Abhilasha 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
Research Subjects
Abhilasha Sharma has a total of 67 co-authors. Here are the top co-authors by number of shared publications:
- Roshni Singh
Delhi Technological University
4 shared publications - Akshi Kumar
Goldsmiths, University of London
3 shared publications - Mansi Gupta
Delhi Technological University
2 shared publications - Parul Sharma
Department of Software Engineering, Delhi Technological University, Delhi, India
2 shared publications - Aakash Garg
Delhi Technological University
1 shared publication - Abdul Aleem
Galgotias University
1 shared publication
Latest Publications
- Open Access
- 30 September 2026
- Published by Sakarya University Journal of Computer and Information Sciences in Sakarya University Journal of Computer and Information Sciences
- Vol. 9 (4) , 1042-1050
Entropy-Aware Activity Recognition for Sports: Case Study on Cricket
In the digital era, activity recognition substantially impacts everyone’s day-to-day lives. Multiple people and their activities can be seen in the video, and their routines depend on video devices, specifically in sports. Video datasets in sports face several challenges, such as intra-class similarity, inter-class ambiguity, noise and motion transitions. The research proposed an entropy-aware deep learning method for activity recognition that integrates a pre-trained CNN with Density-Based Spatial Clustering of Applications with Noise (DBSCAN) for Cricket keyframe selection. A synthesized dataset of 25,000 annotated cricket clips is generated across five fine-grained activity classes. These keyframes are uniformly sampled, encoded into CNN embeddings, and clustered using DBSCAN. The chosen keyframes are then fine-tuned using a CNN to optimize using categorical cross-entropy loss. The extensive experiments show that the proposed method achieves an accuracy of 96.4% and provides a reliable 6% improvement over unclustered data. The findings show that frame selection using DBSCAN improves generalization across a variety of broadcasting conditions and provides a scalable framework for automated cricket video analysis, with real-time applications in highlight generation, intelligent sports surveillance, and player performance monitoring.
- 30 September 2026
- Published by Sakarya University Journal of Computer and Information Sciences in Sakarya University Journal of Computer and Information Sciences
- Vol. 9 (4) , 1042-1050
Open AccessEntropy-Aware Activity Recognition for Sports: Case Study on Cricket
In the digital era, activity recognition substantially impacts everyone’s day-to-day lives. Multiple people and their activities can be seen in the video, and their routines depend on video devices, specifically in sports. Video datasets in sports face several challenges, such as intra-class similarity, inter-class ambiguity, noise and motion transitions. The research proposed an entropy-aware deep learning method for activity recognition that integrates a pre-trained CNN with Density-Based Spatial Clustering of Applications with Noise (DBSCAN) for Cricket keyframe selection. A synthesized dataset of 25,000 annotated cricket clips is generated across five fine-grained activity classes. These keyframes are uniformly sampled, encoded into CNN embeddings, and clustered using DBSCAN. The chosen keyframes are then fine-tuned using a CNN to optimize using categorical cross-entropy loss. The extensive experiments show that the proposed method achieves an accuracy of 96.4% and provides a reliable 6% improvement over unclustered data. The findings show that frame selection using DBSCAN improves generalization across a variety of broadcasting conditions and provides a scalable framework for automated cricket video analysis, with real-time applications in highlight generation, intelligent sports surveillance, and player performance monitoring.
- 2 September 2026
- Published by Springer Nature
- p. 324-336
Comparative Analysis of Skeleton-Based Pose Estimation Models for Human Activity Recognition Using CNN–LSTM
- 2 September 2026
- Published by Springer Nature
- p. 324-336
Comparative Analysis of Skeleton-Based Pose Estimation Models for Human Activity Recognition Using CNN–LSTM
- 2 August 2026
- Published by Springer Nature
- p. 443-454
Recommendation Systems: A Survey of Recent Advances and a Proposal for a Deep Reinforcement Federated Recommendation System
- 2 August 2026
- Published by Springer Nature
- p. 443-454
Recommendation Systems: A Survey of Recent Advances and a Proposal for a Deep Reinforcement Federated Recommendation System
- 16 July 2026
- Published by Wiley
- p. 135-146
GEN‐HAR : Generative Diffusion Learning for Human Activity Recognition
- 16 July 2026
- Published by Wiley
- p. 135-146
GEN‐HAR : Generative Diffusion Learning for Human Activity Recognition
- 7 August 2025
- Published by Springer Nature
- p. 484-493
Genomic Data-Driven Pandemic Forecasting with Federated Deep Learning for Enhanced Privacy
- 7 August 2025
- Published by Springer Nature
- p. 484-493
Genomic Data-Driven Pandemic Forecasting with Federated Deep Learning for Enhanced Privacy
- 1 May 2025
- Published by Springer Nature
- p. 83-91
A Comparative Study: Performance Evaluation of Image Cryptography Techniques
- 1 May 2025
- Published by Springer Nature
- p. 83-91
A Comparative Study: Performance Evaluation of Image Cryptography Techniques
- Open Access
- 28 March 2024
- Published by Wiley in Conservation Letters
- Vol. 17 (3)
Destructive fishing: An expert‐driven definition and exploration of this quasi‐concept
Numerous policy and international frameworks consider that “destructive fishing” hampers efforts to reach sustainability goals. Though ubiquitous, “destructive fishing” is undefined and therefore currently immeasurable. Here we propose a definition developed through expert consultation: “Destructive fishing is any fishing practice that causes irrecoverable habitat degradation, or which causes significant adverse environmental impacts, results in long‐term declines in target or nontarget species beyond biologically safe limits and has negative livelihood impacts.” We show strong stakeholder support for a definition, consensus on many biological and ecological dimensions, and no clustering of respondents from different sectors. Our consensus definition is a significant step toward defining sustainable fisheries goals and will help interpret and implement global political commitments which utilize the term “destructive fishing.” Our definition and results will help reinforce the Food and Agricultural Organization's Code of Conduct and meaningfully support member countries to prohibit destructive fishing practices.
- 28 March 2024
- Published by Wiley in Conservation Letters
- Vol. 17 (3)
Open AccessDestructive fishing: An expert‐driven definition and exploration of this quasi‐concept
Numerous policy and international frameworks consider that “destructive fishing” hampers efforts to reach sustainability goals. Though ubiquitous, “destructive fishing” is undefined and therefore currently immeasurable. Here we propose a definition developed through expert consultation: “Destructive fishing is any fishing practice that causes irrecoverable habitat degradation, or which causes significant adverse environmental impacts, results in long‐term declines in target or nontarget species beyond biologically safe limits and has negative livelihood impacts.” We show strong stakeholder support for a definition, consensus on many biological and ecological dimensions, and no clustering of respondents from different sectors. Our consensus definition is a significant step toward defining sustainable fisheries goals and will help interpret and implement global political commitments which utilize the term “destructive fishing.” Our definition and results will help reinforce the Food and Agricultural Organization's Code of Conduct and meaningfully support member countries to prohibit destructive fishing practices.