Search

Gallbladder cancer (GBC) is the most frequent cause of disease among biliary tract neoplasms. Identifying the molecular mechanisms and biomarkers linked to GBC progression has been a significant challenge in scientific research. Few recent studies have explored the roles of biomarkers in GBC. Our study aimed to identify biomarkers in GBC using machine learning (ML) and bioinformatics techniques. We compared GBC tumor samples with normal samples to identify differentially expressed genes (DEGs) from two microarray datasets (GSE100363, GSE139682) obtained from the NCBI GEO database. A total of 146 DEGs were found, with 39 up-regulated and 107 down-regulated genes. Functional enrichment analysis of these DEGs was performed using Gene Ontology (GO) terms and REACTOME pathways through DAVID. The protein-protein interaction network was constructed using the STRING database. To identify hub genes, we applied three ranking algorithms: Degree, MNC, and Closeness Centrality. The intersection of hub genes from these algorithms yielded 11 hub genes. Simultaneously, two feature selection methods (Pearson correlation and recursive feature elimination) were used to identify significant gene subsets. We then developed ML models using SVM and RF on the GSE100363 dataset, with validation on GSE139682, to determine the gene subset that best distinguishes GBC samples. The hub genes outperformed the other gene subsets. Finally, NTRK2, COL14A1, SCN4B, ATP1A2, SLC17A7, SLIT3, COL7A1, CLDN4, CLEC3B, ADCYAP1R1, and MFAP4 were identified as crucial genes, with SLIT3, COL7A1, and CLDN4 being strongly linked to GBC development and prediction.

Large Language Models (LLMs) are gaining significant popularity in recent years for specialized tasks using prompts due to their low computational cost. Standard methods like prefix tuning utilize special, modifiable tokens that lack semantic meaning and require extensive training for best performance, often falling short. In this context, we propose a novel method called Semantic Knowledge Tuning (SK-Tuning) for prompt and prefix tuning that employs meaningful words instead of random tokens. This method involves using a fixed LLM to understand and process the semantic content of the prompt through zero-shot capabilities. Following this, it integrates the processed prompt with the input text to improve the model's performance on particular tasks. Our experimental results show that SK-Tuning exhibits faster training times, fewer parameters, and superior performance on tasks such as text classification and understanding compared to other tuning methods. This approach offers a promising method for optimizing the efficiency and effectiveness of LLMs in processing language tasks., Comment: Accepted in Nature Scientific Reports

Audio separation in real-world scenarios, where mixtures contain a variable number of sources, presents significant challenges due to limitations of existing models, such as over-separation, under-separation, and dependence on predefined training sources. We propose OpenSep, a novel framework that leverages large language models (LLMs) for automated audio separation, eliminating the need for manual intervention and overcoming source limitations. OpenSep uses textual inversion to generate captions from audio mixtures with off-the-shelf audio captioning models, effectively parsing the sound sources present. It then employs few-shot LLM prompting to extract detailed audio properties of each parsed source, facilitating separation in unseen mixtures. Additionally, we introduce a multi-level extension of the mix-and-separate training framework to enhance modality alignment by separating single source sounds and mixtures simultaneously. Extensive experiments demonstrate OpenSep's superiority in precisely separating new, unseen, and variable sources in challenging mixtures, outperforming SOTA baseline methods. Code is released at https://github.com/tanvir-utexas/OpenSep.git, Comment: Accepted in EMNLP 2024 Main

In the noisy intermediate scale quantum (NISQ) era, the control over the qubits is limited due to the errors caused by quantum decoherence, crosstalk, and imperfect calibration. Hence, it is necessary to reduce the size of the large-scale classical data, such as images, when they are to be processed by quantum networks. Conventionally input classical data are reduced in the classical domain using classical networks such as autoencoders and, subsequently, analyzed in the quantum domain. These conventional techniques involve training an enormous number of parameters, making them computationally costly. In this paper, a dynamic patch-based quantum domain data reduction network with a classical attention mechanism is proposed to avoid such data reductions, and subsequently coupled with a novel quantum classifier to perform classification tasks. The architecture processes the classical data sequentially in patches and reduces them using a quantum convolutional-inspired reduction network and further enriches them using a self-attention technique, which utilizes a classical mask derived from simple statistical operations on the native classical data, after measurement. The reduced representation is passed through a quantum classifier, which re-encodes it into quantum states, processes them through quantum ansatzes, and finally measures them to predict classes. This training process involves a joint optimization scheme that considers both the reduction and classifier networks, making the reduction operation dynamic. The proposed architecture has been extensively tested on the publicly available Fashion MNIST dataset, and it has excellent classification performance using significantly reduced training parameters., Comment: 17 pages, 10 figures, 2 tables

Photonic topological insulators provide unidirectional, robust, wavelength-selective transport of light at an interface while keeping it insulated at the bulk of the material. The non-trivial topology results in an immunity to backscattering, sharp turns, and fabrication defects. This work leverages these unique properties to design a 2-channel optical demultiplexer based on a lithium niobate photonic topological insulator with piezoelectric switch-off capabilities. A photonic topological insulator design for the demultiplexer allows for good wavelength selectivity, crosstalk as low as $-$54 dB, and better isolation between output channels. The primary operating wavelengths presented are the telecommunication wavelengths of 1310 nm and 1550 nm, but the use of the lithium niobate material allows operation at multiple operating wavelengths. Furthermore, we propose a post-fabrication method to switch off the topological protection and, thus, optical transmittance via an applied voltage utilizing the inverse piezoelectric effect of lithium niobate. This work will contribute to advancing lithium niobate integrated photonics and developing efficient, multi-wavelength, electrically controlled optical communication systems and integrated photonic circuits.

This paper presents DENSER, an efficient and effective approach leveraging 3D Gaussian splatting (3DGS) for the reconstruction of dynamic urban environments. While several methods for photorealistic scene representations, both implicitly using neural radiance fields (NeRF) and explicitly using 3DGS have shown promising results in scene reconstruction of relatively complex dynamic scenes, modeling the dynamic appearance of foreground objects tend to be challenging, limiting the applicability of these methods to capture subtleties and details of the scenes, especially far dynamic objects. To this end, we propose DENSER, a framework that significantly enhances the representation of dynamic objects and accurately models the appearance of dynamic objects in the driving scene. Instead of directly using Spherical Harmonics (SH) to model the appearance of dynamic objects, we introduce and integrate a new method aiming at dynamically estimating SH bases using wavelets, resulting in better representation of dynamic objects appearance in both space and time. Besides object appearance, DENSER enhances object shape representation through densification of its point cloud across multiple scene frames, resulting in faster convergence of model training. Extensive evaluations on KITTI dataset show that the proposed approach significantly outperforms state-of-the-art methods by a wide margin. Source codes and models will be uploaded to this repository https://github.com/sntubix/denser

ANNZ is a fast and simple algorithm which utilises artificial neural networks (ANNs), it was known as one of the pioneers of machine learning approaches to photometric redshift estimation decades ago. We enhanced the algorithm by introducing new activation functions like tanh, softplus, SiLU, Mish and ReLU variants; its new performance is then vigorously tested on legacy samples like the Luminous Red Galaxy (LRG) and Stripe-82 samples from SDSS, as well as modern galaxy samples like the Physics of the Accelerating Universe Survey (PAUS). This work focuses on testing the robustness of activation functions with respect to the choice of ANN architectures, particularly on its depth and width, in the context of galaxy photometric redshift estimation. Our upgraded algorithm, which we named ANNZ+, shows that the tanh and Leaky ReLU activation functions provide more consistent and stable results across deeper and wider architectures with > 1 per cent improvement in root-mean-square error ($\sigma_{\textrm{RMS}}$) and 68th percentile error ($\sigma_{68}$) when tested on SDSS data sets. While assessing its capabilities in handling high dimensional inputs, we achieved an improvement of 11 per cent in $\sigma_{\textrm{RMS}}$ and 6 per cent in $\sigma_{68}$ with the tanh activation function when tested on the 40-narrowband PAUS dataset; it even outperformed ANNZ2, its supposed successor, by 44 per cent in $\sigma_{\textrm{RMS}}$. This justifies the effort to upgrade the 20-year-old ANNZ, allowing it to remain viable and competitive within the photo-z community today. The updated algorithm ANNZ+ is publicly available at https://github.com/imdadmpt/ANNzPlus., Comment: 37 pages, 9 figures, submitted to JCAP

Automatic scene generation is an essential area of research with applications in robotics, recreation, visual representation, training and simulation, education, and more. This survey provides a comprehensive review of the current state-of-the-arts in automatic scene generation, focusing on techniques that leverage machine learning, deep learning, embedded systems, and natural language processing (NLP). We categorize the models into four main types: Variational Autoencoders (VAEs), Generative Adversarial Networks (GANs), Transformers, and Diffusion Models. Each category is explored in detail, discussing various sub-models and their contributions to the field. We also review the most commonly used datasets, such as COCO-Stuff, Visual Genome, and MS-COCO, which are critical for training and evaluating these models. Methodologies for scene generation are examined, including image-to-3D conversion, text-to-3D generation, UI/layout design, graph-based methods, and interactive scene generation. Evaluation metrics such as Frechet Inception Distance (FID), Kullback-Leibler (KL) Divergence, Inception Score (IS), Intersection over Union (IoU), and Mean Average Precision (mAP) are discussed in the context of their use in assessing model performance. The survey identifies key challenges and limitations in the field, such as maintaining realism, handling complex scenes with multiple objects, and ensuring consistency in object relationships and spatial arrangements. By summarizing recent advances and pinpointing areas for improvement, this survey aims to provide a valuable resource for researchers and practitioners working on automatic scene generation., Comment: 59 pages, 16 figures, 3 tables, 36 equations, 348 references

Food computing is both important and challenging in computer vision (CV). It significantly contributes to the development of CV algorithms due to its frequent presence in datasets across various applications, ranging from classification and instance segmentation to 3D reconstruction. The polymorphic shapes and textures of food, coupled with high variation in forms and vast multimodal information, including language descriptions and nutritional data, make food computing a complex and demanding task for modern CV algorithms. 3D food modeling is a new frontier for addressing food-related problems, due to its inherent capability to deal with random camera views and its straightforward representation for calculating food portion size. However, the primary hurdle in the development of algorithms for food object analysis is the lack of nutrition values in existing 3D datasets. Moreover, in the broader field of 3D research, there is a critical need for domain-specific test datasets. To bridge the gap between general 3D vision and food computing research, we propose MetaFood3D. This dataset consists of 637 meticulously labeled 3D food objects across 108 categories, featuring detailed nutrition information, weight, and food codes linked to a comprehensive nutrition database. The dataset emphasizes intra-class diversity and includes rich modalities such as textured mesh files, RGB-D videos, and segmentation masks. Experimental results demonstrate our dataset's significant potential for improving algorithm performance, highlight the challenging gap between video captures and 3D scanned data, and show the strength of the MetaFood3D dataset in high-quality data generation, simulation, and augmentation., Comment: Dataset is coming soon

Atmospheric gravity waves occur in the Earths atmosphere caused by an interplay between gravity and buoyancy forces. These waves have profound impacts on various aspects of the atmosphere, including the patterns of precipitation, cloud formation, ozone distribution, aerosols, and pollutant dispersion. Therefore, understanding gravity waves is essential to comprehend and monitor changes in a wide range of atmospheric behaviors. Limited studies have been conducted to identify gravity waves from satellite data using machine learning techniques. Particularly, without applying noise removal techniques, it remains an underexplored area of research. This study presents a novel kernel design aimed at identifying gravity waves within satellite images. The proposed kernel is seamlessly integrated into a deep convolutional neural network, denoted as gWaveNet. Our proposed model exhibits impressive proficiency in detecting images containing gravity waves from noisy satellite data without any feature engineering. The empirical results show our model outperforms related approaches by achieving over 98% training accuracy and over 94% test accuracy which is known to be the best result for gravity waves detection up to the time of this work. We open sourced our code at https://rb.gy/qn68ku., Comment: This paper has been accepted at the 27th International Conference on Pattern Recognition (ICPR) 2024

Sleep stages play an essential role in the identification of sleep patterns and the diagnosis of sleep disorders. In this study, we present an automated sleep stage classifier termed the Attentive Dilated Convolutional Neural Network (AttDiCNN), which uses deep learning methodologies to address challenges related to data heterogeneity, computational complexity, and reliable automatic sleep staging. We employed a force-directed layout based on the visibility graph to capture the most significant information from the EEG signals, representing the spatial-temporal features. The proposed network consists of three compositors: the Localized Spatial Feature Extraction Network (LSFE), the Spatio-Temporal-Temporal Long Retention Network (S2TLR), and the Global Averaging Attention Network (G2A). The LSFE is tasked with capturing spatial information from sleep data, the S2TLR is designed to extract the most pertinent information in long-term contexts, and the G2A reduces computational overhead by aggregating information from the LSFE and S2TLR. We evaluated the performance of our model on three comprehensive and publicly accessible datasets, achieving state-of-the-art accuracy of 98.56%, 99.66%, and 99.08% for the EDFX, HMC, and NCH datasets, respectively, yet maintaining a low computational complexity with 1.4 M parameters. The results substantiate that our proposed architecture surpasses existing methodologies in several performance metrics, thus proving its potential as an automated tool in clinical settings., Comment: In review to IEEEtrans NNLS; 15-pages main paper and 3-pages supplementary material

Fluorescence collection from individual emitters plays a key role in state detection and remote entanglement generation, fundamental functionalities in many quantum platforms. Planar photonics have been demonstrated for robust and scalable addressing of trapped-ion systems, motivating consideration of similar elements for the complementary challenge of photon collection. Here, using an argument from the reciprocity principle, we show that far-field photon collection efficiency can be simply expressed in terms of the fields associated with the collection optic at the emitter position alone. We calculate collection efficiencies into ideal paraxial and fully vectorial focused Gaussian modes parameterized in terms of focal waist, and further quantify the modest enhancements possible with more general beam profiles, establishing design requirements for efficient collection. Towards practical implementation, we design, fabricate, and characterize a diffractive collection element operating at $\lambda=397$ nm predicted to offer a total 0.25\% collection efficiency into a single waveguide mode. A more efficient design with more demanding fabrication requirements would offer $1.14\%$, and we indicate avenues to improved devices approaching the limits predicted for ideal beams. We point out a particularly simple integrated waveguide configuration for polarization-based remote entanglement generation enabled by integrated collection.

Mosquito-related diseases pose a significant threat to global public health, necessitating efficient and accurate mosquito classification for effective surveillance and control. This work presents an innovative approach to mosquito classification by leveraging state-of-the-art vision transformers and open-set learning techniques. A novel framework has been introduced that integrates Transformer-based deep learning models with comprehensive data augmentation and preprocessing methods, enabling robust and precise identification of ten mosquito species. The Swin Transformer model achieves the best performance for traditional closed-set learning with 99.80\% accuracy and 0.998 F1 score. The lightweight MobileViT technique attains an almost similar accuracy of 98.90\% with significantly reduced parameters and model complexities. Next, the applied deep learning models' adaptability and generalizability in a static environment have been enhanced by using new classes of data samples during the inference stage that have not been included in the training set. The proposed framework's ability to handle unseen classes like insects similar to mosquitoes, even humans, through open-set learning further enhances its practical applicability employing the OpenMax technique and Weibull distribution. The traditional CNN model, Xception, outperforms the latest transformer with higher accuracy and F1 score for open-set learning. The study's findings highlight the transformative potential of advanced deep-learning architectures in entomology, providing a strong groundwork for future research and development in mosquito surveillance and vector control. The implications of this work extend beyond mosquito classification, offering valuable insights for broader ecological and environmental monitoring applications., Comment: 23 pages, 15 figures

Bug report management is a costly software maintenance process comprised of several challenging tasks. Given the UI-driven nature of mobile apps, bugs typically manifest through the UI, hence the identification of buggy UI screens and UI components (Buggy UI Localization) is important to localizing the buggy behavior and eventually fixing it. However, this task is challenging as developers must reason about bug descriptions (which are often low-quality), and the visual or code-based representations of UI screens. This paper is the first to investigate the feasibility of automating the task of Buggy UI Localization through a comprehensive study that evaluates the capabilities of one textual and two multi-modal deep learning (DL) techniques and one textual unsupervised technique. We evaluate such techniques at two levels of granularity, Buggy UI Screen and UI Component localization. Our results illustrate the individual strengths of models that make use of different representations, wherein models that incorporate visual information perform better for UI screen localization, and models that operate on textual screen information perform better for UI component localization -- highlighting the need for a localization approach that blends the benefits of both types of techniques. Furthermore, we study whether Buggy UI Localization can improve traditional buggy code localization, and find that incorporating localized buggy UIs leads to improvements of 9%-12% in Hits@10., Comment: 11 pages and 6 figures. To appear in ISSTA'24

Machine learning models have the potential to identify cardiovascular diseases (CVDs) early and accurately in primary healthcare settings, which is crucial for delivering timely treatment and management. Although population-based CVD risk models have been used traditionally, these models often do not consider variations in lifestyles, socioeconomic conditions, or genetic predispositions. Therefore, we aimed to develop machine learning models for CVD detection using primary healthcare data, compare the performance of different models, and identify the best models. We used data from the UK Biobank study, which included over 500,000 middle-aged participants from different primary healthcare centers in the UK. Data collected at baseline (2006--2010) and during imaging visits after 2014 were used in this study. Baseline characteristics, including sex, age, and the Townsend Deprivation Index, were included. Participants were classified as having CVD if they reported at least one of the following conditions: heart attack, angina, stroke, or high blood pressure. Cardiac imaging data such as electrocardiogram and echocardiography data, including left ventricular size and function, cardiac output, and stroke volume, were also used. We used 9 machine learning models (LSVM, RBFSVM, GP, DT, RF, NN, AdaBoost, NB, and QDA), which are explainable and easily interpretable. We reported the accuracy, precision, recall, and F-1 scores; confusion matrices; and area under the curve (AUC) curves., Comment: 19 pages, 3 figures

We provide a general method for constructing moduli stacks whose points are diagrams of vector bundles over a fixed base, indexed by a fixed simplicial set -- that is, quiver bundles of a fixed shape. We discuss some constraints on the base for these moduli stacks to be algebraic and observe that a large class of interesting schemes satisfy these constraints. Using this construction, we provide an alternate construction of moduli stacks of Higgs bundles along with a proof of algebraicity following readily from the algebraicity of moduli stacks of quiver bundles. One feature of our approach is that, for each of the moduli stacks we discuss, there are algebraic moduli stacks parametrizing morphisms of the objects being classified. We discuss some potential applications of this in categorifying non-abelian Hodge theory in a sense we will make precise. We also discuss potential applications of our methods and perspectives to the subjects of quiver modifications, abstract moduli theory, and homotopy theory., Comment: 32 pages

The increasing interest in computer vision applications for nutrition and dietary monitoring has led to the development of advanced 3D reconstruction techniques for food items. However, the scarcity of high-quality data and limited collaboration between industry and academia have constrained progress in this field. Building on recent advancements in 3D reconstruction, we host the MetaFood Workshop and its challenge for Physically Informed 3D Food Reconstruction. This challenge focuses on reconstructing volume-accurate 3D models of food items from 2D images, using a visible checkerboard as a size reference. Participants were tasked with reconstructing 3D models for 20 selected food items of varying difficulty levels: easy, medium, and hard. The easy level provides 200 images, the medium level provides 30 images, and the hard level provides only 1 image for reconstruction. In total, 16 teams submitted results in the final testing phase. The solutions developed in this challenge achieved promising results in 3D food reconstruction, with significant potential for improving portion estimation for dietary assessment and nutritional monitoring. More details about this workshop challenge and access to the dataset can be found at https://sites.google.com/view/cvpr-metafood-2024., Comment: Technical report for MetaFood CVPR 2024 Challenge on Physically Informed 3D Food Reconstruction. arXiv admin note: substantial text overlap with arXiv:2407.01717

Seams are areas of overlapping fabric formed by stitching two or more pieces of fabric together in the cut-and-sew apparel manufacturing process. In SeamPose, we repurposed seams as capacitive sensors in a shirt for continuous upper-body pose estimation. Compared to previous all-textile motion-capturing garments that place the electrodes on the clothing surface, our solution leverages existing seams inside of a shirt by machine-sewing insulated conductive threads over the seams. The unique invisibilities and placements of the seams afford the sensing shirt to look and wear similarly as a conventional shirt while providing exciting pose-tracking capabilities. To validate this approach, we implemented a proof-of-concept untethered shirt with 8 capacitive sensing seams. With a 12-participant user study, our customized deep-learning pipeline accurately estimates the relative (to the pelvis) upper-body 3D joint positions with a mean per joint position error (MPJPE) of 6.0 cm. SeamPose represents a step towards unobtrusive integration of smart clothing for everyday pose estimation.

Self-recording eating behaviors is a step towards a healthy lifestyle recommended by many health professionals. However, the current practice of manually recording eating activities using paper records or smartphone apps is often unsustainable and inaccurate. Smart glasses have emerged as a promising wearable form factor for tracking eating behaviors, but existing systems primarily identify when eating occurs without capturing details of the eating activities (E.g., what is being eaten). In this paper, we present EchoGuide, an application and system pipeline that leverages low-power active acoustic sensing to guide head-mounted cameras to capture egocentric videos, enabling efficient and detailed analysis of eating activities. By combining active acoustic sensing for eating detection with video captioning models and large-scale language models for retrieval augmentation, EchoGuide intelligently clips and analyzes videos to create concise, relevant activity records on eating. We evaluated EchoGuide with 9 participants in naturalistic settings involving eating activities, demonstrating high-quality summarization and significant reductions in video data needed, paving the way for practical, scalable eating activity tracking., Comment: Accepted at ISWC '24

Smart glasses have become more prevalent as they provide an increasing number of applications for users. They store various types of private information or can access it via connections established with other devices. Therefore, there is a growing need for user identification on smart glasses. In this paper, we introduce a low-power and minimally-obtrusive system called SonicID, designed to authenticate users on glasses. SonicID extracts unique biometric information from users by scanning their faces with ultrasonic waves and utilizes this information to distinguish between different users, powered by a customized binary classifier with the ResNet-18 architecture. SonicID can authenticate users by scanning their face for 0.06 seconds. A user study involving 40 participants confirms that SonicID achieves a true positive rate of 97.4%, a false positive rate of 4.3%, and a balanced accuracy of 96.6% using just 1 minute of training data collected for each new user. This performance is relatively consistent across different remounting sessions and days. Given this promising performance, we further discuss the potential applications of SonicID and methods to improve its performance in the future., Comment: 28 pages, 6 tables, 9 figures

Recent advances in pre-trained vision transformers have shown promise in parameter-efficient audio-visual learning without audio pre-training. However, few studies have investigated effective methods for aligning multimodal features in parameter-efficient audio-visual transformers. In this paper, we propose MA-AVT, a new parameter-efficient audio-visual transformer employing deep modality alignment for corresponding multimodal semantic features. Specifically, we introduce joint unimodal and multimodal token learning for aligning the two modalities with a frozen modality-shared transformer. This allows the model to learn separate representations for each modality, while also attending to the cross-modal relationships between them. In addition, unlike prior work that only aligns coarse features from the output of unimodal encoders, we introduce blockwise contrastive learning to align coarse-to-fine-grain hierarchical features throughout the encoding phase. Furthermore, to suppress the background features in each modality from foreground matched audio-visual features, we introduce a robust discriminative foreground mining scheme. Through extensive experiments on benchmark AVE, VGGSound, and CREMA-D datasets, we achieve considerable performance improvements over SOTA methods., Comment: Accepted in Efficient Deep Learning for Computer Vision CVPR Workshop 2024

Video-to-video synthesis models face significant challenges, such as ensuring consistent character generation across frames, maintaining smooth temporal transitions, and preserving quality during fast motion. The introduction of joint fully cross-frame self-attention mechanisms has improved character consistency, but this comes at the cost of increased computational complexity. This full cross-frame self-attention mechanism also incorporates redundant details and limits the number of frames that can be jointly edited due to its computational cost. Moreover, the lack of frames in cross-frame attention adversely affects temporal consistency and visual quality. To address these limitations, we propose a new adaptive motion-guided cross-frame attention mechanism that drastically reduces complexity while preserving semantic details and temporal consistency. Specifically, we selectively incorporate the moving regions of successive frames in cross-frame attention and sparsely include stationary regions based on optical flow sampling. This technique allows for an increased number of jointly edited frames without additional computational overhead. For longer duration of video editing, existing methods primarily focus on frame interpolation or flow-warping from jointly edited keyframes, which often results in blurry frames or reduced temporal consistency. To improve this, we introduce KV-caching of jointly edited frames and reuse the same KV across all intermediate frames, significantly enhancing both intermediate frame quality and temporal consistency. Overall, our motion-sampling method enables the use of around three times more keyframes than existing joint editing methods while maintaining superior prediction quality. Ada-VE achieves up to 4x speed-up when using fully-extended self-attention across 40 frames for joint editing, without compromising visual quality or temporal consistency., Comment: Tech Report

We compute the energy scales of perturbative unitarity violation in $V_L V_L \to V_L V_L h$ processes and compare them to $V_L V_L \to hhh$ process, where $V_L$ refers to a longitudinal mode of $Z$ or $W$ boson, and $h$ the Higgs boson. Using these energy scales, we determine which process is more sensitive to potential modifications in the Higgs sector at high-energy colliders. Within the Higgs Effective Field Theory (HEFT), we consider the Higgs cubic coupling and other interactions with and without derivatives. Any HEFT interactions predict the perturbative unitarity violation at a finite scale, and in a generic case, the minimalistic process is $2\to 3$ scattering. Our analysis reveals that the energy scales for unitarity violation in $V_L V_L \to V_L V_L h$ and $V_L V_L \to hhh$ processes are similar across all scenarios considered. If the backgrounds are similar, $V_L V_L h$ final states are more feasible because $V_L V_L h$ has higher branching ratios in cleaner decay modes than $hhh$. We also investigate HEFT derivative interactions derived from various UV models. In these cases, both $V_L V_L \to V_L V_L$ and $V_L V_L \to hh$ processes exhibit unitarity violating behavior. We demonstrate that the energy scales for unitarity violation in $V_L V_L$ final states are comparable to or even lower than those in the $hh$ final state., Comment: 28 pages, 3 tables, 7 figures, 5 appendices. v2: Journal version; added references, corrected equations, and minor text changes

We introduce MunchSonic, an AI-powered active acoustic sensing system integrated into eyeglasses to track fine-grained dietary actions. MunchSonic emits inaudible ultrasonic waves from the eyeglass frame, with the reflected signals capturing detailed positions and movements of body parts, including the mouth, jaw, arms, and hands involved in eating. These signals are processed by a deep learning pipeline to classify six actions: hand-to-mouth movements for food intake, chewing, drinking, talking, face-hand touching, and other activities (null). In an unconstrained study with 12 participants, MunchSonic achieved a 93.5% macro F1-score in a user-independent evaluation with a 2-second resolution in tracking these actions, also demonstrating its effectiveness in tracking eating episodes and food intake frequency within those episodes., Comment: 8 pages, 7 figures

Policy decisions often depend on evidence generated elsewhere. We take a Bayesian decision-theoretic approach to choosing where to experiment to optimize external validity. We frame external validity through a policy lens, developing a prior specification for the joint distribution of site-level treatment effects using a microeconometric structural model and allowing for other sources of heterogeneity. With data from South Asia, we show that, relative to basing policies on experiments in optimal sites, large efficiency losses result from instead using evidence from randomly-selected sites or, conversely, from sites with the largest expected treatment effects.

TripAdvisor reviews and comparable data sources play an important role in many tasks in Natural Language Processing (NLP), providing a data basis for the identification and classification of subjective judgments, such as hotel or restaurant reviews, into positive or negative polarities. This study explores three important factors influencing variation in crowdsourced polarity judgments, focusing on TripAdvisor reviews in Spanish. Three hypotheses are tested: the role of Part Of Speech (POS), the impact of sentiment words such as "tasty", and the influence of neutral words like "ok" on judgment variation. The study's methodology employs one-word titles, demonstrating their efficacy in studying polarity variation of words. Statistical tests on mean equality are performed on word groups of our interest. The results of this study reveal that adjectives in one-word titles tend to result in lower judgment variation compared to other word types or POS. Sentiment words contribute to lower judgment variation as well, emphasizing the significance of sentiment words in research on polarity judgments, and neutral words are associated with higher judgment variation as expected. However, these effects cannot be always reproduced in longer titles, which suggests that longer titles do not represent the best data source for testing the ambiguity of single words due to the influence on word polarity by other words like negation in longer titles. This empirical investigation contributes valuable insights into the factors influencing polarity variation of words, providing a foundation for NLP practitioners that aim to capture and predict polarity judgments in Spanish and for researchers that aim to understand factors influencing judgment variation., Comment: Accepted manuscript to be published in PLoS One

Code-mixing is a well-studied linguistic phenomenon that occurs when two or more languages are mixed in text or speech. Several studies have been conducted on building datasets and performing downstream NLP tasks on code-mixed data. Although it is not uncommon to observe code-mixing of three or more languages, most available datasets in this domain contain code-mixed data from only two languages. In this paper, we introduce EmoMix-3L, a novel multi-label emotion detection dataset containing code-mixed data from three different languages. We experiment with several models on EmoMix-3L and we report that MuRIL outperforms other models on this dataset., Comment: arXiv admin note: substantial text overlap with arXiv:2310.18387, arXiv:2310.18023

Quantum machine learning (QML) is a promising early use case for quantum computing. There has been progress in the last five years from theoretical studies and numerical simulations to proof of concepts. Use cases demonstrated on contemporary quantum devices include classifying medical images and items from the Iris dataset, classifying and generating handwritten images, toxicity screening, and learning a probability distribution. Potential benefits of QML include faster training and identification of feature maps not found classically. Although, these examples lack the scale for commercial exploitation, and it may be several years before QML algorithms replace the classical solutions, QML is an exciting area. This article is written for those who already have a sound knowledge of quantum computing and now wish to gain a basic overview of the terminology and some applications of classical machine learning ready to study quantum machine learning. The reader will already understand the relevant relevant linear algebra, including Hilbert spaces, a vector space with an inner product., Comment: 32 pages, 21 figures, technical report

In today's world, image processing plays a crucial role across various fields, from scientific research to industrial applications. But one particularly exciting application is image captioning. The potential impact of effective image captioning is vast. It can significantly boost the accuracy of search engines, making it easier to find relevant information. Moreover, it can greatly enhance accessibility for visually impaired individuals, providing them with a more immersive experience of digital content. However, despite its promise, image captioning presents several challenges. One major hurdle is extracting meaningful visual information from images and transforming it into coherent language. This requires bridging the gap between the visual and linguistic domains, a task that demands sophisticated algorithms and models. Our project is focused on addressing these challenges by developing an automatic image captioning architecture that combines the strengths of convolutional neural networks (CNNs) and encoder-decoder models. The CNN model is used to extract the visual features from images, and later, with the help of the encoder-decoder framework, captions are generated. We also did a performance comparison where we delved into the realm of pre-trained CNN models, experimenting with multiple architectures to understand their performance variations. In our quest for optimization, we also explored the integration of frequency regularization techniques to compress the "AlexNet" and "EfficientNetB0" model. We aimed to see if this compressed model could maintain its effectiveness in generating image captions while being more resource-efficient.

We present a novel multimodal dataset for Cognitive Load Assessment in REaltime (CLARE). The dataset contains physiological and gaze data from 24 participants with self-reported cognitive load scores as ground-truth labels. The dataset consists of four modalities, namely, Electrocardiography (ECG), Electrodermal Activity (EDA), Electroencephalogram (EEG), and Gaze tracking. To map diverse levels of mental load on participants during experiments, each participant completed four nine-minutes sessions on a computer-based operator performance and mental workload task (the MATB-II software) with varying levels of complexity in one minute segments. During the experiment, participants reported their cognitive load every 10 seconds. For the dataset, we also provide benchmark binary classification results with machine learning and deep learning models on two different evaluation schemes, namely, 10-fold and leave-one-subject-out (LOSO) cross-validation. Benchmark results show that for 10-fold evaluation, the convolutional neural network (CNN) based deep learning model achieves the best classification performance with ECG, EDA, and Gaze. In contrast, for LOSO, the best performance is achieved by the deep learning model with ECG, EDA, and EEG., Comment: 12 pages, 10 figures, 6 tables

This paper presents the phase stability, opto-electronic and thermo-electric behavior of X2AuYZ6 (X = Cs, Rb; Z = Cl/Br/I) double perovskite halides by using the DFT method. The compounds belong to the cubic arrangement and are verified by the tolerance and octahedral factor. Formation enthalpy and binding energy meet the requirements of structural stability. The ductility behavior was also confirmed by the Cauchy pressure, Pugh's ratio, and Poisson's ratio. The positive frequency of phonon dispersion except Rb2AuYI6 compound shows the dynamical stability and the negative formation energy of each identified competing phase confirms the thermo-dynamic equilibrium of all compounds. The band gap values of 2.85(2.91), 2.35(2.40), and 1.74(1.78) eV of Cs2AuYZ6 (Rb2AuYZ6) [Z = Cl, Br, I) double perovskites has been explored in the context of optoelectronic properties, and the results show that these materials might be useful in such devices. The spectral optical response covers the visible-to-UV area, which governs the solar cell and thermo-electric device applications. A comprehensive study of thermo-electric properties such as the thermal conductivity (electrical and electronic part), carrier concentration, thermo-power, and figure of merit was also observed. The investigated compounds [Cs (Rb)-based] exhibit ZT values of 0.51(0.55), 0.53(0.62), and 0.58(0.75) at room temperature with Cl, Br, and I respectively. Additional routine work was also done on the thermo-mechanical characteristics. These studies provide in-depth knowledge of these materials in preparation for their future use.

We present ActSonic, an intelligent, low-power active acoustic sensing system integrated into eyeglasses that can recognize 27 different everyday activities (e.g., eating, drinking, toothbrushing) from inaudible acoustic waves around the body with a time resolution of one second. It only needs a pair of miniature speakers and microphones mounted on each hinge of eyeglasses to emit ultrasonic waves to create an acoustic aura around the body. Based on the position and motion of various body parts, the acoustic signals are reflected with unique patterns captured by the microphone and analyzed by a customized self-supervised deep learning framework to infer the performed activities. ActSonic was deployed in a user study with 19 participants across 19 households to evaluate its efficacy. Without requiring any training data from a new user (leave-one-participant-out evaluation), ActSonic was able to detect 27 activities, achieving an average F1-score of 86.6% in fully unconstrained scenarios and 93.4% in prompted settings at participants' homes., Comment: 29 pages, 11 figures

Image classification is a fundamental task in computer vision, and the quest to enhance DNN accuracy without inflating model size or latency remains a pressing concern. We make a couple of advances in this regard, leading to a novel EncodeNet design and training framework. The first advancement involves Converting Autoencoders, a novel approach that transforms images into an easy-to-classify image of its class. Our prior work that applied the Converting Autoencoder and a simple classifier in tandem achieved moderate accuracy over simple datasets, such as MNIST and FMNIST. However, on more complex datasets like CIFAR-10, the Converting Autoencoder has a large reconstruction loss, making it unsuitable for enhancing DNN accuracy. To address these limitations, we generalize the design of Converting Autoencoders by leveraging a larger class of DNNs, those with architectures comprising feature extraction layers followed by classification layers. We incorporate a generalized algorithmic design of the Converting Autoencoder and intraclass clustering to identify representative images, leading to optimized image feature learning. Next, we demonstrate the effectiveness of our EncodeNet design and training framework, improving the accuracy of well-trained baseline DNNs while maintaining the overall model size. EncodeNet's building blocks comprise the trained encoder from our generalized Converting Autoencoders transferring knowledge to a lightweight classifier network - also extracted from the baseline DNN. Our experimental results demonstrate that EncodeNet improves the accuracy of VGG16 from 92.64% to 94.05% on CIFAR-10 and RestNet20 from 74.56% to 76.04% on CIFAR-100. It outperforms state-of-the-art techniques that rely on knowledge distillation and attention mechanisms, delivering higher accuracy for models of comparable size., Comment: 15 pages

Deepfake technology, derived from deep learning, seamlessly inserts individuals into digital media, irrespective of their actual participation. Its foundation lies in machine learning and Artificial Intelligence (AI). Initially, deepfakes served research, industry, and entertainment. While the concept has existed for decades, recent advancements render deepfakes nearly indistinguishable from reality. Accessibility has soared, empowering even novices to create convincing deepfakes. However, this accessibility raises security concerns.The primary deepfake creation algorithm, GAN (Generative Adversarial Network), employs machine learning to craft realistic images or videos. Our objective is to utilize CNN (Convolutional Neural Network) and CapsuleNet with LSTM to differentiate between deepfake-generated frames and originals. Furthermore, we aim to elucidate our model's decision-making process through Explainable AI, fostering transparent human-AI relationships and offering practical examples for real-life scenarios.

We present Ring-a-Pose, a single untethered ring that tracks continuous 3D hand poses. Located in the center of the hand, the ring emits an inaudible acoustic signal that each hand pose reflects differently. Ring-a-Pose imposes minimal obtrusions on the hand, unlike multi-ring or glove systems. It is not affected by the choice of clothing that may cover wrist-worn systems. In a series of three user studies with a total of 30 participants, we evaluate Ring-a-Pose's performance on pose tracking and micro-finger gesture recognition. Without collecting any training data from a user, Ring-a-Pose tracks continuous hand poses with a joint error of 14.1mm. The joint error decreases to 10.3mm for fine-tuned user-dependent models. Ring-a-Pose recognizes 7-class micro-gestures with a 90.60% and 99.27% accuracy for user-independent and user-dependent models, respectively. Furthermore, the ring exhibits promising performance when worn on any finger. Ring-a-Pose enables the future of smart rings to track and recognize hand poses using relatively low-power acoustic sensing.

The Machine learning (ML) is a rapidly evolving field of technology that has the potential to greatly impact society in a variety of ways. However, there are also concerns about the potential negative effects of ML on society, such as job displacement and privacy issues. This research aimed to conduct a comprehensive analysis of the current and future impact of ML on society. The research included a thorough literature review, case studies, and surveys to gather data on the economic impact of ML, ethical and privacy implications, and public perceptions of the technology. The survey was conducted on 150 respondents from different areas. The case studies conducted were on the impact of ML on healthcare, finance, transportation, and manufacturing. The findings of this research revealed that the majority of respondents have a moderate level of familiarity with the concept of ML, believe that it has the potential to benefit society, and think that society should prioritize the development and use of ML. Based on these findings, it was recommended that more research is conducted on the impact of ML on society, stronger regulations and laws to protect the privacy and rights of individuals when it comes to ML should be developed, transparency and accountability in ML decision-making processes should be increased, and public education and awareness about ML should be enhanced., Comment: 12 pages

Ocean eddies play a significant role both on the sea surface and beneath it, contributing to the sustainability of marine life dependent on oceanic behaviors. Therefore, it is crucial to investigate ocean eddies to monitor changes in the Earth, particularly in the oceans, and their impact on climate. This study aims to pinpoint ocean eddies using AWS cloud services, specifically SageMaker. The primary objective is to detect small-scale (<20km) ocean eddies from satellite remote images and assess the feasibility of utilizing SageMaker, which offers tools for deploying AI applications. Moreover, this research not only explores the deployment of cloud-based services for remote sensing of Earth data but also evaluates several YOLO (You Only Look Once) models using single and multi-GPU-based services in the cloud. Furthermore, this study underscores the potential of these services, their limitations, challenges related to deployment and resource management, and their user-riendliness for Earth science projects., Comment: 10 pages

Visual sound source localization poses a significant challenge in identifying the semantic region of each sounding source within a video. Existing self-supervised and weakly supervised source localization methods struggle to accurately distinguish the semantic regions of each sounding object, particularly in multi-source mixtures. These methods often rely on audio-visual correspondence as guidance, which can lead to substantial performance drops in complex multi-source localization scenarios. The lack of access to individual source sounds in multi-source mixtures during training exacerbates the difficulty of learning effective audio-visual correspondence for localization. To address this limitation, in this paper, we propose incorporating the text modality as an intermediate feature guide using tri-modal joint embedding models (e.g., AudioCLIP) to disentangle the semantic audio-visual source correspondence in multi-source mixtures. Our framework, dubbed T-VSL, begins by predicting the class of sounding entities in mixtures. Subsequently, the textual representation of each sounding source is employed as guidance to disentangle fine-grained audio-visual source correspondence from multi-source mixtures, leveraging the tri-modal AudioCLIP embedding. This approach enables our framework to handle a flexible number of sources and exhibits promising zero-shot transferability to unseen classes during test time. Extensive experiments conducted on the MUSIC, VGGSound, and VGGSound-Instruments datasets demonstrate significant performance improvements over state-of-the-art methods. Code is released at https://github.com/enyac-group/T-VSL/tree/main, Comment: Accepted in CVPR-2024. Code: https://github.com/enyac-group/T-VSL/tree/main

Conditional sound separation in multi-source audio mixtures without having access to single source sound data during training is a long standing challenge. Existing mix-and-separate based methods suffer from significant performance drop with multi-source training mixtures due to the lack of supervision signal for single source separation cases during training. However, in the case of language-conditional audio separation, we do have access to corresponding text descriptions for each audio mixture in our training data, which can be seen as (rough) representations of the audio samples in the language modality. To this end, in this paper, we propose a generic bi-modal separation framework which can enhance the existing unsupervised frameworks to separate single-source signals in a target modality (i.e., audio) using the easily separable corresponding signals in the conditioning modality (i.e., language), without having access to single-source samples in the target modality during training. We empirically show that this is well within reach if we have access to a pretrained joint embedding model between the two modalities (i.e., CLAP). Furthermore, we propose to incorporate our framework into two fundamental scenarios to enhance separation performance. First, we show that our proposed methodology significantly improves the performance of purely unsupervised baselines by reducing the distribution shift between training and test samples. In particular, we show that our framework can achieve 71% boost in terms of Signal-to-Distortion Ratio (SDR) over the baseline, reaching 97.5% of the supervised learning performance. Second, we show that we can further improve the performance of the supervised learning itself by 17% if we augment it by our proposed weakly-supervised framework, that enables a powerful semi-supervised framework for audio separation., Comment: Tech report. Accepted in ICLR-2024

With an aim to build analog computers out of soft matter fluidic systems in future, this work attempts to invent a new information-theoretic language, in the form of two-dimensional Quick Response (QR) codes. This language is, effectively, a digital representation of the analog signals shown by the proteinoids. We use two different experimental techniques: (i) a voltage-sensitive dye and (ii) a pair of differential electrodes, to record the analog signals. The analog signals are digitally approximatied (synthesised) by sampling the analog signals into a series of discrete values, which are then converted into binary representations. We have shown the AND-OR-NOT-XOR-NOR-NAND-XNOR gate representation of the digitally sampled signal of proteinoids. Additional encoding schemes are applied to convert the binary code identified above to a two-dimensional QR code. As a result, the QR code becomes a digital, unique marker of a given proteinoid network. We show that it is possible to retrieve the analog signal from the QR code by scanning the QR code using a mobile phone. Our work shows that soft matter fluidic systems, such as proteinoids, can have a fundamental informatiom-theoretic language, unique to their internal information transmission properties (electrical activity in this case) - such a language can be made universal and accessible to everyone using 2D QR codes, which can digitally encode their internal properties and give an option to recover the original signal when required. On a more fundamental note, this study identifies the techniques of approximating continuum properties of soft matter fluidic systems using a series representation of gates and QR codes, which are a piece-wise digital representation, and thus one step closer to programming the fluids using information-theoretic methods, as suggested almost a decade ago by Tao's fluid program., Comment: 7 pages, 5 figures