Zobrazeno 1 - 10
of 41
pro vyhledávání: '"Namboodiri, Anoop M."'
Forensic sketch-to-mugshot matching is a challenging task in face recognition, primarily hindered by the scarcity of annotated forensic sketches and the modality gap between sketches and photographs. To address this, we propose CLIP4Sketch, a novel a
Externí odkaz:
http://arxiv.org/abs/2408.01233
Evaluating the risk level of adversarial images is essential for safely deploying face authentication models in the real world. Popular approaches for physical-world attacks, such as print or replay attacks, suffer from some limitations, like includi
Externí odkaz:
http://arxiv.org/abs/2311.11753
Autor:
Mullick, Koustav, Namboodiri, Anoop M.
We look at the problem of developing a compact and accurate model for gesture recognition from videos in a deep-learning framework. Towards this we propose a joint 3DCNN-LSTM model that is end-to-end trainable and is shown to be better suited to capt
Externí odkaz:
http://arxiv.org/abs/1712.10136
Autor:
Aggarwal, Rajat, Namboodiri, Anoop M.
Publikováno v:
ACM International Conference Proceeding Series; 12/18/2016, p1-8, 8p
Publikováno v:
2016 IEEE Conference on Computer Vision & Pattern Recognition (CVPR); 2016, p3755-3763, 9p
Publikováno v:
2015 13th International Conference on Document Analysis & Recognition (ICDAR); 2015, p1061-1065, 5p
Publikováno v:
2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR); 2015, p630-634, 5p
Publikováno v:
2015 3rd IAPR Asian Conference on Pattern Recognition (ACPR); 2015, p599-603, 5p