Zobrazeno 1 - 10
of 113
pro vyhledávání: '"Lal, Rohit"'
Autor:
Ta, Calvin-Khang, Dutta, Arindam, Kundu, Rohit, Lal, Rohit, Cruz, Hannah Dela, Raychaudhuri, Dripta S., Roy-Chowdhury, Amit
The Skinned Multi-Person Linear (SMPL) model plays a crucial role in 3D human pose estimation, providing a streamlined yet effective representation of the human body. However, ensuring the validity of SMPL configurations during tasks such as human me
Externí odkaz:
http://arxiv.org/abs/2410.14540
Autor:
Roy, Sujit, Singh, Talwinder, Freitag, Marcus, Schmude, Johannes, Lal, Rohit, Hegde, Dinesha, Ranjan, Soumya, Lin, Amy, Gaur, Vishal, Vos, Etienne Eben, Ghosal, Rinki, Patro, Badri Narayana, Aydin, Berkay, Pogorelov, Nikolai, Moreno, Juan Bernabe, Maskey, Manil, Ramachandran, Rahul
Deep learning-based methods have been widely researched in the areas of language and vision, demonstrating their capacity to understand long sequences of data and their usefulness in numerous helio-physics applications. Foundation models (FMs), which
Externí odkaz:
http://arxiv.org/abs/2410.10841
Autor:
Schmude, Johannes, Roy, Sujit, Trojak, Will, Jakubik, Johannes, Civitarese, Daniel Salles, Singh, Shraddha, Kuehnert, Julian, Ankur, Kumar, Gupta, Aman, Phillips, Christopher E, Kienzler, Romeo, Szwarcman, Daniela, Gaur, Vishal, Shinde, Rajat, Lal, Rohit, Da Silva, Arlindo, Diaz, Jorge Luis Guevara, Jones, Anne, Pfreundschuh, Simon, Lin, Amy, Sheshadri, Aditi, Nair, Udaysankar, Anantharaj, Valentine, Hamann, Hendrik, Watson, Campbell, Maskey, Manil, Lee, Tsengdar J, Moreno, Juan Bernabe, Ramachandran, Rahul
Triggered by the realization that AI emulators can rival the performance of traditional numerical weather prediction models running on HPC systems, there is now an increasing number of large AI models that address use cases such as forecasting, downs
Externí odkaz:
http://arxiv.org/abs/2409.13598
In this work, we explore the usage of the Frequency Transformation for reducing the domain shift between the source and target domain (e.g., synthetic image and real image respectively) towards solving the Domain Adaptation task. Most of the Unsuperv
Externí odkaz:
http://arxiv.org/abs/2407.19551
Autor:
Dutta, Arindam, Lal, Rohit, Garg, Yash, Ta, Calvin-Khang, Raychaudhuri, Dripta S., Cruz, Hannah Dela, Roy-Chowdhury, Amit K.
Existing algorithms for human body part segmentation have shown promising results on challenging datasets, primarily relying on end-to-end supervision. However, these algorithms exhibit severe performance drops in the face of domain shifts, leading t
Externí odkaz:
http://arxiv.org/abs/2407.03549
Autor:
Lal, Rohit, Bachu, Saketh, Garg, Yash, Dutta, Arindam, Ta, Calvin-Khang, Raychaudhuri, Dripta S., Cruz, Hannah Dela, Asif, M. Salman, Roy-Chowdhury, Amit K.
The capability to accurately estimate 3D human poses is crucial for diverse fields such as action recognition, gait recognition, and virtual/augmented reality. However, a persistent and significant challenge within this field is the accurate predicti
Externí odkaz:
http://arxiv.org/abs/2312.16221
Recent advancements in computer vision predominantly rely on learning-based systems, leveraging annotations as the driving force to develop specialized models. However, annotating pixel-level information, particularly in semantic segmentation, presen
Externí odkaz:
http://arxiv.org/abs/2312.02420
Autor:
Dutta, Arindam, Lal, Rohit, Raychaudhuri, Dripta S., Ta, Calvin Khang, Roy-Chowdhury, Amit K.
Publikováno v:
Winter Conference on Applications of Computer Vision, 2024
Human silhouette extraction is a fundamental task in computer vision with applications in various downstream tasks. However, occlusions pose a significant challenge, leading to incomplete and distorted silhouettes. To address this challenge, we intro
Externí odkaz:
http://arxiv.org/abs/2311.05077
Autor:
Raychaudhuri, Dripta S., Ta, Calvin-Khang, Dutta, Arindam, Lal, Rohit, Roy-Chowdhury, Amit K.
Domain adaptation methods for 2D human pose estimation typically require continuous access to the source data during adaptation, which can be challenging due to privacy, memory, or computational constraints. To address this limitation, we focus on th
Externí odkaz:
http://arxiv.org/abs/2308.13954
Single-Source Single-Target Domain Adaptation (1S1T) aims to bridge the gap between a labelled source domain and an unlabelled target domain. Despite 1S1T being a well-researched topic, they are typically not deployed to the real world. Methods like
Externí odkaz:
http://arxiv.org/abs/2302.00995