Výsledky vyhledávání

Improving Semantic Segmentation via Efficient Self-Training

Autor: Yi Zhu, Zhongyue Zhang, Chongruo Wu, Zhi Zhang, Tong He, Hang Zhang, R Manmatha, Mu Li, Alexander J Smola

Publikováno v: IEEE transactions on pattern analysis and machine intelligence.

Starting from the seminal work of Fully Convolutional Networks (FCN), there has been significant progress on semantic segmentation. However, deep learning models often require large amounts of pixelwise annotations to train accurate and robust models

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a5ff7b0c00b374a6e60a3ba3d6824538
https://pubmed.ncbi.nlm.nih.gov/34951840

Zobrazit plný text záznamu

Akademický článek

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

DocFormer: End-to-End Transformer for Document Understanding

Autor: Srikar Appalaraju, Bhavan Jasani, Bhargava Urala Kota, Yusheng Xie, R. Manmatha

We present DocFormer -- a multi-modal transformer based architecture for the task of Visual Document Understanding (VDU). VDU is a challenging problem which aims to understand documents in their varied formats (forms, receipts etc.) and layouts. In a

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::355c4a6a8697c19b2b01f6b77af88c1f
http://arxiv.org/abs/2106.11539

Zobrazit plný text záznamu

Saliency Driven Perceptual Image Compression

Autor: R. Manmatha, Yash Patel, Srikar Appalaraju

Publikováno v: WACV

This paper proposes a new end-to-end trainable model for lossy image compression, which includes several novel components. The method incorporates 1) an adequate perceptual similarity metric; 2) saliency in the images; 3) a hierarchical auto-regressi

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::f4693647c4a81b6631cb640bc0dc45dd
https://doi.org/10.1109/wacv48630.2021.00027

Zobrazit plný text záznamu

ResNeSt: Split-Attention Networks

Autor: Hang Zhang, Chongruo Wu, Zhongyue Zhang, Yi Zhu, Haibin Lin, Zhi Zhang, Yue Sun, Tong He, Jonas Mueller, R. Manmatha, Mu Li, Alexander Smola

It is well known that featuremap attention and multi-path representation are important for visual recognition. In this paper, we present a modularized architecture, which applies the channel-wise attention on different network branches to leverage th

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::7e36b4f1135cce7f906520035eb619ea
http://arxiv.org/abs/2004.08955

Zobrazit plný text záznamu

SCATTER: Selective Context Attentional Scene Text Recognizer

Autor: Shahar Tsiper, R. Manmatha, Oron Anschel, Roee Litman, Ron Litman, Shai Mazor

Publikováno v: CVPR

Scene Text Recognition (STR), the task of recognizing text against complex image backgrounds, is an active area of research. Current state-of-the-art (SOTA) methods still struggle to recognize text written in arbitrary shapes. In this paper, we intro

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::413d34bbfe68c6981641263036796e2d

Zobrazit plný text záznamu

Sequence-to-Sequence Contrastive Learning for Text Recognition

Autor: Oron Anschel, Shai Mazor, Ron Litman, Shahar Tsiper, Aviad Aberdam, R. Manmatha, Pietro Perona, Ron Slossberg

Publikováno v: CVPR

We propose a framework for sequence-to-sequence contrastive learning (SeqCLR) of visual representations, which we apply to text recognition. To account for the sequence-to-sequence structure, each feature map is divided into different instances over

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3c8ad4d49d82fdfb5664597c43fba3f6

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání