arXiv subjects

Dinesh Kumar Vishwakarma

Publications and source records attributed to Dinesh Kumar Vishwakarma.

At least 37 records · Page 2Linked to original sources

arXiv2022

Transformer-Based Named Entity Recognition for French Using Adversarial Adaptation to Similar Domain Corpora

Named Entity Recognition (NER) involves the identification and classification of named entities in unstructured text into predefined classes. NER in languages with limited resources, like French, is still an open problem due to the lack of large, robust, labelled datasets. In this paper, we propose a transformer-based NER approach for French using adversarial adaptation to similar domain or general corpora for improved feature extraction and better generalization. We evaluate our approach on three labelled datasets and show that our adaptation framework outperforms the corresponding non-adaptive models for various combinations of transformer models, source datasets and target corpora.

cs.CL↗

arXiv2022

An Emotion-guided Approach to Domain Adaptive Fake News Detection using Adversarial Learning

Recent works on fake news detection have shown the efficacy of using emotions as a feature for improved performance. However, the cross-domain impact of emotion-guided features for fake news detection still remains an open problem. In this work, we propose an emotion-guided, domain-adaptive, multi-task approach for cross-domain fake news detection, proving the efficacy of emotion-guided models in cross-domain settings for various datasets.

cs.CL↗

arXiv2022

CKS: A Community-based K-shell Decomposition Approach using Community Bridge Nodes for Influence Maximization

Social networks have enabled user-specific advertisements and recommendations on their platforms, which puts a significant focus on Influence Maximisation (IM) for target advertising and related tasks. The aim is to identify nodes in the network which can maximize the spread of information through a diffusion cascade. We propose a community structures-based approach that employs K-Shell algorithm with community structures to generate a score for the connections between seed nodes and communities. Further, our approach employs entropy within communities to ensure the proper spread of information within the communities. We validate our approach on four publicly available networks and show its superiority to four state-of-the-art approaches while still being relatively efficient.

cs.SI↗

arXiv2022

Emotion-guided Cross-domain Fake News Detection using Adversarial Domain Adaptation

Recent works on fake news detection have shown the efficacy of using emotions as a feature or emotions-based features for improved performance. However, the impact of these emotion-guided features for fake news detection in cross-domain settings, where we face the problem of domain shift, is still largely unexplored. In this work, we evaluate the impact of emotion-guided features for cross-domain fake news detection, and further propose an emotion-guided, domain-adaptive approach using adversarial learning. We prove the efficacy of emotion-guided models in cross-domain settings for various combinations of source and target datasets from FakeNewsAMT, Celeb, Politifact and Gossipcop datasets.

cs.CL↗

arXiv2022

A Spreader Ranking Algorithm for Extremely Low-budget Influence Maximization in Social Networks using Community Bridge Nodes

In recent years, social networking platforms have gained significant popularity among the masses like connecting with people and propagating ones thoughts and opinions. This has opened the door to user-specific advertisements and recommendations on these platforms, bringing along a significant focus on Influence Maximisation (IM) on social networks due to its wide applicability in target advertising, viral marketing, and personalized recommendations. The aim of IM is to identify certain nodes in the network which can help maximize the spread of certain information through a diffusion cascade. While several works have been proposed for IM, most were inefficient in exploiting community structures to their full extent. In this work, we propose a community structures-based approach, which employs a K-Shell algorithm in order to generate a score for the connections between seed nodes and communities for low-budget scenarios. Further, our approach employs entropy within communities to ensure the proper spread of information within the communities. We choose the Independent Cascade (IC) model to simulate information spread and evaluate it on four evaluation metrics. We validate our proposed approach on eight publicly available networks and find that it significantly outperforms the baseline approaches on these metrics, while still being relatively efficient.

cs.SI↗

arXiv2022

Influence Maximization in Social Networks using Discretized Harris Hawks Optimization Algorithm and Neighbour Scout Strategy

Influence Maximization (IM) is the task of determining k optimal influential nodes in a social network to maximize the influence spread using a propagation model. IM is a prominent problem for viral marketing, and helps significantly in social media advertising. However, developing effective algorithms with minimal time complexity for real-world social networks still remains a challenge. While traditional heuristic approaches have been applied for IM, they often result in minimal performance gains over the computationally expensive Greedy-based and Reverse Influence Sampling-based approaches. In this paper, we propose the discretization of the nature-inspired Harris Hawks Optimisation meta-heuristic algorithm using community structures for optimal selection of seed nodes for influence spread. In addition to Harris Hawks intelligence, we employ a neighbour scout strategy algorithm to avoid blindness and enhance the searching ability of the hawks. Further, we use a candidate nodes-based random population initialization approach, and these candidate nodes aid in accelerating the convergence process for the entire populace. We evaluate the efficacy of our proposed DHHO approach on six social networks using the Independent Cascade model for information diffusion. We observe that DHHO is comparable or better than competing meta-heuristic approaches for Influence Maximization across five metrics, and performs noticeably better than competing heuristic approaches.

cs.SI↗

arXiv2021

Clickbait in YouTube Prevention, Detection and Analysis of the Bait using Ensemble Learning

Unscrupulous content creators on YouTube employ deceptive techniques such as spam and clickbait to reach a broad audience and trick users into clicking on their videos to increase their advertisement revenue. Clickbait detection on YouTube requires an in depth examination and analysis of the intricate relationship between the video content and video descriptors title and thumbnail. However, the current solutions are mostly centred around the study of video descriptors and other metadata such as likes, tags, comments, etc and fail to utilize the video content, both video and audio. Therefore, we introduce a novel model to detect clickbaits on YouTube that consider the relationship between video content and title or thumbnail. The proposed model consists of a stacking classifier framework composed of six base models (K Nearest Neighbours, Support Vector Machine, XGBoost, Naive Bayes, Logistic Regression, and Multilayer Perceptron) and a meta classifier. The developed clickbait detection model achieved a high accuracy of 92.89% for the novel BollyBAIT dataset and 95.38% for Misleading Video Dataset. Additionally, the stated classifier does not use meta features or other statistics dependent on user interaction with the video (the number of likes, followers, or comments) for classification, and thus, can be used to detect potential clickbait videos before they are uploaded, thereby preventing the nuisance of clickbaits altogether and improving the users streaming experience.

cs.SI↗

arXiv2021

Fake News Detection using Semi-Supervised Graph Convolutional Network

Social media becomes the central way for people to obtain and utilise news, due to its rapidness and inexpensive value of data distribution. Though, such features of social media platforms also present it a root cause of fake news distribution, causing adverse consequences on both people and culture. Hence, detecting fake news has become a significant research interest for bringing feasible real time solutions to the problem. Most current techniques of fake news disclosure are supervised, that need large cost in terms of time and effort to make a certainly interpreted dataset. The proposed framework concentrates on the text-based detection of fake news items while considering that only limited number of labels are available. Graphs are functioned extensively under several purposes of real-world problems on the strength of their property to structure things easily. Deep neural networks are used to generate great results within tasks that utilizes graph classification. The Graph Convolution Network works as a deep learning paradigm which works on graphs. Our proposed framework deals with limited amount of labelled data; we go for a semi-supervised learning method. We come up with a semi-supervised fake news detection technique based on GCN (Graph Convolutional Networks). The recommended architecture comprises of three basic components: collecting word embeddings from the news articles in datasets utilising GloVe, building similarity graph using Word Movers Distance (WMD) and finally applying Graph Convolution Network (GCN) for binary classification of news articles in semi-supervised paradigm. The implemented technique is validated on three different datasets by varying the volume of labelled data achieving 95.27 % highest accuracy on Real or Fake dataset. Comparison with other contemporary techniques also reinforced the supremacy of the proposed framework.

cs.SI↗

arXiv2021

Multi-modal Fusion using Fine-tuned Self-attention and Transfer Learning for Veracity Analysis of Web Information

The nuisance of misinformation and fake news has escalated many folds since the advent of online social networks. Human consciousness and decision-making capabilities are negatively influenced by manipulated, fabricated, biased or unverified news posts. Therefore, there is a high demand for designing veracity analysis systems to detect fake information contents in multiple data modalities. In an attempt to find a sophisticated solution to this critical issue, we proposed an architecture to consider both the textual and visual attributes of the data. After the data pre-processing is done, text and image features are extracted from the training data using separate deep learning models. Feature extraction from text is done using BERT and ALBERT language models that leverage the benefits of bidirectional training of transformers using a deep self-attention mechanism. The Inception-ResNet-v2 deep neural network model is employed for image data to perform the task. The proposed framework focused on two independent multi-modal fusion architectures of BERT and Inception-ResNet-v2 as well as ALBERT and Inception-ResNet-v2. Multi-modal fusion of textual and visual branches is extensively experimented and analysed using concatenation of feature vectors and weighted averaging of probabilities named as Early Fusion and Late Fusion respectively. Three publicly available broadly accepted datasets All Data, Weibo and MediaEval 2016 that incorporates English news articles, Chinese news articles, and Tweets correspondingly are used so that our designed framework's outcomes can be properly tested and compared with previous notable work in the domain.

cs.SI↗

arXiv2021

A Unified Approach of Detecting Misleading Images via Tracing its Instances on Web and Analysing its Past Context for the Verification of Content

The verification of multimedia content over social media is one of the challenging and crucial issues in the current scenario and gaining prominence in an age where user-generated content and online social web platforms are the leading sources in shaping and propagating news stories. As these sources allow users to share their opinions without restriction, opportunistic users often post misleading/ unreliable content on social media such as Twitter, Facebook, etc. At present, to lure users towards the news story, the text is often attached with some multimedia content (images/videos/audios). Verifying these contents to maintain the credibility and reliability of social media information is of paramount importance. Motivated by this, we proposed a generalized system that supports the automatic classification of images into credible or misleading. In this paper, we investigated machine learning-based as well as deep learning-based approaches utilized to verify misleading multimedia content, where the available image traces are used to identify the credibility of the content. The experiment is performed on the real-world dataset (Media-eval-2015 dataset) collected from Twitter. It also demonstrates the efficiency of our proposed approach and features using both Machine and Deep Learning Model (Bi-directional LSTM). The experiment result reveals that the Microsoft bings image search engine is quite effective in retrieving titles and performs better than our study's Google image search engine. It also shows that gathering clues from attached multimedia content (image) is more effective than detecting only posted content-based features.

cs.SI↗

arXiv2021

An Automated Multi-Web Platform Voting Framework to Predict Misleading Information Proliferated during COVID-19 Outbreak using Ensemble Method

Spreading of misleading information on social web platforms has fuelled huge panic and confusion among the public regarding the Corona disease, the detection of which is of paramount importance. To address this issue, in this paper, we have developed an automated system that can collect and validate the fact from multi web-platform to decide the credibility of the content. To identify the credibility of the posted claim, probable instances/clues(titles) of news information are first gathered from various web platforms. Later, the crucial set of features is retrieved that further feeds into the ensemble-based machine learning model to classify the news as misleading or real. The four sets of features based on the content, linguistics/semantic cues, similarity, and sentiments gathered from web-platforms and voting are applied to validate the news. Finally, the combined voting decides the support given to a specific claim. In addition to the validation part, a unique source platform is designed for collecting data/facts from three web platforms (Twitter, Facebook, Google) based on certain queries/words. This unique platform can also help researchers build datasets and gather useful/efficient clues from various web platforms. It has been observed that our proposed intelligent strategy gives promising results and quite effective in predicting misleading information. The proposed work provides practical implications for the policy makers and health practitioners that could be useful in protecting the world from misleading information proliferation during this pandemic.

cs.IR↗

arXiv2021

Multilevel profiling of situation and dialogue-based deep networks for movie genre classification using movie trailers

Automated movie genre classification has emerged as an active and essential area of research and exploration. Short duration movie trailers provide useful insights about the movie as video content consists of the cognitive and the affective level features. Previous approaches were focused upon either cognitive or affective content analysis. In this paper, we propose a novel multi-modality: situation, dialogue, and metadata-based movie genre classification framework that takes both cognition and affect-based features into consideration. A pre-features fusion-based framework that takes into account: situation-based features from a regular snapshot of a trailer that includes nouns and verbs providing the useful affect-based mapping with the corresponding genres, dialogue (speech) based feature from audio, metadata which together provides the relevant information for cognitive and affect based video analysis. We also develop the English movie trailer dataset (EMTD), which contains 2000 Hollywood movie trailers belonging to five popular genres: Action, Romance, Comedy, Horror, and Science Fiction, and perform cross-validation on the standard LMTD-9 dataset for validating the proposed framework. The results demonstrate that the proposed methodology for movie genre classification has performed excellently as depicted by the F1 scores, precision, recall, and area under the precision-recall curves.

cs.CL↗

arXiv2021

Deep and Shallow Covariance Feature Quantization for 3D Facial Expression Recognition

Facial expressions recognition (FER) of 3D face scans has received a significant amount of attention in recent years. Most of the facial expression recognition methods have been proposed using mainly 2D images. These methods suffer from several issues like illumination changes and pose variations. Moreover, 2D mapping from 3D images may lack some geometric and topological characteristics of the face. Hence, to overcome this problem, a multi-modal 2D + 3D feature-based method is proposed. We extract shallow features from the 3D images, and deep features using Convolutional Neural Networks (CNN) from the transformed 2D images. Combining these features into a compact representation uses covariance matrices as descriptors for both features instead of single-handedly descriptors. A covariance matrix learning is used as a manifold layer to reduce the deep covariance matrices size and enhance their discrimination power while preserving their manifold structure. We then use the Bag-of-Features (BoF) paradigm to quantize the covariance matrices after flattening. Accordingly, we obtained two codebooks using shallow and deep features. The global codebook is then used to feed an SVM classifier. High classification performances have been achieved on the BU-3DFE and Bosphorus datasets compared to the state-of-the-art methods.

cs.CV↗

arXiv2020

Person Re-Identification using Deep Learning Networks: A Systematic Review

Person re-identification has received a lot of attention from the research community in recent times. Due to its vital role in security based applications, person re-identification lies at the heart of research relevant to tracking robberies, preventing terrorist attacks and other security critical events. While the last decade has seen tremendous growth in re-id approaches, very little review literature exists to comprehend and summarize this progress. This review deals with the latest state-of-the-art deep learning based approaches for person re-identification. While the few existing re-id review works have analysed re-id techniques from a singular aspect, this review evaluates numerous re-id techniques from multiple deep learning aspects such as deep architecture types, common Re-Id challenges (variation in pose, lightning, view, scale, partial or complete occlusion, background clutter), multi-modal Re-Id, cross-domain Re-Id challenges, metric learning approaches and video Re-Id contributions. This review also includes several re-id benchmarks collected over the years, describing their characteristics, specifications and top re-id results obtained on them. The inclusion of the latest deep re-id works makes this a significant contribution to the re-id literature. Lastly, the conclusion and future directions are included.

cs.CV↗

arXiv2020

A Deep Multi-Level Attentive network for Multimodal Sentiment Analysis

Multimodal sentiment analysis has attracted increasing attention with broad application prospects. The existing methods focuses on single modality, which fails to capture the social media content for multiple modalities. Moreover, in multi-modal learning, most of the works have focused on simply combining the two modalities, without exploring the complicated correlations between them. This resulted in dissatisfying performance for multimodal sentiment classification. Motivated by the status quo, we propose a Deep Multi-Level Attentive network, which exploits the correlation between image and text modalities to improve multimodal learning. Specifically, we generate the bi-attentive visual map along the spatial and channel dimensions to magnify CNNs representation power. Then we model the correlation between the image regions and semantics of the word by extracting the textual features related to the bi-attentive visual features by applying semantic attention. Finally, self-attention is employed to automatically fetch the sentiment-rich multimodal features for the classification. We conduct extensive evaluations on four real-world datasets, namely, MVSA-Single, MVSA-Multiple, Flickr, and Getty Images, which verifies the superiority of our method.

cs.MM↗

arXiv2020

A Deep Language-independent Network to analyze the impact of COVID-19 on the World via Sentiment Analysis

Towards the end of 2019, Wuhan experienced an outbreak of novel coronavirus, which soon spread all over the world, resulting in a deadly pandemic that infected millions of people around the globe. The government and public health agencies followed many strategies to counter the fatal virus. However, the virus severely affected the social and economic lives of the people. In this paper, we extract and study the opinion of people from the top five worst affected countries by the virus, namely USA, Brazil, India, Russia, and South Africa. We propose a deep language-independent Multilevel Attention-based Conv-BiGRU network (MACBiG-Net), which includes embedding layer, word-level encoded attention, and sentence-level encoded attention mechanism to extract the positive, negative, and neutral sentiments. The embedding layer encodes the sentence sequence into a real-valued vector. The word-level and sentence-level encoding is performed by a 1D Conv-BiGRU based mechanism, followed by word-level and sentence-level attention, respectively. We further develop a COVID-19 Sentiment Dataset by crawling the tweets from Twitter. Extensive experiments on our proposed dataset demonstrate the effectiveness of the proposed MACBiG-Net. Also, attention-weights visualization and in-depth results analysis shows that the proposed network has effectively captured the sentiments of the people.

cs.CL↗

arXiv2019

View-invariant Deep Architecture for Human Action Recognition using late fusion

Human action Recognition for unknown views is a challenging task. We propose a view-invariant deep human action recognition framework, which is a novel integration of two important action cues: motion and shape temporal dynamics (STD). The motion stream encapsulates the motion content of action as RGB Dynamic Images (RGB-DIs) which are processed by the fine-tuned InceptionV3 model. The STD stream learns long-term view-invariant shape dynamics of action using human pose model (HPM) based view-invariant features mined from structural similarity index matrix (SSIM) based key depth human pose frames. To predict the score of the test sample, three types of late fusion (maximum, average and product) techniques are applied on individual stream scores. To validate the performance of the proposed novel framework the experiments are performed using both cross subject and cross-view validation schemes on three publically available benchmarks- NUCLA multi-view dataset, UWA3D-II Activity dataset and NTU RGB-D Activity dataset. Our algorithm outperforms with existing state-of-the-arts significantly that is reported in terms of accuracy, receiver operating characteristic (ROC) curve and area under the curve (AUC).

cs.CV↗

arXiv2019

Skeleton based Activity Recognition by Fusing Part-wise Spatio-temporal and Attention Driven Residues

There exist a wide range of intra class variations of the same actions and inter class similarity among the actions, at the same time, which makes the action recognition in videos very challenging. In this paper, we present a novel skeleton-based part-wise Spatiotemporal CNN RIAC Network-based 3D human action recognition framework to visualise the action dynamics in part wise manner and utilise each part for action recognition by applying weighted late fusion mechanism. Part wise skeleton based motion dynamics helps to highlight local features of the skeleton which is performed by partitioning the complete skeleton in five parts such as Head to Spine, Left Leg, Right Leg, Left Hand, Right Hand. The RIAFNet architecture is greatly inspired by the InceptionV4 architecture which unified the ResNet and Inception based Spatio-temporal feature representation concept and achieving the highest top-1 accuracy till date. To extract and learn salient features for action recognition, attention driven residues are used which enhance the performance of residual components for effective 3D skeleton-based Spatio-temporal action representation. The robustness of the proposed framework is evaluated by performing extensive experiments on three challenging datasets such as UT Kinect Action 3D, Florence 3D action Dataset, and MSR Daily Action3D datasets, which consistently demonstrate the superiority of our method

cs.CV↗