Zobrazeno 1 - 10
of 112
pro vyhledávání: '"Jain, Arjun"'
Publikováno v:
International Conference on Computer Vision (ICCV) 2021
This paper proposes GraviCap, i.e., a new approach for joint markerless 3D human motion capture and object trajectory estimation from monocular RGB videos. We focus on scenes with objects partially observed during a free flight. In contrast to existi
Externí odkaz:
http://arxiv.org/abs/2108.08844
Autor:
Mulè, Matthew P., Martins, Andrew J., Cheung, Foo, Farmer, Rohit, Sellers, Brian A., Quiel, Juan A., Jain, Arjun, Kotliarov, Yuri, Bansal, Neha, Chen, Jinguo, Schwartzberg, Pamela L., Tsang, John S.
Publikováno v:
In Immunity 14 May 2024 57(5):1160-1176
Autor:
Dabral, Rishabh, Gundavarapu, Nitesh B, Mitra, Rahul, Sharma, Abhishek, Ramakrishnan, Ganesh, Jain, Arjun
Multi-person 3D human pose estimation from a single image is a challenging problem, especially for in-the-wild settings due to the lack of 3D annotated data. We propose HG-RCNN, a Mask-RCNN based network that also leverages the benefits of the Hourgl
Externí odkaz:
http://arxiv.org/abs/1909.10854
Few-shot learning (FSL) for action recognition is a challenging task of recognizing novel action categories which are represented by few instances in the training data. In a more generalized FSL setting (G-FSL), both seen as well as novel action cate
Externí odkaz:
http://arxiv.org/abs/1909.07945
Online and Early detection of gestures is crucial for building touchless gesture based interfaces. These interfaces should operate on a stream of video frames instead of the complete video and detect the presence of gestures at an earlier stage than
Externí odkaz:
http://arxiv.org/abs/1909.06672
This paper provides a comprehensive and exhaustive study of adversarial attacks on human pose estimation models and the evaluation of their robustness. Besides highlighting the important differences between well-studied classification and human pose-
Externí odkaz:
http://arxiv.org/abs/1908.06401
The best performing methods for 3D human pose estimation from monocular images require large amounts of in-the-wild 2D and controlled 3D pose annotated datasets which are costly and require sophisticated systems to acquire. To reduce this annotation
Externí odkaz:
http://arxiv.org/abs/1908.05293
Monocular 3D human-pose estimation from static images is a challenging problem, due to the curse of dimensionality and the ill-posed nature of lifting 2D-to-3D. In this paper, we propose a Deep Conditional Variational Autoencoder based model that syn
Externí odkaz:
http://arxiv.org/abs/1904.01324
Autor:
Upadhyay, Uddeshya, Jain, Arjun
Many biological data analysis processes like Cytometry or Next Generation Sequencing (NGS) produce massive amounts of data which needs to be processed in batches for down-stream analysis. Such datasets are prone to technical variations due to differe
Externí odkaz:
http://arxiv.org/abs/1901.06654