Shalaka Prasad Deore
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Shalaka Prasad Deore has a total of 25 co-authors. Here are the top co-authors by number of shared publications:
- Avinash Bhute
Pimpri Chinchwad College of Engineering
1 shared publication - Balaji K. Bodkhe
Department of Computer Engineering, MES Wadia College of Engineering, S. P. Pune University, Pune, Maharashtra 411001, India
1 shared publication - Bharati P. Vasgi
Department of Information Technology, Marathwada Mitra Mandal's College of Engineering, Karvenagar, Pune, Maharashtra, India
1 shared publication - Chandrakant D. Kokane
Department of Computer Science and Engineering (Artificial Intelligence), Vishwakarma Institute of Technology, Pune, Maharashtra, India
1 shared publication - Harsha Bhute
Department of Information Technology, Pimpri Chinchwad College of Engineering, Pune, Maharashtra, India
1 shared publication - Harsheen Tejindersingh Rajpal
Computer Engineering, MES College of Engineering, S. P. Pune University, 411001 Pune, India
1 shared publication
Latest Publications
- 6 May 2026
- Published by World Scientific Pub Co Pte Ltd in International Journal of Image and Graphics
Deep Learning Innovations in Ray Tracing: A Survey of Transition to Neural Rendering
This work provides a comprehensive analysis of the evolution of rendering techniques in computer graphics, focusing on the transition from rasterization, a method renowned for its efficiency, to physically based rendering techniques such as ray tracing and path tracing, which offer superior visual realism. Despite the unmatched accuracy of ray tracing in simulating complex light interactions, its widespread adoption has historically been limited by its high computational demands and sampling noise. Recent breakthroughs in deep learning have catalyzed a paradigm shift in rendering workflows, offering practical solutions to these challenges. Neural networks, through intelligent denoising, adaptive sampling strategies, and novel acceleration architectures, are now significantly enhancing both the performance and quality of ray tracing. This technological synergy is becoming increasingly critical to meet the escalating demand for high-fidelity, real-time graphics in fields such as gaming, virtual production, and immersive simulations. The report evaluates the transformative impact of deep learning on ray tracing and its implications for the future of interactive digital media.
- 6 May 2026
- Published by World Scientific Pub Co Pte Ltd in International Journal of Image and Graphics
Deep Learning Innovations in Ray Tracing: A Survey of Transition to Neural Rendering
This work provides a comprehensive analysis of the evolution of rendering techniques in computer graphics, focusing on the transition from rasterization, a method renowned for its efficiency, to physically based rendering techniques such as ray tracing and path tracing, which offer superior visual realism. Despite the unmatched accuracy of ray tracing in simulating complex light interactions, its widespread adoption has historically been limited by its high computational demands and sampling noise. Recent breakthroughs in deep learning have catalyzed a paradigm shift in rendering workflows, offering practical solutions to these challenges. Neural networks, through intelligent denoising, adaptive sampling strategies, and novel acceleration architectures, are now significantly enhancing both the performance and quality of ray tracing. This technological synergy is becoming increasingly critical to meet the escalating demand for high-fidelity, real-time graphics in fields such as gaming, virtual production, and immersive simulations. The report evaluates the transformative impact of deep learning on ray tracing and its implications for the future of interactive digital media.
- 31 October 2025
- Published by Elsevier in Indian Journal of Tuberculosis
- Vol. 72, S31-S38
CNN-based image recognition of Acid-Fast Bacilli in sputum smears for enhanced tuberculosis diagnosis
- 31 October 2025
- Published by Elsevier in Indian Journal of Tuberculosis
- Vol. 72, S31-S38
CNN-based image recognition of Acid-Fast Bacilli in sputum smears for enhanced tuberculosis diagnosis
- 17 October 2025
- Published by Elsevier in Indian Journal of Tuberculosis
- Vol. 72, S18-S23
Federated learning framework for predicting multi-drug resistant tuberculosis across regional databases
- 17 October 2025
- Published by Elsevier in Indian Journal of Tuberculosis
- Vol. 72, S18-S23
Federated learning framework for predicting multi-drug resistant tuberculosis across regional databases
- Open Access
- 3 February 2024
- Published by Acadlore Publishing Services Limited in Information Dynamics and Applications
- Vol. 3 (1) , 12-20
Enhancing Image Captioning and Auto-Tagging Through a FCLN with Faster R-CNN Integration
In the realm of automated image captioning, which entails generating descriptive text for images, the fusion of Natural Language Processing (NLP) and computer vision techniques is paramount. This study introduces the Fully Convolutional Localization Network (FCLN), a novel approach that concurrently addresses localization and description tasks within a singular forward pass. It maintains spatial information and avoids detail loss, streamlining the training process with consistent optimization. The foundation of FCLN is laid by a Convolutional Neural Network (CNN), adept at extracting salient image features. Central to this architecture is a Localization Layer, pivotal in precise object detection and caption generation. The FCLN architecture amalgamates a region detection network, reminiscent of Faster Region-CNN (R-CNN), with a captioning network. This synergy enables the production of contextually meaningful image captions. The incorporation of the Faster R-CNN framework facilitates region-based object detection, offering precise contextual understanding and inter-object relationships. Concurrently, a Long Short-Term Memory (LSTM) network is employed for generating captions. This integration yields superior performance in caption accuracy, particularly in complex scenes. Evaluations conducted on the Microsoft Common Objects in Context (MS COCO) test server affirm the model's superiority over existing benchmarks, underscoring its efficacy in generating precise and context-rich image captions.
- 3 February 2024
- Published by Acadlore Publishing Services Limited in Information Dynamics and Applications
- Vol. 3 (1) , 12-20
Open AccessEnhancing Image Captioning and Auto-Tagging Through a FCLN with Faster R-CNN Integration
In the realm of automated image captioning, which entails generating descriptive text for images, the fusion of Natural Language Processing (NLP) and computer vision techniques is paramount. This study introduces the Fully Convolutional Localization Network (FCLN), a novel approach that concurrently addresses localization and description tasks within a singular forward pass. It maintains spatial information and avoids detail loss, streamlining the training process with consistent optimization. The foundation of FCLN is laid by a Convolutional Neural Network (CNN), adept at extracting salient image features. Central to this architecture is a Localization Layer, pivotal in precise object detection and caption generation. The FCLN architecture amalgamates a region detection network, reminiscent of Faster Region-CNN (R-CNN), with a captioning network. This synergy enables the production of contextually meaningful image captions. The incorporation of the Faster R-CNN framework facilitates region-based object detection, offering precise contextual understanding and inter-object relationships. Concurrently, a Long Short-Term Memory (LSTM) network is employed for generating captions. This integration yields superior performance in caption accuracy, particularly in complex scenes. Evaluations conducted on the Microsoft Common Objects in Context (MS COCO) test server affirm the model's superiority over existing benchmarks, underscoring its efficacy in generating precise and context-rich image captions.