Filters








52 Hits in 1.5 sec

Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models [article]

Ashwin K Vijayakumar, Michael Cogswell, Ramprasath R. Selvaraju, Qing Sun, Stefan Lee, David Crandall, Dhruv Batra
2018 arXiv   pre-print
is the maximum value of the metric over a list of k potential solutions.  ...  For each partial solution, the set of |V| continuations are sorted and assigned intra-sibling ranks k ∈ [L] in order of decreasing log-probabilities, θ t (y t ).  ... 
arXiv:1610.02424v2 fatcat:jskj532wabelpfq32cmpbmlsdi

We are Humor Beings: Understanding and Predicting Visual Humor

Arjun Chandrasekaran, Ashwin K. Vijayakumar, Stanislaw Antol, Mohit Bansal, Dhruv Batra, C. Lawrence Zitnick, Devi Parikh
2016 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
A modification to this baseline is to replace K objects that are least similar to the scene. Based on performance on the validation set, T and K are determined to be 0.8 and 4, respectively. Model.  ...  Priors (do not replace) 39.93 % 79.86% Priors (object's tendency to be replaced) 73.13 % 71.5% Anomaly detection (threshold distance) 62.16 % 58.30% Anomaly detection (top-K objects) 63.01 % 64.31%  ... 
doi:10.1109/cvpr.2016.498 dblp:conf/cvpr/ChandrasekaranV16 fatcat:uvwvj6rxgbga7b5j6kmrpupo4e

Sound-Word2Vec: Learning Word Representations Grounded in Sounds [article]

Ashwin K Vijayakumar, Ramakrishna Vedantam, Devi Parikh
2017 arXiv   pre-print
We then use K-Means algorithm to cluster the sounds in this feature space to assign each sound to a cluster C(s) ∈ {1, . . . K}.  ...  We set K to 30 by evaluating the performance of the embeddings on text-based audio-retrieval on the held out validation set.  ... 
arXiv:1703.01720v4 fatcat:cy652b52sjfm7e7zi26ex23spe

We Are Humor Beings: Understanding and Predicting Visual Humor [article]

Arjun Chandrasekaran, Ashwin K. Vijayakumar, Stanislaw Antol, Mohit Bansal, Dhruv Batra, C. Lawrence Zitnick, Devi Parikh
2016 arXiv   pre-print
A modification to this baseline is to replace K objects that are least similar to the scene. Based on performance on the validation set, T and K are determined to be 0.8 and 4, respectively. Model.  ...  Priors (do not replace) 50% % 79.86% Priors (object's tendency to be replaced) 73.13 % 71.5% Anomaly detection (threshold distance) 62.16 % 58.30% Anomaly detection (top-K objects) 63.01 % 64.31%  ... 
arXiv:1512.04407v4 fatcat:xui3va77wbfmtjioqzzf7krnae

Optical modeling of a line-scan optical coherence tomography system for high-speed three-dimensional endoscopic imaging

Mohammad Kamal, Narayanswamy Sivakumar, Muthukumaran Packirisamy, Réal Vallée
2009 Photonics North 2009  
Avinash K.  ...  Arvind Chandrasekaran, Muthukumaran Packirisamy, Subhash Rakheja, Vijayakumar Devabhaktuni, 2007, "A hybrid integrated microfluidic Lab-On-a-Chip on silicon platform for high throughput bio-Assays" International  ... 
doi:10.1117/12.839593 fatcat:fglaerbklzeczlwklk2h2qyt4q

Table of Contents

2020 2020 International Conference on Communication and Signal Processing (ICCSP)  
Vijayakumar, Ditipriya Gorai, Nitin Chauhan and Ujjawal Kant 1447 297.  ...  Ashwin and V. Sivasankaran 1472 303. Interocular Distance Based Facial Recognition Sundar G, Varsha Anand and Anita J P 1478 304.  ... 
doi:10.1109/iccsp48568.2020.9182154 fatcat:xalvxgme3zhnle4i7ko5d62cbu

Trainable Decoding of Sets of Sequences for Neural Sequence Models

Ashwin Kalyan, Peter Anderson, Stefan Lee, Dhruv Batra
2019 International Conference on Machine Learning  
argmax-K Yt−1×V k∈[K] t∈[T ] P(y k t |y k ≤t−1 , x) (3) where argmax-K selects the K maximizing alternatives.  ...  C t \S k−1 s k ∼ softmax g k /τ S k ← S k−1 ∪ {s k } end Y t = S K end return Y T Sequential Subset Selection.  ... 
dblp:conf/icml/KalyanALB19 fatcat:4oitykz47fb23eeiwgaxtofl5e

Acknowledgment of Reviewers

Arturo Casadevall
2016 mBio  
Arthur David Askew Ina Atrée Taeok Bae Fabio Bagnoli Joel Baines Mona Bajaj-Elliot David Baker Nathalie Balaban Ashwin  ...  Verstrepen Laura Via Marco Vignuzzi Waldemar Vollmer Veronika von Messling Andreas Wack Stephen Waggoner Matthew Waldor K.  ... 
doi:10.1128/mbio.00195-16 fatcat:owmddwqj55el7cxiktufpfoizi

Table of Contents

2022 2022 6th International Conference on Trends in Electronics and Informatics (ICOEI)  
Deepika, K. P.  ...  Aiswarya Lakshmi, K.  ... 
doi:10.1109/icoei53556.2022.9776703 fatcat:a27s7bvq2rhwxelwrpkfaxwtau

Progressive Failure Analysis of Laminated Composite Plates with Elliptical or Circular Cutout Using Finite Element Method

A Lakshminarayana, R Vijayakumar, G Krishnamohana Rao
2016 IOP Conference Series: Materials Science and Engineering  
Composite Turbine Blade Using Puck Failure Criteria M Ozyildiz, C Muyan and D Coker -Effect of magnetostrictive material layer on the stress and deformation behaviour of laminated structure S D Suman, C K  ...  Singh S.B and Ashwin K presented [5,6] the post buckling behaviour and progressive failure response of symmetric laminates under uniaxial compression and uniaxial compression combined with in-plane positive  ...  Parma Nand Jah and Ashwin Kumar [13] used non-linear finite element method to study the first ply failure load of thin laminated composite plates under combined effect of in-plane (shear and uniaxial  ... 
doi:10.1088/1757-899x/149/1/012104 fatcat:oc3iqye4afa35hyeigq7loibsy

Table of Contents

2021 2021 International Conference on Technological Advancements and Innovations (ICTAI)  
K.  ...  Gowtham, K. Naveen, H.  ... 
doi:10.1109/ictai53825.2021.9673182 fatcat:k5xao4z4b5getd2xdh2g6ccdda

A Kannada Document Image Retrieval System based on Correlation Method

Chandrakala HT
2013 International Journal of Computer Applications  
REFERENCES [3] Bansal V, Sinha R M K 1999 "On how to describe shapes of Devanagari characters and use them for recognition.  ...  An OCR (Optical Character Recognition) system for Kannada script is described by Ashwin T V et al 2002[2] using Support Vector Machine (SVM) classifiers.  ... 
doi:10.5120/13377-0989 fatcat:267vqp6dknbkzowxn2dwsus2ca

Exploring Model Consensus to Generate Translation Paraphrases

Zhenhao Li, Marina Fomicheva, Lucia Specia
2020 Proceedings of the Fourth Workshop on Neural Generation and Translation  
Ashwin K Vijayakumar, Michael Cogswell, Ramprasath R Selvaraju, Qing Sun, Stefan Lee, David Crandall, and Dhruv Batra. 2016.  ...  We also experimented with different data filtering strategies on the STAPLE dataset by only keeping the top-K translations with the highest weights (we refer to this as tune-K).  ... 
doi:10.18653/v1/2020.ngt-1.19 dblp:conf/aclnmt/LiFS20 fatcat:yvfn4bjkabg5ncaonzajxva7ki

Percolating Plastic Failure as a Mechanism for Shear Softening in Amorphous Solids [article]

Vijayakumar Chikkadi, Oleg Gendelman, Valery Ilyin, J Ashwin and Itamar Procaccia
2013 arXiv   pre-print
(k + 2q)!! (k − 2)!!(k + 2l)!! x −(k+2l) c . (6) We chose the parameters x c = 7/4, k = 10 and q = 6.  ...  Temperature was measured in units of ǫ SL /k B where k B is Boltzmann's constant.  ... 
arXiv:1312.4136v1 fatcat:qocltpungnan3c6frou5avkyay

Technical Session Schedule

2021 2021 Innovations in Power and Advanced Computing Technologies (i-PACT)  
VIJAYAKUMAR, S.  ...  K.  ... 
doi:10.1109/i-pact52855.2021.9696846 fatcat:x4os34tvsvb7hoxfvhprrkjdla
« Previous Showing results 1 — 15 out of 52 results