Zobrazeno 1 - 10
of 125
pro vyhledávání: '"Sur, Arijit"'
Recently, transformers have captured significant interest in the area of single-image super-resolution tasks, demonstrating substantial gains in performance. Current models heavily depend on the network's extensive ability to extract high-level seman
Externí odkaz:
http://arxiv.org/abs/2408.09940
Underwater imagery is often compromised by factors such as color distortion and low contrast, posing challenges for high-level vision tasks. Recent underwater image restoration (UIR) methods either analyze the input image at full resolution, resultin
Externí odkaz:
http://arxiv.org/abs/2408.09912
Hand gesture recognition allows humans to interact with machines non-verbally, which has a huge application in underwater exploration using autonomous underwater vehicles. Recently, a new gesture-based language called CADDIAN has been devised for div
Externí odkaz:
http://arxiv.org/abs/2407.14103
Knee Osteoarthritis (KOA) is the third most prevalent Musculoskeletal Disorder (MSD) after neck and back pain. To monitor such a severe MSD, a segmentation map of the femur, tibia and tibiofemoral cartilage is usually accessed using the automated seg
Externí odkaz:
http://arxiv.org/abs/2401.12932
Publikováno v:
IEEE Trans. Cogn. Dev. Syst. 16 (2024) 1775-1788
Successive proposals of several self-supervised training schemes continue to emerge, taking one step closer to developing a universal foundation model. In this process, the unsupervised downstream tasks are recognized as one of the evaluation methods
Externí odkaz:
http://arxiv.org/abs/2401.12820
Autor:
Sarma, Sandipan, Sur, Arijit
Inspired by strategies like Active Learning, it is intuitive that intelligently selecting the training classes from a dataset for Zero-Shot Learning (ZSL) can improve the performance of existing ZSL methods. In this work, we propose a framework calle
Externí odkaz:
http://arxiv.org/abs/2301.00236
Zero-shot detection (ZSD) is a challenging task where we aim to recognize and localize objects simultaneously, even when our model has not been trained with visual samples of a few target ("unseen") classes. Recently, methods employing generative mod
Externí odkaz:
http://arxiv.org/abs/2212.06097
Publikováno v:
In Neurocomputing 28 September 2024 599
Knee Osteoarthritis (OA) is a destructive joint disease identified by joint stiffness, pain, and functional disability concerning millions of lives across the globe. It is generally assessed by evaluating physical symptoms, medical history, and other
Externí odkaz:
http://arxiv.org/abs/2106.14292
In recent times, deep learning-based steganalysis classifiers became popular due to their state-of-the-art performance. Most deep steganalysis classifiers usually extract noise residuals using high-pass filters as preprocessing steps and feed them to
Externí odkaz:
http://arxiv.org/abs/2106.10430