Rakesh Dey
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Rakesh Dey has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Saumik Bhattacharya
IIT Kharagpur
2 shared publications - Umapada Pal
Indian Statistical Institute
2 shared publications - Palaiahnakote Shivakumara
University of Salford
1 shared publication - Siladittya Manna
Indian Statistical Institute
1 shared publication - Soumitri Chattopadhyay
Department of Information Technology, Jadavpur University, Kolkata, India
1 shared publication - Sukalpa Chanda
Østfold University College
1 shared publication
Latest Publications
- 3 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Emerging Topics in Computational Intelligence
- Vol. 10 (1) , 454-467
SFTT: A Spatial-Frequency-Temporal-Based End-to-End Transformer for Heart Rate Estimation
Vision-based Heart Rate (HR) estimation in adverse situations, such as changes in skin tone, arbitrary face movements, and complex backgrounds, etc., is challenging. Unlike state-of-the-art models that use color and spatial-temporal information, the present work exploits a Spatial-Frequency-Temporal Transformer (SFTT) for heart rate estimation. For extracting multi-scale contextual features, we propose an end-to-end transformer that encodes contextual information through a pyramidal structure-based approach. Furthermore, to strengthen the features, the proposed model introduces a new attention approach that performs mutual-sharing operations between spatial-temporal and frequency-temporal domains in an end-to-end fashion. Experimental results on four standard datasets, namely UBFC-rPPG, VIPL-HR, OBF, and MMSE-HR, show that the proposed model is generic and invariant to the aforementioned challenges. Further, a comparative study with the state-of-the-art models demonstrates the effectiveness of the proposed method over the existing methods on all four benchmark datasets. Besides, experiments on cross-dataset validation show that the proposed method is reliable and robust.
- 3 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Emerging Topics in Computational Intelligence
- Vol. 10 (1) , 454-467
SFTT: A Spatial-Frequency-Temporal-Based End-to-End Transformer for Heart Rate Estimation
Vision-based Heart Rate (HR) estimation in adverse situations, such as changes in skin tone, arbitrary face movements, and complex backgrounds, etc., is challenging. Unlike state-of-the-art models that use color and spatial-temporal information, the present work exploits a Spatial-Frequency-Temporal Transformer (SFTT) for heart rate estimation. For extracting multi-scale contextual features, we propose an end-to-end transformer that encodes contextual information through a pyramidal structure-based approach. Furthermore, to strengthen the features, the proposed model introduces a new attention approach that performs mutual-sharing operations between spatial-temporal and frequency-temporal domains in an end-to-end fashion. Experimental results on four standard datasets, namely UBFC-rPPG, VIPL-HR, OBF, and MMSE-HR, show that the proposed model is generic and invariant to the aforementioned challenges. Further, a comparative study with the state-of-the-art models demonstrates the effectiveness of the proposed method over the existing methods on all four benchmark datasets. Besides, experiments on cross-dataset validation show that the proposed method is reliable and robust.
- 3 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. 6 (6) , 1502-1512
Dynamically Scaled Temperature in Self-Supervised Contrastive Learning
In contemporary self-supervised contrastive algorithms like SimCLR, MoCo, etc., the task of balancing attraction between two semantically similar samples and repulsion between two samples of different classes is primarily affected by the presence of hard negative samples. While the InfoNCE loss has been shown to impose penalties based on hardness, the temperature hyper-parameter is the key to regulating the penalties and the trade-off between uniformity and tolerance. In this work, we focus our attention on improving the performance of InfoNCE loss in self-supervised learning by proposing a novel cosine similarity dependent temperature scaling function to effectively optimize the distribution of the samples in the feature space. We also provide mathematical analyses to support the construction of such a dynamically scaled temperature function. Experimental evidence shows that the proposed framework outperforms the contrastive loss-based SSL algorithms. Our code is available at https://www.github.com/sadimanna/DySTreSS.
- 3 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Artificial Intelligence
- Vol. 6 (6) , 1502-1512
Dynamically Scaled Temperature in Self-Supervised Contrastive Learning
In contemporary self-supervised contrastive algorithms like SimCLR, MoCo, etc., the task of balancing attraction between two semantically similar samples and repulsion between two samples of different classes is primarily affected by the presence of hard negative samples. While the InfoNCE loss has been shown to impose penalties based on hardness, the temperature hyper-parameter is the key to regulating the penalties and the trade-off between uniformity and tolerance. In this work, we focus our attention on improving the performance of InfoNCE loss in self-supervised learning by proposing a novel cosine similarity dependent temperature scaling function to effectively optimize the distribution of the samples in the feature space. We also provide mathematical analyses to support the construction of such a dynamically scaled temperature function. Experimental evidence shows that the proposed framework outperforms the contrastive loss-based SSL algorithms. Our code is available at https://www.github.com/sadimanna/DySTreSS.