Recent advancements in vision-language models have achieved remarkable results in making language models understand vision inputs. However, a unified approach to align these models across diverse tasks such as image captioning and visual question answering remains a challenge. Existing methods either require very big language models or very big datasets which is not efficient in utilizing existing models. This paper addresses this gap and devises a training strategy of auto-regressive vision-language models, to unify vision-language tasks like image-captioning and visual question answering. We propose four training stages for aligning the vision model with the language model, in other words, the language model is given an ability to process visual inputs. We also devise different attention masks for training transformer-based language models that improve the quality of visual features. Further, we introduce some findings, 1) the attention mask should not be applied on visual inputs, 2) the Language model converges faster on AI- generated data, 3) More work should be done in the alignment stage during the pre-training of the model, 4) the model can easily adapt to any downstream tasks like visual question answering on healthcare datasets like PathVQA. After training the model for one epoch for all the stages, it outperforms large models like VILA-13 billion models on common benchmarks like CIDEr scores on COCO and Flickr30k datasets and achieves very close scores to GIT-2 on the same dataset despite being a much smaller model trained on a much smaller dataset. All of the training is done using best practices available like multi- GPU parallel training, lower-precision training with 16-bit float numbers, faster attention (SDPA), and gradient accumulation, and completed the training within 12 hours.

In this paper, we study the late time cosmic acceleration of the Quintessence model within the framework of Hoyle Narlikar Gravity, consisting of a creation field. Using the Hubble tension as a function of the density parameter for matter, the density parameter for radiation, and the density parameter for dark energy in the covariant formulation, we find the gravitational field equations in the spatially flat, homogeneous, and isotropic spacetime to examine the dynamical mechanism that leads to cosmic acceleration in the late-time universe. We analyze the observational constraints on the late-time density parameters using various recent observational datasets, including the Hubble datasets, Pantheon+, and joint compilation, Pantheon++BAO. Consequently, it is explicitly demonstrated that late-time cosmic acceleration can be consistent with recent observational data in Hoyle Narlikar Gravity with non-minimal matter interaction. In contrast with other modified theories of gravity, it is observed that the creation field theory with non-minimal matter interaction renders more compact constraints on the Hubble tension together with density parameters, and extensively explains the accelerating expansion of the universe, which makes it a more plausible option compared to the {\Lambda}CDM model. Furthermore, the w dw phase analysis confirms alternating thawing and freezing behaviour of the model, with all trajectories ultimately converging toward the {\Lambda}CDM point, thereby confirming the model stability and the observational consistency.

Flavor is expressed through interaction of molecules via gustatory and olfactory mechanisms. Knowing the utility of flavor molecules in food and fragrances, it is valuable to add a comprehensive repository of flavor compounds characterizing their flavor profile, chemical properties, regulatory status, consumption statistics, taste/aroma threshold values, reported uses in food categories, and synthesis. FlavorDB2 (this https URL) is an updated database of flavor molecules with an user-friendly interface. This repository simplifies the search for flavor molecules, their attributes and offers a range of applications including food pairing. FlavorDB2 serves as a standard repository of flavor compounds.

Small object detection in aerial imagery presents significant challenges in computer vision due to the minimal data inherent in small-sized objects and their propensity to be obscured by larger objects and background noise. Traditional methods using transformer-based models often face limitations stemming from the lack of specialized databases, which adversely affect their performance with objects of varying orientations and scales. This underscores the need for more adaptable, lightweight models. In response, this paper introduces two innovative approaches that significantly enhance detection and segmentation capabilities for small aerial objects. Firstly, we explore the use of the SAHI framework on the newly introduced lightweight YOLO v9 architecture, which utilizes Programmable Gradient Information (PGI) to reduce the substantial information loss typically encountered in sequential feature extraction processes. The paper employs the Vision Mamba model, which incorporates position embeddings to facilitate precise location-aware visual understanding, combined with a novel bidirectional State Space Model (SSM) for effective visual context modeling. This State Space Model adeptly harnesses the linear complexity of CNNs and the global receptive field of Transformers, making it particularly effective in remote sensing image classification. Our experimental results demonstrate substantial improvements in detection accuracy and processing efficiency, validating the applicability of these approaches for real-time small object detection across diverse aerial scenarios. This paper also discusses how these methodologies could serve as foundational models for future advancements in aerial object recognition technologies. The source code will be made accessible here.

Deepfake is a widely used technology employed in recent years to create pernicious content such as fake news, movies, and rumors by altering and substituting facial information from various sources. Given the ongoing evolution of deepfakes investigation of continuous identification and prevention is crucial. Due to recent technological advancements in AI (Artificial Intelligence) distinguishing deepfakes and artificially altered images has become challenging. This approach introduces the robust detection of subtle ear movements and shape changes to generate ear descriptors. Further, we also propose a novel optimized hybrid deepfake detection model that considers the ear biometric descriptors via enhanced RCNN (Region-Based Convolutional Neural Network). Initially, the input video is converted into frames and preprocessed through resizing, normalization, grayscale conversion, and filtering processes followed by face detection using the Viola-Jones technique. Next, a hybrid model comprising DBN (Deep Belief Network) and Bi-GRU (Bidirectional Gated Recurrent Unit) is utilized for deepfake detection based on ear descriptors. The output from the detection phase is determined through improved score-level fusion. To enhance the performance, the weights of both detection models are optimally tuned using the SU-JFO (Self-Upgraded Jellyfish Optimization method). Experimentation is conducted based on four scenarios: compression, noise, rotation, pose, and illumination on three different datasets. The performance results affirm that our proposed method outperforms traditional models such as CNN (Convolution Neural Network), SqueezeNet, LeNet, LinkNet, LSTM (Long Short-Term Memory), DFP (Deepfake Predictor) [1], and ResNext+CNN+LSTM [2] in terms of various performance metrics viz. accuracy, specificity, and precision.

Diabetic Retinopathy (DR), a prevalent complication in diabetes patients, can lead to vision impairment due to lesions formed on the retina. Detecting DR at an advanced stage often results in irreversible blindness. The traditional process of diagnosing DR through retina fundus images by ophthalmologists is not only time-intensive but also expensive. While classical transfer learning models have been widely adopted for computer-aided detection of DR, their high maintenance costs can hinder their detection efficiency. In contrast, Quantum Transfer Learning offers a more effective solution to this challenge. This approach is notably advantageous because it operates on heuristic principles, making it highly optimized for the task. Our proposed methodology leverages this hybrid quantum transfer learning technique to detect DR. To construct our model, we utilize the APTOS 2019 Blindness Detection dataset, available on Kaggle. We employ the ResNet-18, ResNet34, ResNet50, ResNet101, ResNet152 and Inception V3, pre-trained classical neural networks, for the initial feature extraction. For the classification stage, we use a Variational Quantum Classifier. Our hybrid quantum model has shown remarkable results, achieving an accuracy of 97% for ResNet-18. This demonstrates that quantum computing, when integrated with quantum machine learning, can perform tasks with a level of power and efficiency unattainable by classical computers alone. By harnessing these advanced technologies, we can significantly improve the detection and diagnosis of Diabetic Retinopathy, potentially saving many from the risk of blindness. Keywords: Diabetic Retinopathy, Quantum Transfer Learning, Deep Learning

This paper addresses the challenges of face attribute detection specifically in the Indian context. While there are numerous face datasets in unconstrained environments, none of them captures emotions in different face orientations. Moreover, there is an under-representation of people of Indian ethnicity in these datasets since they have been scraped from popular search engines. As a result, the performance of state-of-the-art techniques can't be evaluated on Indian faces. In this work, we introduce a new dataset, IIITM Face, for the scientific community to address these challenges. Our dataset includes 107 participants who exhibit 6 emotions in 3 different face orientations. Each of these images is further labelled on attributes like gender, presence of moustache, beard or eyeglasses, clothes worn by the subjects and the density of their hair. Moreover, the images are captured in high resolution with specific background colors which can be easily replaced by cluttered backgrounds to simulate `in the Wild' behaviour. We demonstrate the same by constructing IIITM Face-SUE. Both IIITM Face and IIITM Face-SUE have been benchmarked across key multi-label metrics for the research community to compare their results.

This paper introduces a new semantic search algorithm that uses Word2Vec and Annoy Index to improve the efficiency of information retrieval from large datasets. The proposed approach addresses the limitations of traditional search methods by offering enhanced speed, accuracy, and scalability. Testing on datasets up to 100GB demonstrates the method's effectiveness in processing vast amounts of data while maintaining high precision and performance.

This paper presents the design and results of the "PEg TRAnsfert Workflow recognition" (PETRAW) challenge whose objective was to develop surgical workflow recognition methods based on one or several modalities, among video, kinematic, and segmentation data, in order to study their added value. The PETRAW challenge provided a data set of 150 peg transfer sequences performed on a virtual simulator. This data set was composed of videos, kinematics, semantic segmentation, and workflow annotations which described the sequences at three different granularity levels: phase, step, and activity. Five tasks were proposed to the participants: three of them were related to the recognition of all granularities with one of the available modalities, while the others addressed the recognition with a combination of modalities. Average application-dependent balanced accuracy (AD-Accuracy) was used as evaluation metric to take unbalanced classes into account and because it is more clinically relevant than a frame-by-frame score. Seven teams participated in at least one task and four of them in all tasks. Best results are obtained with the use of the video and the kinematics data with an AD-Accuracy between 93% and 90% for the four teams who participated in all tasks. The improvement between video/kinematic-based methods and the uni-modality ones was significant for all of the teams. However, the difference in testing execution time between the video/kinematic-based and the kinematic-based methods has to be taken into consideration. Is it relevant to spend 20 to 200 times more computing time for less than 3% of improvement? The PETRAW data set is publicly available at www.synapse.org/PETRAW to encourage further research in surgical workflow recognition.

In the framework of $f(Q)$ gravity, where gravity emerges from non-metricity $Q$, we explore the cosmological implications of its non-minimal coupling to matter. Inspired by the recent success of Chaplygin gas models in explaining dark energy, we consider a background fluid composed of baryonic matter, radiation, and a family of Chaplygin gas variants namely Generalized Chaplygin Gas (GCG), Modified Chaplygin Gas (MCG), and Variable Chaplygin Gas (VCG). We constrain these models with three recent observational datasets: Observational Hubble Data (OHD), Baryonic Acoustic Oscillation (BAO) measurements, and Quasi-Stellar Objects (QSO) data. For the QSO dataset, we propose an analytical expression for errors in comoving distance to circumvent the reliance on Monte Carlo simulations. Using kinematic diagnostics such as the deceleration and jerk parameters and Om diagnostic, we assess deviations of the proposed models from $\Lambda$CDM. Our joint analysis of the three datasets reveals that the transition redshift from a decelerated to an accelerated expansion of the universe for the GCG, MCG and VCG models is $0.620^{+0.018}_{-0.017}$, $0.537^{+0.017}_{-0.017}$ and $0.470^{+0.012}_{-0.012}$ respectively, indicating a departure from $\Lambda$CDM.

We investigate the existence and multiplicity of positive solutions to the following problem driven by the superposition of the Laplacian and the fractional Laplacian with Hardy potential \begin{equation*} \left\{ \begin{aligned} -\Delta u + (-\Delta)^s u - \mu \frac{u}{|x|^2} &= \lambda |u|^{p-2} u + |u|^{2^*-2} u \quad \text{in } \Omega \subset \mathbb{R}^N, u &= 0 \quad \text{in } \mathbb{R}^N \setminus \Omega, \end{aligned} \right. \end{equation*} where $\Omega \subset \mathbb{R}^N$ is a bounded domain with smooth boundary, 0 < s < 1 , 1 < p < 2^* , with $2^* = \frac{2N}{N-2}$, \lambda > 0 , and $\mu \in (0, \bar{\mu})$ where $\bar \mu = \left( \frac{N-2}{2} \right)^2$. The aim of this paper is twofold. First, we establish uniform asymptotic estimates for solutions of the problem by means of a suitable transformation. Then, according to the value of the exponent $p$, we analyze three distinct cases and prove the existence of a positive solution. Moreover, in the sublinear regime 1 < p < 2, we demonstrate the existence of multiple positive solutions for small perturbations of the fractional Laplacian.

In this work, we have developed an FLRW type model of a universe which displays transition from deceleration in the past to the acceleration at the present. For this, we have considered field equations of $f(R,T)$ gravity and have taken $f(R,T) = R + 2 \lambda T$, $\lambda$ being an arbitrary constant. We have estimated the $\lambda$ parameter in such a way that the transition red shift is found similar in the deceleration parameter, pressure and the equation of state parameter $\omega$. The present value of Hubble parameter is estimated on the basis of the three types of observational data set: latest compilation of $46$ Hubble data set, SNe Ia $580$ data sets of distance modulus and $66$ Pantheon data set of apparent magnitude which comprised of 40 SN Ia binned and 26 high redshift data's in the range $0.014 \leq z \leq 2.26$. These data are compared with theoretical results through the $\chi^2$ statistical test. Interestingly, the model satisfies all the three weak, strong and dominant energy conditions. The model fits well with observational findings. We have discussed some of the physical aspects of the model, in particular the age of the universe.

Skin cancer is the most common human malignancy(American Cancer Society) which is primarily diagnosed visually, starting with an initial clinical screening and followed potentially by dermoscopic(related to skin) analysis, a biopsy and histopathological examination. Skin cancer occurs when errors (mutations) occur in the DNA of skin cells. The mutations cause the cells to grow out of control and form a mass of cancer cells. The aim of this study was to try to classify images of skin lesions with the help of convolutional neural networks. The deep neural networks show humongous potential for image classification while taking into account the large variability exhibited by the environment. Here we trained images based on the pixel values and classified them on the basis of disease labels. The dataset was acquired from an Open Source Kaggle Repository(Kaggle Dataset)which itself was acquired from ISIC(International Skin Imaging Collaboration) Archive. The training was performed on multiple models accompanied with Transfer Learning. The highest model accuracy achieved was over 86.65%. The dataset used is publicly available to ensure credibility and reproducibility of the aforementioned result.

In this article, we are concerned with the eigenvalue problem driven by the mixed local and nonlocal $p$-Laplacian operator having the interpolated Hardy term \begin{equation*} \mathcal{T}(u) :=- \Delta_p u + (- \Delta_p)^s u - \mu \frac{|u|^{p-2}u}{|x|^{p \theta}}, \end{equation*} where $0

The present study offers a general exponential operator connected with a^2+x^2; for positive real "a". We estimate the asymptotic formula for simultaneous and ordinary approximation of the constructed operator. In the last section, we graphically interpret the created operator's convergence to two periodic functions "x sin(x)" and "-x/2*cos(pi*x)". We also consider the limiting case a tends to 0; which provides Post-Widder operator. In addition, we analyze each particular case of the defined operator and determine the optimal value of "a", that would yield the greatest approximation; this facilitates us to contrast the well-known operators existing in the literature, especially the Post-Widder operator and the operator due to Ismail-May.

In this article, we study the expanding nature of universe in the contest of $f(R,L_m)$ gravity theory, here $R$ represents the Ricci scalar and $L_m$ is the matter Lagrangian density. With a specific form of $f(R,L_m)$, we obtain the field equations for flat FLRW metric. We parametrize the deceleration parameter in terms of the Hubble parameter and from here we find four free parameters, which are constraints and estimated by using $H(z)$, $Pantheon$, and their joint data sets. Further, we investigate the evolution of the deceleration parameter which depicts a transition from the deceleration to acceleration phases of the universe. The evolution behaviour of energy density, pressure, and EoS parameters shows that the present model is an accelerated quintessence dark energy model. To compare our model with the $\Lambda$CDM model we use some of the diagnostic techniques. Thus, we find that our model in $f(R,L_m)$ gravity supports the recent standard observational studies and delineates the late-time cosmic acceleration.

Recently, online social media has become a primary source for new information and misinformation or rumours. In the absence of an automatic rumour detection system the propagation of rumours has increased manifold leading to serious societal damages. In this work, we propose a novel method for building automatic rumour detection system by focusing on oversampling to alleviating the fundamental challenges of class imbalance in rumour detection task. Our oversampling method relies on contextualised data augmentation to generate synthetic samples for underrepresented classes in the dataset. The key idea exploits selection of tweets in a thread for augmentation which can be achieved by introducing a non-random selection criteria to focus the augmentation process on relevant tweets. Furthermore, we propose two graph neural networks(GNN) to model non-linear conversations on a thread. To enhance the tweet representations in our method we employed a custom feature selection technique based on state-of-the-art BERTweet model. Experiments of three publicly available datasets confirm that 1) our GNN models outperform the the current state-of-the-art classifiers by more than 20%(F1-score); 2) our oversampling technique increases the model performance by more than 9%;(F1-score) 3) focusing on relevant tweets for data augmentation via non-random selection criteria can further improve the results; and 4) our method has superior capabilities to detect rumours at very early stage.

Augmented Reality (AR) technologies hold immense potential for revolutionizing the way individuals with disabilities interact with the world. AR systems can provide real-time assistance and support by overlaying digital information over the physical environment based on the requirements of the use, hence addressing different types of disabilities. Through an in-depth analysis of four case studies, this paper aims to provide a comprehensive overview of the current-state-of-the-art in AR assistive technologies for individuals with disabilities, highlighting their potential to assist and transform their lives. The findings show the significance that AR has made to bridge the accessibility gap, while also discussing the challenges faced and ethical considerations associated with the implementation across the various cases. This is done through theory analysis, practical examples, and future projections that will motivate and seek to inspire further innovation in this very relevant area of exploration.

The number of Hindi speakers on social media has increased dramatically in recent years. Regret is a common emotional experience in our everyday life. Many speakers on social media, share their regretful experiences and opinions regularly. It might cause a re-evaluation of one's choices and a desire to make a different option if given the chance. As a result, knowing the source of regret is critical for investigating its impact on behavior and decision-making. This study focuses on regret and how it is expressed, specifically in Hindi, on various social media platforms. In our study, we present a novel dataset from three different sources, where each sentence has been manually classified into one of three classes "Regret by action", "Regret by inaction", and "No regret". Next, we use this dataset to investigate the linguistic expressions of regret in Hindi text and also identify the textual domains that are most frequently associated with regret. Our findings indicate that individuals on social media platforms frequently express regret for both past inactions and actions, particularly within the domain of interpersonal relationships. We use a pre-trained BERT model to generate word embeddings for the Hindi dataset and also compare deep learning models with conventional machine learning models in order to demonstrate accuracy. Our results show that BERT embedding with CNN consistently surpassed other models. This described the effectiveness of BERT for conveying the context and meaning of words in the regret domain.

We present a first detailed survey on underwater and air-water (A-W) wireless communication networks (WCNs) that mainly focuses on the security challenges and the countermeasures proposed to date. For clarity of exposition, this survey paper is mainly divided into two parts. The first part of the paper focuses on the state-of-the-art underwater and A-W WCNs whereby we outline the benefits and drawbacks of the four promising underwater and A-W candidate technologies: radio frequency (RF), acoustic, optical and magnetic induction (MI), along with their channel characteristics. To this end, we also describe the indirect (relay-aided) and direct mechanisms for the A-W WCNs along with their channel characteristics. This sets the stage for the second part of the paper whereby we provide a thorough comparative discussion of a vast set of works that have reported the security breaches (as well as viable countermeasures) for many diverse configurations of the underwater and A-W WCNs. Specifically, we provide a detailed literature review of the various kinds of active and passive attacks which hamper the confidentiality, integrity, authentication and availability of both underwater and A-W WCNs. Finally, we highlight some research gaps in the open literature and identify security related some open problems for the future work.