Sledovat
Yash Patel
Yash Patel
Amazon Web Services AI
E-mailová adresa ověřena na: amazon.com - Domovská stránka
Název
Citace
Citace
Rok
Icdar2017 robust reading challenge on multi-lingual scene text detection and script identification-rrc-mlt
N Nayef, F Yin, I Bizid, H Choi, Y Feng, D Karatzas, Z Luo, U Pal, ...
2017 14th IAPR international conference on document analysis and recognition …, 2017
4252017
ICDAR2019 Robust Reading Challenge on Multi-lingual Scene Text Detection and Recognition--RRC-MLT-2019
N Nayef*, Y Patel*, M Busta, PN Chowdhury, D Karatzas, W Khlif, J Matas, ...
International Conference on Document Analysis and Recognition (ICDAR), 2019
2642019
Self-supervised learning of visual features through embedding images into text topic spaces
L Gomez*, Y Patel*, M Rusiñol, D Karatzas, CV Jawahar
Proceedings of the IEEE Conference on Computer Vision and Pattern …, 2017
1272017
E2e-mlt-an unconstrained end-to-end method for multi-language scene text
M Bušta, Y Patel, J Matas
Asian conference on computer vision, 127-143, 2018
892018
Filtering, Distillation, and Hard Negatives for Vision-Language Pre-Training
F Radenovic, A Dubey, A Kadian, T Mihaylov, S Vandenhende, Y Patel, ...
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023
572023
Recall@k Surrogate Loss with Large Batches and Similarity Mixup
Y Patel, G Tolias, J Matas
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022
552022
Saliency driven perceptual image compression
Y Patel, S Appalaraju, R Manmatha
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer …, 2021
452021
Deep Perceptual Compression
Y Patel, S Appalaraju, R Manmatha
arXiv preprint arXiv:1907.08310, 2019
34*2019
Human perceptual evaluations for image compression
Y Patel, S Appalaraju, R Manmatha
arXiv preprint arXiv:1908.04187, 2019
272019
Dynamic lexicon generation for natural scene images
Y Patel, L Gomez, M Rusinol, D Karatzas
Computer Vision–ECCV 2016 Workshops: Amsterdam, The Netherlands, October 8 …, 2016
242016
E2E-MLT-an unconstrained end-to-end method for multi-language scene text
Y Patel¹, M Bušta¹, J Matas¹
222018
DocILE Benchmark for Document Information Localization and Extraction
Š Šimsa, M Šulc, M Uřičář, Y Patel, A Hamdi, M Kocián, M Skalický, ...
International Conference on Document Analysis and Recognition (ICDAR), 2023
202023
Plant recognition by AI: Deep neural nets, transformers, and kNN in deep embeddings
L Picek, M Šulc, Y Patel, J Matas
Frontiers in plant science 13, 787527, 2022
192022
Learning Surrogates via Deep Embedding
Y Patel, T Hodan, J Matas
European Conference on Computer Vision (ECCV), 2020
192020
Generalized Differentiable RANSAC
T Wei, Y Patel, A Shekhovtsov, J Matas, D Barath
International Conference on Computer Vision (ICCV), 2023
18*2023
Self-supervised visual representations for cross-modal retrieval
Y Patel, L Gomez, M Rusiñol, D Karatzas, CV Jawahar
Proceedings of the 2019 on International Conference on Multimedia Retrieval …, 2019
162019
Neural Network-based Acoustic Vehicle Counting
S Djukanović, Y Patel, J Matas, T Virtanen
European Signal Processing Conference (EUSIPCO), 2021
112021
Learned lossy image compression codec
S Appalaraju, R Manmatha, Y Patel
US Patent 10,909,728, 2021
82021
Hierarchical auto-regressive model for image compression incorporating object saliency and a deep perceptual loss
Y Patel, S Appalaraju, R Manmatha
arXiv preprint arXiv:2002.04988 7, 2020
82020
Learning Sampling Policies for Domain Adaptation
Y Patel*, K Chitta*, B Jasani*
arXiv preprint arXiv:1805.07641, 2018
82018
Systém momentálně nemůže danou operaci provést. Zkuste to znovu později.
Články 1–20