arXiv subjects

Dinesh Kumar Vishwakarma

Publications and source records attributed to Dinesh Kumar Vishwakarma.

At least 19 recordsLinked to original sources

arXiv2026

HCIG: A Hierarchical Cross-Modal Incongruity Graph Network for Multimodal Sarcasm and Cyberbullying Detection

Multimodal sarcasm and cyberbullying detection remain challenging because the intended meaning often emerges from incongruity between textual and visual information rather than from either modality alone. Existing multimodal approaches primarily rely on feature fusion or cross-modal attention, which may not effectively capture hierarchical semantic inconsistencies across different levels of representation. To address this limitation, this paper proposes HCIG (Hierarchical Cross-modal Incongruity Graph Network), a novel framework that models cross-modal incongruity at token, phrase, and global levels using graph attention networks and adaptively integrates these representations through a learned hierarchical attention mechanism. As a complementary architecture, we also introduce GCCN (Graph-based Cross-modal Contradiction Network), which performs graph-based reasoning using contradiction-aware pooling for efficient multimodal interaction learning. The proposed models are evaluated on the MMSD sarcasm benchmark and the MultiBully cyberbullying dataset, together with comprehensive ablation studies and cross-task transfer experiments. Experimental results demonstrate that HCIG achieves the best performance on MMSD with 85.74% accuracy and 85.29% macro-F1, while GCCN attains the highest macro-F1 (68.66%) on MultiBully and HCIG achieves the highest accuracy (69.62%) and bullying-class F1 (74.90%). The findings demonstrate that hierarchical multi-granularity incongruity modeling provides more effective multimodal reasoning than conventional fusion strategies, offering a robust framework for sarcasm and cyberbullying detection in social media.

cs.CV↗

arXiv2026

FlowFake: Liquid Networks for Audio Deepfake Detection

Audio deepfakes generated by neural text-to-speech and voice-cloning systems threaten speaker verification and public discourse at scale. The core challenge is cross-dataset generalization: detectors trained on one synthesis pipeline collapse on unseen forgeries. We argue that this failure is primarily because of structural synthetic speech artifacts which are multi-timescale trajectory anomalies. Though every existing detector aggregates a fixed-window frame statistics, this misaligns the architecture with the signal. We propose FlowFake, a Liquid Time-Constant (LTC) architecture whose hidden state evolves via a learned ODE, with per-neuron adaptive time constants simultaneously resolving spectral (10ms) and prosodic (2s) cues. At only 34K parameters FlowFake achieves formal BIBO stability and O(dt^4) integration error. On a four-dataset cross domain benchmark (ASVspoof2019-LA, FakeOrReal, InTheWild, MLAAD), FlowFake reaches 75.29% on ASVspoof2019 trained only on FakeOrReal and 79.97% trained only on MLAAD. It outperforms RawGAT-ST and Whisper-DF on every evaluated pair and matching SSL Wav2vec2 (300x larger) at 0.01% of its parameter count. The source code is available on : https://github.com/GhostRider2023/FlowFake

cs.SD↗

arXiv2026

Gait Recognition with Temporal Kolmogorov-Arnold Networks

Gait recognition is a biometric modality that identifies individuals from their characteristic walking patterns. Unlike conventional biometric traits, gait can be acquired at a distance and without active subject cooperation, making it suitable for surveillance and public safety applications. Nevertheless, silhouette-based temporal models remain sensitive to long sequences, observation noise, and appearance-related covariates. Recurrent architectures often struggle to preserve information from earlier frames and are inherently sequential to optimize, whereas transformer-based models typically require greater computational resources and larger training sets and may be sensitive to irregular sequence lengths and noisy inputs. These limitations reduce robustness under clothing variation, carrying conditions, and view changes, while also hindering the joint modeling of local gait cycles and longer-term motion trends. To address these challenges, we introduce a Temporal Kolmogorov-Arnold Network (TKAN) for gait recognition. The proposed model replaces fixed edge weights with learnable one-dimensional functions and incorporates a two-level memory mechanism consisting of short-term RKAN sublayers and a gated long-term pathway. This design enables efficient modeling of both cycle-level dynamics and broader temporal context while maintaining a compact backbone. Experiments on the CASIA-B dataset indicate that the proposed CNN+TKAN framework achieves strong recognition performance under the reported evaluation setting.

cs.CV↗

arXiv2025

Tex-ViT: A Generalizable, Robust, Texture-based dual-branch cross-attention deepfake detector

Deepfakes, which employ GAN to produce highly realistic facial modification, are widely regarded as the prevailing method. Traditional CNN have been able to identify bogus media, but they struggle to perform well on different datasets and are vulnerable to adversarial attacks due to their lack of robustness. Vision transformers have demonstrated potential in the realm of image classification problems, but they require enough training data. Motivated by these limitations, this publication introduces Tex-ViT (Texture-Vision Transformer), which enhances CNN features by combining ResNet with a vision transformer. The model combines traditional ResNet features with a texture module that operates in parallel on sections of ResNet before each down-sampling operation. The texture module then serves as an input to the dual branch of the cross-attention vision transformer. It specifically focuses on improving the global texture module, which extracts feature map correlation. Empirical analysis reveals that fake images exhibit smooth textures that do not remain consistent over long distances in manipulations. Experiments were performed on different categories of FF++, such as DF, f2f, FS, and NT, together with other types of GAN datasets in cross-domain scenarios. Furthermore, experiments also conducted on FF++, DFDCPreview, and Celeb-DF dataset underwent several post-processing situations, such as blurring, compression, and noise. The model surpassed the most advanced models in terms of generalization, achieving a 98% accuracy in cross-domain scenarios. This demonstrates its ability to learn the shared distinguishing textural characteristics in the manipulated samples. These experiments provide evidence that the proposed model is capable of being applied to various situations and is resistant to many post-processing procedures.

cs.CV↗

arXiv2024

MHS-STMA: Multimodal Hate Speech Detection via Scalable Transformer-Based Multilevel Attention Framework

Social media has a significant impact on people's lives. Hate speech on social media has emerged as one of society's most serious issues in recent years. Text and pictures are two forms of multimodal data that are distributed within articles. Unimodal analysis has been the primary emphasis of earlier approaches. Additionally, when doing multimodal analysis, researchers neglect to preserve the distinctive qualities associated with each modality. To address these shortcomings, the present article suggests a scalable architecture for multimodal hate content detection called transformer-based multilevel attention (STMA). This architecture consists of three main parts: a combined attention-based deep learning mechanism, a vision attention-mechanism encoder, and a caption attention-mechanism encoder. To identify hate content, each component uses various attention processes and handles multimodal data in a unique way. Several studies employing multiple assessment criteria on three hate speech datasets such as Hateful memes, MultiOff, and MMHS150K, validate the suggested architecture's efficacy. The outcomes demonstrate that on all three datasets, the suggested strategy performs better than the baseline approaches.

cs.CL↗

arXiv2024

Hate Content Detection via Novel Pre-Processing Sequencing and Ensemble Methods

Social media, particularly Twitter, has seen a significant increase in incidents like trolling and hate speech. Thus, identifying hate speech is the need of the hour. This paper introduces a computational framework to curb the hate content on the web. Specifically, this study presents an exhaustive study of pre-processing approaches by studying the impact of changing the sequence of text pre-processing operations for the identification of hate content. The best-performing pre-processing sequence, when implemented with popular classification approaches like Support Vector Machine, Random Forest, Decision Tree, Logistic Regression and K-Neighbor provides a considerable boost in performance. Additionally, the best pre-processing sequence is used in conjunction with different ensemble methods, such as bagging, boosting and stacking to improve the performance further. Three publicly available benchmark datasets (WZ-LS, DT, and FOUNTA), were used to evaluate the proposed approach for hate speech identification. The proposed approach achieves a maximum accuracy of 95.14% highlighting the effectiveness of the unique pre-processing approach along with an ensemble classifier.

cs.CL↗

arXiv2024

A Noise and Edge extraction-based dual-branch method for Shallowfake and Deepfake Localization

The trustworthiness of multimedia is being increasingly evaluated by advanced Image Manipulation Localization (IML) techniques, resulting in the emergence of the IML field. An effective manipulation model necessitates the extraction of non-semantic differential features between manipulated and legitimate sections to utilize artifacts. This requires direct comparisons between the two regions.. Current models employ either feature approaches based on handcrafted features, convolutional neural networks (CNNs), or a hybrid approach that combines both. Handcrafted feature approaches presuppose tampering in advance, hence restricting their effectiveness in handling various tampering procedures, but CNNs capture semantic information, which is insufficient for addressing manipulation artifacts. In order to address these constraints, we have developed a dual-branch model that integrates manually designed feature noise with conventional CNN features. This model employs a dual-branch strategy, where one branch integrates noise characteristics and the other branch integrates RGB features using the hierarchical ConvNext Module. In addition, the model utilizes edge supervision loss to acquire boundary manipulation information, resulting in accurate localization at the edges. Furthermore, this architecture utilizes a feature augmentation module to optimize and refine the presentation of attributes. The shallowfakes dataset (CASIA, COVERAGE, COLUMBIA, NIST16) and deepfake dataset Faceforensics++ (FF++) underwent thorough testing to demonstrate their outstanding ability to extract features and their superior performance compared to other baseline models. The AUC score achieved an astounding 99%. The model is superior in comparison and easily outperforms the existing state-of-the-art (SoTA) models.

cs.CV↗

arXiv2024

Contrastive Learning-based Multi Modal Architecture for Emoticon Prediction by Employing Image-Text Pairs

The emoticons are symbolic representations that generally accompany the textual content to visually enhance or summarize the true intention of a written message. Although widely utilized in the realm of social media, the core semantics of these emoticons have not been extensively explored based on multiple modalities. Incorporating textual and visual information within a single message develops an advanced way of conveying information. Hence, this research aims to analyze the relationship among sentences, visuals, and emoticons. For an orderly exposition, this paper initially provides a detailed examination of the various techniques for extracting multimodal features, emphasizing the pros and cons of each method. Through conducting a comprehensive examination of several multimodal algorithms, with specific emphasis on the fusion approaches, we have proposed a novel contrastive learning based multimodal architecture. The proposed model employs the joint training of dual-branch encoder along with the contrastive learning to accurately map text and images into a common latent space. Our key finding is that by integrating the principle of contrastive learning with that of the other two branches yields superior results. The experimental results demonstrate that our suggested methodology surpasses existing multimodal approaches in terms of accuracy and robustness. The proposed model attained an accuracy of 91% and an MCC-score of 90% while assessing emoticons using the Multimodal-Twitter Emoticon dataset acquired from Twitter. We provide evidence that deep features acquired by contrastive learning are more efficient, suggesting that the proposed fusion technique also possesses strong generalisation capabilities for recognising emoticons across several modes.

cs.CV↗

arXiv2024

Modelling Visual Semantics via Image Captioning to extract Enhanced Multi-Level Cross-Modal Semantic Incongruity Representation with Attention for Multimodal Sarcasm Detection

Sarcasm is a type of irony, characterized by an inherent mismatch between the literal interpretation and the intended connotation. Though sarcasm detection in text has been extensively studied, there are situations in which textual input alone might be insufficient to perceive sarcasm. The inclusion of additional contextual cues, such as images, is essential to recognize sarcasm in social media data effectively. This study presents a novel framework for multimodal sarcasm detection that can process input triplets. Two components of these triplets comprise the input text and its associated image, as provided in the datasets. Additionally, a supplementary modality is introduced in the form of descriptive image captions. The motivation behind incorporating this visual semantic representation is to more accurately capture the discrepancies between the textual and visual content, which are fundamental to the sarcasm detection task. The primary contributions of this study are: (1) a robust textual feature extraction branch that utilizes a cross-lingual language model; (2) a visual feature extraction branch that incorporates a self-regulated residual ConvNet integrated with a lightweight spatially aware attention module; (3) an additional modality in the form of image captions generated using an encoder-decoder architecture capable of reading text embedded in images; (4) distinct attention modules to effectively identify the incongruities between the text and two levels of image representations; (5) multi-level cross-domain semantic incongruity representation achieved through feature fusion. Compared with cutting-edge baselines, the proposed model achieves the best accuracy of 92.89% and 64.48%, respectively, on the Twitter multimodal sarcasm and MultiBully datasets.

cs.CV↗

arXiv2024

VyAnG-Net: A Novel Multi-Modal Sarcasm Recognition Model by Uncovering Visual, Acoustic and Glossary Features

Various linguistic and non-linguistic clues, such as excessive emphasis on a word, a shift in the tone of voice, or an awkward expression, frequently convey sarcasm. The computer vision problem of sarcasm recognition in conversation aims to identify hidden sarcastic, criticizing, and metaphorical information embedded in everyday dialogue. Prior, sarcasm recognition has focused mainly on text. Still, it is critical to consider all textual information, audio stream, facial expression, and body position for reliable sarcasm identification. Hence, we propose a novel approach that combines a lightweight depth attention module with a self-regulated ConvNet to concentrate on the most crucial features of visual data and an attentional tokenizer based strategy to extract the most critical context-specific information from the textual data. The following is a list of the key contributions that our experimentation has made in response to performing the task of Multi-modal Sarcasm Recognition: an attentional tokenizer branch to get beneficial features from the glossary content provided by the subtitles; a visual branch for acquiring the most prominent features from the video frames; an utterance-level feature extraction from acoustic content and a multi-headed attention based feature fusion branch to blend features obtained from multiple modalities. Extensive testing on one of the benchmark video datasets, MUSTaRD, yielded an accuracy of 79.86% for speaker dependent and 76.94% for speaker independent configuration demonstrating that our approach is superior to the existing methods. We have also conducted a cross-dataset analysis to test the adaptability of VyAnG-Net with unseen samples of another dataset MUStARD++.

cs.CV↗

arXiv2024

Target-Dependent Multimodal Sentiment Analysis Via Employing Visual-to Emotional-Caption Translation Network using Visual-Caption Pairs

The natural language processing and multimedia field has seen a notable surge in interest in multimodal sentiment recognition. Hence, this study aims to employ Target-Dependent Multimodal Sentiment Analysis (TDMSA) to identify the level of sentiment associated with every target (aspect) stated within a multimodal post consisting of a visual-caption pair. Despite the recent advancements in multimodal sentiment recognition, there has been a lack of explicit incorporation of emotional clues from the visual modality, specifically those pertaining to facial expressions. The challenge at hand is to proficiently obtain visual and emotional clues and subsequently synchronise them with the textual content. In light of this fact, this study presents a novel approach called the Visual-to-Emotional-Caption Translation Network (VECTN) technique. The primary objective of this strategy is to effectively acquire visual sentiment clues by analysing facial expressions. Additionally, it effectively aligns and blends the obtained emotional clues with the target attribute of the caption mode. The experimental findings demonstrate that our methodology is capable of producing ground-breaking outcomes when applied to two publicly accessible multimodal Twitter datasets, namely, Twitter-2015 and Twitter-2017. The experimental results show that the suggested model achieves an accuracy of 81.23% and a macro-F1 of 80.61% on the Twitter-15 dataset, while 77.42% and 75.19% on the Twitter-17 dataset, respectively. The observed improvement in performance reveals that our model is better than others when it comes to collecting target-level sentiment in multimodal data using the expressions of the face.

cs.CV↗

arXiv2024

A Visually Attentive Splice Localization Network with Multi-Domain Feature Extractor and Multi-Receptive Field Upsampler

Image splice manipulation presents a severe challenge in today's society. With easy access to image manipulation tools, it is easier than ever to modify images that can mislead individuals, organizations or society. In this work, a novel, "Visually Attentive Splice Localization Network with Multi-Domain Feature Extractor and Multi-Receptive Field Upsampler" has been proposed. It contains a unique "visually attentive multi-domain feature extractor" (VA-MDFE) that extracts attentional features from the RGB, edge and depth domains. Next, a "visually attentive downsampler" (VA-DS) is responsible for fusing and downsampling the multi-domain features. Finally, a novel "visually attentive multi-receptive field upsampler" (VA-MRFU) module employs multiple receptive field-based convolutions to upsample attentional features by focussing on different information scales. Experimental results conducted on the public benchmark dataset CASIA v2.0 prove the potency of the proposed model. It comfortably beats the existing state-of-the-arts by achieving an IoU score of 0.851, pixel F1 score of 0.9195 and pixel AUC score of 0.8989.

cs.CV↗

arXiv2024

Towards Effective Image Forensics via A Novel Computationally Efficient Framework and A New Image Splice Dataset

Splice detection models are the need of the hour since splice manipulations can be used to mislead, spread rumors and create disharmony in society. However, there is a severe lack of image splicing datasets, which restricts the capabilities of deep learning models to extract discriminative features without overfitting. This manuscript presents two-fold contributions toward splice detection. Firstly, a novel splice detection dataset is proposed having two variants. The two variants include spliced samples generated from code and through manual editing. Spliced images in both variants have corresponding binary masks to aid localization approaches. Secondly, a novel Spatio-Compression Lightweight Splice Detection Framework is proposed for accurate splice detection with minimum computational cost. The proposed dual-branch framework extracts discriminative spatial features from a lightweight spatial branch. It uses original resolution compression data to extract double compression artifacts from the second branch, thereby making it 'information preserving.' Several CNNs are tested in combination with the proposed framework on a composite dataset of images from the proposed dataset and the CASIA v2.0 dataset. The best model accuracy of 0.9382 is achieved and compared with similar state-of-the-art methods, demonstrating the superiority of the proposed framework.

cs.CV↗

arXiv2024

Datasets, Clues and State-of-the-Arts for Multimedia Forensics: An Extensive Review

With the large chunks of social media data being created daily and the parallel rise of realistic multimedia tampering methods, detecting and localising tampering in images and videos has become essential. This survey focusses on approaches for tampering detection in multimedia data using deep learning models. Specifically, it presents a detailed analysis of benchmark datasets for malicious manipulation detection that are publicly available. It also offers a comprehensive list of tampering clues and commonly used deep learning architectures. Next, it discusses the current state-of-the-art tampering detection methods, categorizing them into meaningful types such as deepfake detection methods, splice tampering detection methods, copy-move tampering detection methods, etc. and discussing their strengths and weaknesses. Top results achieved on benchmark datasets, comparison of deep learning approaches against traditional methods and critical insights from the recent tampering detection methods are also discussed. Lastly, the research gaps, future direction and conclusion are discussed to provide an in-depth understanding of the tampering detection research arena.

cs.CV↗

arXiv2023

DQSSA: A Quantum-Inspired Solution for Maximizing Influence in Online Social Networks (Student Abstract)

Influence Maximization is the task of selecting optimal nodes maximising the influence spread in social networks. This study proposes a Discretized Quantum-based Salp Swarm Algorithm (DQSSA) for optimizing influence diffusion in social networks. By discretizing meta-heuristic algorithms and infusing them with quantum-inspired enhancements, we address issues like premature convergence and low efficacy. The proposed method, guided by quantum principles, offers a promising solution for Influence Maximisation. Experiments on four real-world datasets reveal DQSSA's superior performance as compared to established cutting-edge algorithms.

cs.SI↗

arXiv2023

Optimizing Electric Vehicle Efficiency with Real-Time Telemetry using Machine Learning

In the contemporary world with degrading natural resources, the urgency of energy efficiency has become imperative due to the conservation and environmental safeguarding. Therefore, it's crucial to look for advanced technology to minimize energy consumption. This research focuses on the optimization of battery-electric city style vehicles through the use of a real-time in-car telemetry system that communicates between components through the robust Controller Area Network (CAN) protocol. By harnessing real-time data from various sensors embedded within vehicles, our driving assistance system provides the driver with visual and haptic actionable feedback that guides the driver on using the optimum driving style to minimize power consumed by the vehicle. To develop the pace feedback mechanism for the driver, real-time data is collected through a Shell Eco Marathon Urban Concept vehicle platform and after pre-processing, it is analyzed using the novel machine learning algorithm TEMSL, that outperforms the existing baseline approaches across various performance metrics. This innovative method after numerous experimentation has proven effective in enhancing energy efficiency, guiding the driver along the track, and reducing human errors. The driving-assistance system offers a range of utilities, from cost savings and extended vehicle lifespan to significant contributions to environmental conservation and sustainable driving practices.

eess.SY↗

arXiv2023

Adversarial Adaptation for French Named Entity Recognition

Named Entity Recognition (NER) is the task of identifying and classifying named entities in large-scale texts into predefined classes. NER in French and other relatively limited-resource languages cannot always benefit from approaches proposed for languages like English due to a dearth of large, robust datasets. In this paper, we present our work that aims to mitigate the effects of this dearth of large, labeled datasets. We propose a Transformer-based NER approach for French, using adversarial adaptation to similar domain or general corpora to improve feature extraction and enable better generalization. Our approach allows learning better features using large-scale unlabeled corpora from the same domain or mixed domains to introduce more variations during training and reduce overfitting. Experimental results on three labeled datasets show that our adaptation framework outperforms the corresponding non-adaptive models for various combinations of Transformer models, source datasets, and target corpora. We also show that adversarial adaptation to large-scale unlabeled corpora can help mitigate the performance dip incurred on using Transformer models pre-trained on smaller corpora.

cs.CL↗

arXiv2022

An Emotion-Aware Multi-Task Approach to Fake News and Rumour Detection using Transfer Learning

Social networking sites, blogs, and online articles are instant sources of news for internet users globally. However, in the absence of strict regulations mandating the genuineness of every text on social media, it is probable that some of these texts are fake news or rumours. Their deceptive nature and ability to propagate instantly can have an adverse effect on society. This necessitates the need for more effective detection of fake news and rumours on the web. In this work, we annotate four fake news detection and rumour detection datasets with their emotion class labels using transfer learning. We show the correlation between the legitimacy of a text with its intrinsic emotion for fake news and rumour detection, and prove that even within the same emotion class, fake and real news are often represented differently, which can be used for improved feature extraction. Based on this, we propose a multi-task framework for fake news and rumour detection, predicting both the emotion and legitimacy of the text. We train a variety of deep learning models in single-task and multi-task settings for a more comprehensive comparison. We further analyze the performance of our multi-task approach for fake news detection in cross-domain settings to verify its efficacy for better generalization across datasets, and to verify that emotions act as a domain-independent feature. Experimental results verify that our multi-task models consistently outperform their single-task counterparts in terms of accuracy, precision, recall, and F1 score, both for in-domain and cross-domain settings. We also qualitatively analyze the difference in performance in single-task and multi-task learning models.

cs.CL↗