Zobrazeno 1 - 10 of 101 pro vyhledávání: '"Ramakrishnan, KR."'
1
Report
Transfer Learning in CNNs Using Filter-Trees
Autor: Kumaraswamy, Suresh Kirthi, Sastry, PS, Ramakrishnan, KR
Convolutional Neural Networks (CNNs) are very effective for many pattern recognition tasks. However, training deep CNNs needs extensive computation and large training data. In this paper we propose Bank of Filter-Trees (BFT) as a trans- fer learning
Externí odkaz: http://arxiv.org/abs/1711.09648
Zobrazit plný text záznamu
3
Influence of Strain History on Dynamic Strain Localization and Stress State During High-Rate Tensile Loading of Titanium Alloys:Experiments, Modeling, and Analytical Methods
Autor: Gour, G, Thomson, D, Ramakrishnan, KR, Townsend, D, Petrinic, N, Pellegrino, A
Publikováno v: Gour, G, Thomson, D, Ramakrishnan, K R, Townsend, D, Petrinic, N & Pellegrino, A 2023, ' Influence of Strain History on Dynamic Strain Localization and Stress State During High-Rate Tensile Loading of Titanium Alloys : Experiments, Modeling, and Analytical Methods ', Journal of Applied Mechanics, vol. 90, no. 2, 021005 . https://doi.org/10.1115/1.4056136
The determination of the mechanical response of engineering materials subjected to high loading rates plays an important role in determining their performance and application. The high strain-rate tensile response of metals is usually investigated by
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::28580dd1027a2a26bff891ee03fa5c28
https://hdl.handle.net/1983/adf0974a-4289-4586-b03c-354b71de0bd6
Zobrazit plný text záznamu
4
Covariance profiles: a signature representation for object sets
Autor: Anoop, KR, Mitra, Adway, Bonde, Ujwal, Bhattacharyya, Chiranjib, Ramakrishnan, KR
Publikováno v: IndraStra Global.
We consider the problem of extracting a signature representation of similar entities employing covariance descriptors. Covariance descriptors can efficiently represent objects and are robust to scale and pose changes. We posit that covariance descrip
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=issn23813652::989d2509209bcb2a167be11a27825732
https://igi.indrastra.com/items/show/197005
Zobrazit plný text záznamu
5
Motion segmentation using curve fitting on Lagrangian particle trajectories
Autor: Narayan, Sanath, Ramakrishnan, KR
Publikováno v: IndraStra Global.
In this paper we present a segmentation algorithm to extract foreground object motion in a moving camera scenario without any preprocessing step such as tracking selected features, video alignment, or foreground segmentation. By viewing it as a curve
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=issn23813652::f7451c4f0bd580293d700a62658161e0
https://igi.indrastra.com/items/show/197004
Zobrazit plný text záznamu
6
A post processing technique for improved harmonic/percussion separation in polyphonic speech
Autor: Thoshkahna, Balaji, Ramakrishnan, KR
Publikováno v: IndraStra Global.
In this paper we propose a postprocessing technique for a spectrogram diffusion based harmonic/percussion decom- position algorithm. The proposed technique removes har- monic instrument leakages in the percussion enhanced out- puts of the baseline al
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=issn23813652::fdd109a44d4b9b8743f0a8d264965b2d
https://igi.indrastra.com/items/show/196969
Zobrazit plný text záznamu
7
Parts based representation for pedestrian using NMF with robustness to partial occlusion
Autor: Shankar, Naveen N, Ramakrishnan, KR
Publikováno v: IndraStra Global.
Computer Vision has seen a resurgence in the parts-based representation for objects over the past few years. The parts are usually annotated beforehand for training. We present an annotation free parts-based representation for the pedestrian using No
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=issn23813652::7f316a84a97d5d8c8b893bf1c78e999e
https://igi.indrastra.com/items/show/196014
Zobrazit plný text záznamu
8
Learning Feature Trajectories Using Gabor Filter Bank for Human Activity Segmentation and Recognition
Autor: Gupta, Sunil Kumar, Kumar, Y Senthil, Ramakrishnan, KR
Publikováno v: IndraStra Global.
We describe a novel method for human activity segmentation and interpretation in surveillance applications based on Gabor filter-bank features. A complex human activity is modeled as a sequence of elementary human actions like walking, running, joggi
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=issn23813652::3141a382d6dc28a76677bf119f385947
http://eprints.iisc.ac.in/26495/1/getPDF.pdf
Zobrazit plný text záznamu
10
Novel melody line identification algorithm for polyphonic MIDI music
Autor: Velusamy, Sudha, Thoshkahna, Balaji, Ramakrishnan, KR
Publikováno v: IndraStra Global.
The problem of automatic melody line identification in a MIDI file plays an important role towards taking QBH systems to the next level. We present here, a novel algorithm to identify the melody line in a polyphonic MIDI file. A note pruning and trac
Externí odkaz: https://explore.openaire.eu/search/publication?articleId=issn23813652::1275a3dcf5a59af1b97322bc0f617c49
http://eprints.iisc.ac.in/26572/1/fullt.pdf
Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání

Omezení vyhledávání
Plný text Recenzováno Digitální knihovna AV ČR
Zdroje