals between functionally related brain regions in the absence of any stimulus or task. When compared to healthy controls, ADHD patients have lower average connectivity in the Supramarginal Gyrus and Superior Parietal Lobule, but higher connectivity in the Lateral Occipital Cortex and Inferior Temporal Gyrus. We also hypothesize that the network organization of default mode and dorsal attention regions is abnormal in ADHD patients., Comment: 8 Figures, 14 Pages

Due to the numerous potential applications in visual surveillance and nighttime driving, recognizing human action in low-light conditions remains a difficult problem in computer vision. Existing methods separate action recognition and dark enhancement into two distinct steps to accomplish this task. However, isolating the recognition and enhancement impedes end-to-end learning of the space-time representation for video action classification. This paper presents a domain adaptation-based action recognition approach that uses adversarial learning in cross-domain settings to learn cross-domain action recognition. Supervised learning can train it on a large amount of labeled data from the source domain (daytime action sequences). However, it uses deep domain invariant features to perform unsupervised learning on many unlabelled data from the target domain (night-time action sequences). The resulting augmented model, named 3D-DiNet can be trained using standard backpropagation with an additional layer. It achieves SOTA performance on InFAR and XD145 actions datasets., Comment: 6 Pages, 6 Figures

Diffusion Models (DMs) have demonstrated state-of-the-art performance in content generation without requiring adversarial training. These models are trained using a two-step process. First, a forward - diffusion - process gradually adds noise to a datum (usually an image). Then, a backward - reverse diffusion - process gradually removes the noise to turn it into a sample of the target distribution being modelled. DMs are inspired by non-equilibrium thermodynamics and have inherent high computational complexity. Due to the frequent function evaluations and gradient calculations in high-dimensional spaces, these models incur considerable computational overhead during both training and inference stages. This can not only preclude the democratization of diffusion-based modelling, but also hinder the adaption of diffusion models in real-life applications. Not to mention, the efficiency of computational models is fast becoming a significant concern due to excessive energy consumption and environmental scares. These factors have led to multiple contributions in the literature that focus on devising computationally efficient DMs. In this review, we present the most recent advances in diffusion models for vision, specifically focusing on the important design aspects that affect the computational efficiency of DMs. In particular, we emphasize the recently proposed design choices that have led to more efficient DMs. Unlike the other recent reviews, which discuss diffusion models from a broad perspective, this survey is aimed at pushing this research direction forward by highlighting the design strategies in the literature that are resulting in practicable models for the broader research community. We also provide a future outlook of diffusion models in vision from their computational efficiency viewpoint., Comment: 14 Pages, 5 Figures (in progress)

Vision transformers are emerging as a powerful tool to solve computer vision problems. Recent techniques have also proven the efficacy of transformers beyond the image domain to solve numerous video-related tasks. Among those, human action recognition is receiving special attention from the research community due to its widespread applications. This article provides the first comprehensive survey of vision transformer techniques for action recognition. We analyze and summarize the existing and emerging literature in this direction while highlighting the popular trends in adapting transformers for action recognition. Due to their specialized application, we collectively refer to these methods as ``action transformers''. Our literature review provides suitable taxonomies for action transformers based on their architecture, modality, and intended objective. Within the context of action transformers, we explore the techniques to encode spatio-temporal data, dimensionality reduction, frame patch and spatio-temporal cube construction, and various representation methods. We also investigate the optimization of spatio-temporal attention in transformer layers to handle longer sequences, typically by reducing the number of tokens in a single attention operation. Moreover, we also investigate different network learning strategies, such as self-supervised and zero-shot learning, along with their associated losses for transformer-based action recognition. This survey also summarizes the progress towards gaining grounds on evaluation metric scores on important benchmarks with action transformers. Finally, it provides a discussion on the challenges, outlook, and future avenues for this research direction., Comment: 15 Figures and 5 Tables

In recent year, quantum image processing got a lot of attention in the field of image processing due to opportunity to place huge image data in quantum Hilbert space. Hilbert space or Euclidean space has infinite dimension to locate and process the image data faster. Moreover, several researches show that, the computational time of quantum process is faster than classical computer. By encoding and compressing the image in quantum domain is still challenging issue. From literature survey, we have proposed a DCTEFRQI (Direct Cosine Transform Efficient Flexible Representation of Quantum Image) algorithm to represent and compress gray image efficiently which save computational time and minimize the complexity of preparation. The objective of this work is to represent and compress various gray image size in quantum computer using DCT(Discrete Cosine Transform) and EFRQI (Efficient Flexible Representation of Quantum Image) approach together. Quirk simulation tool is used to design corresponding quantum image circuit. Due to limitation of qubit, total 16 numbers of qubit are used to represent the gray scale image among those 8 are used to map the coefficient values and the rest 8 are used to generate the corresponding coefficient position. Theoretical analysis and experimental result show that, proposed DCTEFRQI scheme provides better representation and compression compare to DCT-GQIR, DWT-GQIR and DWT-EFRQI in terms of PSNR(Peak Signal to Noise Ratio) and bit rate..

With the fast growth of immersive video sequences, achieving seamless and high-quality compressed 3D content is even more critical. MPEG recently developed a video-based point cloud compression (V-PCC) standard for dynamic point cloud coding. However, reconstructed point clouds using V-PCC suffer from different artifacts, including losing data during pre-processing before applying existing video coding techniques, e.g., High-Efficiency Video Coding (HEVC). Patch generations and self-occluded points in the 3D to the 2D projection are the main reasons for missing data using V-PCC. This paper proposes a new method that introduces overlapping slicing as an alternative to patch generation to decrease the number of patches generated and the amount of data lost. In the proposed method, the entire point cloud has been cross-sectioned into variable-sized slices based on the number of self-occluded points so that data loss can be minimized in the patch generation process and projection. For this, a variable number of layers are considered, partially overlapped to retain the self-occluded points. The proposed method's added advantage is to reduce the bits requirement and to encode geometric data using the slicing base position. The experimental results show that the proposed method is much more flexible than the standard V-PCC method, improves the rate-distortion performance, and decreases the data loss significantly compared to the standard V-PCC method.