Swati Srivastava
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Swati Srivastava has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Himanshu Sharma
Department of Computer Engineering and Applications GLA University Mathura India
9 shared publications Awanish Kumar Mishra
Maharana Pratap Engineering College
3 shared publications- Indresh Kumar Gupta
Pranveer Singh Institute of Technology
3 shared publications - Joel Jose Puga Coelho Rodrigues
Federal University of Piau (UFPI), Teresina - PI, Brazil
3 shared publications Bipin Tripathi
2 shared publicationsBipin Kumar Tripathi
1 shared publication
Latest Publications
- 8 November 2026
- Published by Wiley in Computational Intelligence
- Vol. 42 (6)
TextVQA : A Comprehensive Study of Approaches, Datasets, and Evaluation Metrics
Text‐based visual question answering (Text‐VQA) aims to answer question by combining visual features with embedded textual content. This field has gained substantial attention due to developments in deep learning technologies across vision, text and voice. A typical Text‐VQA pipeline includes Optical Character Recognition (OCR) for extracting textual content from images, which are then employed within a VQA model to reason about the content. In this survey, we conducted a detailed study of the field, systematically analyzing key approaches, datasets, and evaluation metrics that have shaped the expansion of Text‐VQA systems. We provide a comprehensive overview of recent state‐of‐the‐art (SOTA) methods and evaluate their performance on three major datasets: TextVQA, ST‐VQA and OCR‐VQA. By observing each phase of the Text‐VQA methods, we discussed key challenges, acknowledge major contributions, and presented promising directions for future research in this evolving field.
- 8 November 2026
- Published by Wiley in Computational Intelligence
- Vol. 42 (6)
TextVQA : A Comprehensive Study of Approaches, Datasets, and Evaluation Metrics
Text‐based visual question answering (Text‐VQA) aims to answer question by combining visual features with embedded textual content. This field has gained substantial attention due to developments in deep learning technologies across vision, text and voice. A typical Text‐VQA pipeline includes Optical Character Recognition (OCR) for extracting textual content from images, which are then employed within a VQA model to reason about the content. In this survey, we conducted a detailed study of the field, systematically analyzing key approaches, datasets, and evaluation metrics that have shaped the expansion of Text‐VQA systems. We provide a comprehensive overview of recent state‐of‐the‐art (SOTA) methods and evaluate their performance on three major datasets: TextVQA, ST‐VQA and OCR‐VQA. By observing each phase of the Text‐VQA methods, we discussed key challenges, acknowledge major contributions, and presented promising directions for future research in this evolving field.
- 1 October 2025
- Published by Springer Nature
- p. 1-14
Diabetes Mellitus Recognition Using Marine Predators Algorithm with Machine Learning Model
- 1 October 2025
- Published by Springer Nature
- p. 1-14
Diabetes Mellitus Recognition Using Marine Predators Algorithm with Machine Learning Model
- 29 August 2025
- Published by Springer Nature
- p. 29-44
Deep Learning-Driven Blood Vessel Segmentation for Early Detection and Classification of Diabetic Retinopathy
- 29 August 2025
- Published by Springer Nature
- p. 29-44
Deep Learning-Driven Blood Vessel Segmentation for Early Detection and Classification of Diabetic Retinopathy
- 24 August 2025
- Published by Springer Nature
- p. 77-88
Enhanced Particle Swarm Optimization to Solve Traveling Salesman Problem
- 24 August 2025
- Published by Springer Nature
- p. 77-88
Enhanced Particle Swarm Optimization to Solve Traveling Salesman Problem
- 1 November 2024
- Published by SPIE-Intl Soc Optical Eng in Journal of Electronic Imaging
- Vol. 33 (06) , 063052-18
Deep multimodal relational reasoning and guided attention for chart question answering
The proposed work for chart question answering (CQA) addresses crucial aspects, particularly those associated with questions requiring complex reasoning and visual references to charts and those related to optical character recognition (OCR) noise. Existing methods focused mainly on image features, neglecting the unique characteristics of the visual representation, which consequently not able to answer complex reasoning questions. Introducing structural embedding, question embedding, and a transformer-based relational understanding of the visualizations enable the proposed model to answer complex reasoning questions. The incorporation of the reading component and visual component using BERT encoding leverages both textual and visual information, which overcomes the OCR noise-related issue. The comprehensive ablation study systematically evaluates the different components of our model. Moreover, experiments are conducted on five datasets: DVQA, FigureQA, PlotQA, LEAFQA++, and ChartQA, which makes the assessment robust and generalized. The overall accuracy of our model is increased by 1.15% compared with STL-CQA on the test familiar of DVQA, 0.55% compared with PReFIL on FigureQA, 8.03% compared with Plot-QA, 2.28% compared with STL-CQA test-familiar split of LEAFQA++, and 0.40% compared with VisionTaPas on the test-set of ChartQA, which shows the effectiveness and superiority of the proposed model over existing methods on these datasets.
- 1 November 2024
- Published by SPIE-Intl Soc Optical Eng in Journal of Electronic Imaging
- Vol. 33 (06) , 063052-18
Deep multimodal relational reasoning and guided attention for chart question answering
The proposed work for chart question answering (CQA) addresses crucial aspects, particularly those associated with questions requiring complex reasoning and visual references to charts and those related to optical character recognition (OCR) noise. Existing methods focused mainly on image features, neglecting the unique characteristics of the visual representation, which consequently not able to answer complex reasoning questions. Introducing structural embedding, question embedding, and a transformer-based relational understanding of the visualizations enable the proposed model to answer complex reasoning questions. The incorporation of the reading component and visual component using BERT encoding leverages both textual and visual information, which overcomes the OCR noise-related issue. The comprehensive ablation study systematically evaluates the different components of our model. Moreover, experiments are conducted on five datasets: DVQA, FigureQA, PlotQA, LEAFQA++, and ChartQA, which makes the assessment robust and generalized. The overall accuracy of our model is increased by 1.15% compared with STL-CQA on the test familiar of DVQA, 0.55% compared with PReFIL on FigureQA, 8.03% compared with Plot-QA, 2.28% compared with STL-CQA test-familiar split of LEAFQA++, and 0.40% compared with VisionTaPas on the test-set of ChartQA, which shows the effectiveness and superiority of the proposed model over existing methods on these datasets.
- 29 December 2023
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 83 (21) , 59577-59595
Integrating multimodal features by a two-way co-attention mechanism for visual question answering
- 29 December 2023
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 83 (21) , 59577-59595
Integrating multimodal features by a two-way co-attention mechanism for visual question answering
- Open Access
- 24 October 2023
- Published by Qeios Ltd
Review of: "Attention Mechanism Model Combined with Adversarial Learning for E-commerce User Behavior Classification and Personality Recommendation"
This paper proposes a model to detect and identify fake comments through user behavior classification using Attention Mechanism combined with Adversarial Learning where feature extraction is based on super-complete independent component analysis algo...
- 24 October 2023
- Published by Qeios Ltd
Open AccessReview of: "Attention Mechanism Model Combined with Adversarial Learning for E-commerce User Behavior Classification and Personality Recommendation"
This paper proposes a model to detect and identify fake comments through user behavior classification using Attention Mechanism combined with Adversarial Learning where feature extraction is based on super-complete independent component analysis algo...
- 12 July 2023
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 83 (5) , 14085-14109
Face recognition for human identification through integration of complex domain unsupervised and supervised frameworks
- 12 July 2023
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 83 (5) , 14085-14109
Face recognition for human identification through integration of complex domain unsupervised and supervised frameworks
- 1 May 2023
- Published by SPIE-Intl Soc Optical Eng in Journal of Electronic Imaging
- Vol. 32 (03) , 033023-19
Improving scene text image captioning using transformer-based multilevel attention
Many existing image captioning methods only focus on image objects and their relationships for generating image captions, ignoring the text present in an image. Scene text (ST) contains crucial information to understand an image and facilitating reasoning. The existing methods fail to establish strong correlations between optical character recognition (OCR) tokens, as they have limited OCR representation power. Further, these methods have not efficiently used the positional information of the text. In this work, we have proposed an ST-based image captioning model (Trans-MAtt) based on a multilevel attention mechanism and relation network. We have used relation networks to enhance the connections between ST tokens. We have employed a multi-level attention method, which comprises of spatial, semantic, and appearance attention modules that precisely define the image. To represent context-enriched ST tokens, we use a combination of appearance, location, FastText, and PHOC features. We predict the ST location in the image, which is further integrated with the generated word embeddings for final caption generation. Experiments on the TextCaps dataset demonstrate the effectiveness of the proposed Trans-MAtt model, where it outperforms the current best model by 3.4% on B-4, 2.9% on METEOR, 3.3% on ROUGE-L, 3.1% on CIDEr-D, and 4.1% on SPICE metric scores. Our experiments on the Flickr30k and MSCOCO datasets demonstrated the superiority of our proposed model over existing methods.
- 1 May 2023
- Published by SPIE-Intl Soc Optical Eng in Journal of Electronic Imaging
- Vol. 32 (03) , 033023-19
Improving scene text image captioning using transformer-based multilevel attention
Many existing image captioning methods only focus on image objects and their relationships for generating image captions, ignoring the text present in an image. Scene text (ST) contains crucial information to understand an image and facilitating reasoning. The existing methods fail to establish strong correlations between optical character recognition (OCR) tokens, as they have limited OCR representation power. Further, these methods have not efficiently used the positional information of the text. In this work, we have proposed an ST-based image captioning model (Trans-MAtt) based on a multilevel attention mechanism and relation network. We have used relation networks to enhance the connections between ST tokens. We have employed a multi-level attention method, which comprises of spatial, semantic, and appearance attention modules that precisely define the image. To represent context-enriched ST tokens, we use a combination of appearance, location, FastText, and PHOC features. We predict the ST location in the image, which is further integrated with the generated word embeddings for final caption generation. Experiments on the TextCaps dataset demonstrate the effectiveness of the proposed Trans-MAtt model, where it outperforms the current best model by 3.4% on B-4, 2.9% on METEOR, 3.3% on ROUGE-L, 3.1% on CIDEr-D, and 4.1% on SPICE metric scores. Our experiments on the Flickr30k and MSCOCO datasets demonstrated the superiority of our proposed model over existing methods.
- 17 December 2022
- Published by Springer Nature in Neural Processing Letters
- Vol. 55 (5) , 5693-5715
A Framework for Image Captioning Based on Relation Network and Multilevel Attention Mechanism
- 17 December 2022
- Published by Springer Nature in Neural Processing Letters
- Vol. 55 (5) , 5693-5715
A Framework for Image Captioning Based on Relation Network and Multilevel Attention Mechanism