Sachin Sharma
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
Sachin Sharma has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Federico Simonetta
GSSI – Gran Sasso Science Institute
3 shared publications - Michele Flammini
Gran Sasso Science Institute, L’Aquila, Italy
2 shared publications - Jorge Junior Morgado Vega
Gran Sasso Science Institute, L'Aquila, L'Aquila, Italy
1 shared publication - Prabhudutta Ray
Institute of Advanced Research
1 shared publication - Raj Raval
Gujarat Pulmonary and Critical Care Medicine
1 shared publication
Latest Publications
- 28 August 2026
- Published by Springer Nature
- p. 215-228
TrOCR for Medieval HTR: A Systematic Ablation Study with Cross-Dataset Validation
- 28 August 2026
- Published by Springer Nature
- p. 215-228
TrOCR for Medieval HTR: A Systematic Ablation Study with Cross-Dataset Validation
- Open Access
- 8 July 2026
- Published by Springer Nature in Research Square
TrOCR for Medieval HTR: A Systematic Ablation Study with Cross-Dataset Validation
Fine-tuning transformer-based handwritten text recognition (HTR) models on medieval manuscripts is challenging because these models are pre-trained on modern text and must adapt to a very different visual domain. This paper studies how three controllable finetuning choices (contrast normalization, data augmentation, and layer freezing) affect recognition accuracy when adapting TrOCR to small historical datasets. We run controlled experiments on a 13th-century Italian manuscript (I-CT 91 “Cortonese”) and replicate the same experimental grid on the public READ-16 benchmark as robustness evidence. On Cortonese, our best configuration achieves 8.03% character error rate (CER). Statistical comparisons across 13 configurations show that freezing up to three encoder layers or six decoder layers does not significantly harm accuracy, while deeper freezing becomes progressively detrimental. Removing contrast normalization (CLAHE) yields 7.84% CER, comparable to a domain-specialized baseline, suggesting strong optimization can reduce reliance on image preprocessing. Cross-dataset validation on READ-16 shows that decoder freezing thresholds transfer more robustly than encoder thresholds, and combined freezing strategies require dataset-specific re-validation. Finally, we use Grad-CAM gradient attributions and decoder cross-attention maps to diagnose error patterns and failure modes revealed by the ablations. Source code is available at https://github.com/LaudareProject/TrOCR-analysis
- 8 July 2026
- Published by Springer Nature in Research Square
Open AccessTrOCR for Medieval HTR: A Systematic Ablation Study with Cross-Dataset Validation
Fine-tuning transformer-based handwritten text recognition (HTR) models on medieval manuscripts is challenging because these models are pre-trained on modern text and must adapt to a very different visual domain. This paper studies how three controllable finetuning choices (contrast normalization, data augmentation, and layer freezing) affect recognition accuracy when adapting TrOCR to small historical datasets. We run controlled experiments on a 13th-century Italian manuscript (I-CT 91 “Cortonese”) and replicate the same experimental grid on the public READ-16 benchmark as robustness evidence. On Cortonese, our best configuration achieves 8.03% character error rate (CER). Statistical comparisons across 13 configurations show that freezing up to three encoder layers or six decoder layers does not significantly harm accuracy, while deeper freezing becomes progressively detrimental. Removing contrast normalization (CLAHE) yields 7.84% CER, comparable to a domain-specialized baseline, suggesting strong optimization can reduce reliance on image preprocessing. Cross-dataset validation on READ-16 shows that decoder freezing thresholds transfer more robustly than encoder thresholds, and combined freezing strategies require dataset-specific re-validation. Finally, we use Grad-CAM gradient attributions and decoder cross-attention maps to diagnose error patterns and failure modes revealed by the ablations. Source code is available at https://github.com/LaudareProject/TrOCR-analysis
- Open Access
- 25 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 28-35
Drafting the Landscape of Computational Musicology Tools: a Survey-Based Approach
- 25 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 28-35
Open AccessDrafting the Landscape of Computational Musicology Tools: a Survey-Based Approach
- Open Access
- 1 March 2023
- Published by Institute of Advanced Engineering and Science in International Journal of Reconfigurable and Embedded Systems (IJRES)
- Vol. 12 (1) , 42-50
Application of artificial intelligence techniques in the intensive care unit
Intensive care unit deals with data that are dynamic in nature like real time measurement of health condition to laboratory test data that are continuously changes accordingly with time. Artificial intelligence (AI’s) potential ability to perform complex pattern analyses using large volumes of data. Generated pattern discovers the new symptoms of the disease in the Intensive care units (ICUs), helps the doctors to prescribe the new drug discovery which is helpful to intelligent use. Currently research work has been focused in the ICU making more efficient clinical workflow by generation of high-risk patterns from improved high volumes of data. Emerging area of AI in the ICU includes mortality prediction, uses of powerful sensors, new drug discovery, prediction of length of stay and legal role in uses of drugs for severity of disease. This review focuses latest application of AI drugs and other relevant issues for the ICU.
- 1 March 2023
- Published by Institute of Advanced Engineering and Science in International Journal of Reconfigurable and Embedded Systems (IJRES)
- Vol. 12 (1) , 42-50
Open AccessApplication of artificial intelligence techniques in the intensive care unit
Intensive care unit deals with data that are dynamic in nature like real time measurement of health condition to laboratory test data that are continuously changes accordingly with time. Artificial intelligence (AI’s) potential ability to perform complex pattern analyses using large volumes of data. Generated pattern discovers the new symptoms of the disease in the Intensive care units (ICUs), helps the doctors to prescribe the new drug discovery which is helpful to intelligent use. Currently research work has been focused in the ICU making more efficient clinical workflow by generation of high-risk patterns from improved high volumes of data. Emerging area of AI in the ICU includes mortality prediction, uses of powerful sensors, new drug discovery, prediction of length of stay and legal role in uses of drugs for severity of disease. This review focuses latest application of AI drugs and other relevant issues for the ICU.