A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Filters
Accurate Scene Text Detection via Scale-Aware Data Augmentation and Shape Similarity Constraint
2021
IEEE transactions on multimedia
Preserved Fulltext
Scene text detection has attracted increasing concerns with the rapid development of deep neural networks in recent years. ...
However, existing scene text detectors may overfit on the public datasets due to the limited training data, or generate inaccurate localization for arbitrary-shape scene texts. ...
on the public arbitrary-shape scene text benchmarks. ...
doi:10.1109/tmm.2021.3073575
fatcat:r4rgthwbk5cw3boixvko3zbpoi
All You Need is a Second Look: Towards Arbitrary-Shaped Text Detection
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
In this paper, we propose a two-stage segmentation-based detector, termed as NASK (Need A Second looK), for arbitrary-shaped text detection. ...
Arbitrary-shaped text detection is a challenging task since curved texts in the wild are of the complex geometric layouts. ...
EAST [18] is another one-stage based detector which directly predicts text instances with arbitrary orientations and quadrilateral shapes in full images. Liao et al. ...
arXiv:2106.12720v1
fatcat:3h3dt2ofundwrpenf2uqdgrv6a
Location-Aware Feature Selection Text Detection Network
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
However, they are behind in accuracy comparing with recent segmentation-based text detectors. ...
To address this issue, we propose a novel Location-Aware feature Selection text detection Network (LASNet). ...
It realizes text detection of arbitrary shape. ...
arXiv:2004.10999v2
fatcat:27rnkktwzfbc7cbxuq5v4lljr4
Cluttered TextSpotter: An End-to-End Trainable Light- weight Scene Text Spotter for Cluttered Environment
2020
IEEE Access
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
It helps to localize in scene images with background clutters, where partially occluded text parts, truncation artifacts, and perspective distortions are present. ...
Scene text spotting aims at simultaneously localizing and recognizing text instances, symbols, and logos in natural scene images. ...
In [46] , arbitrary shape text is detected by extracting text proposals, which are refined using a recurrent neural network (RNN) and an adaptive number of boundary points. ...
doi:10.1109/access.2020.3002808
fatcat:x4kbcajahrc5vgtuxsc6oyyjsa
Learning Pixel Affinity Pyramid for Arbitrary-Shaped Text Detection
2022
ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
, denoting its superior capability in detecting arbitrary-shaped texts. ...
boundary description for separating closely located texts. ...
in the arbitrary-shaped text detection. ...
doi:10.1145/3524617
fatcat:wccolxaysndjxg5nijush7ayte
Axis Learning for Orientated Objects Detection in Aerial Images
2020
Remote Sensing
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Besides, a new aspect-ratio-aware orientation centerness method is proposed to better weigh positive pixel points, in order to guide the network to learn discriminative features from a complex background ...
The method is tested on two common aerial image datasets, achieving better performance compared with most one-stage orientated methods and many two-stage anchor-based methods with a simpler procedure and ...
achieved great performances with aerial images such as the DOTA dataset or on natural scene-text detection such as MSRA-TD500. ...
doi:10.3390/rs12060908
fatcat:ohce7ratdneqpgmvvjtzuozk6q
PoseDet: Fast Multi-Person Pose Estimation Using Pose Embedding
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Moreover, we propose the keypoint-aware pose embedding to represent an object in terms of the locations of its keypoints. ...
Extensive experiments on the CrowdPose benchmark show the robustness in the crowd scenes. Source code is available. ...
Figure 1 : 1 Keypoint-aware pose embedding usually detect person instances by using a person detector, then estimate the single-person pose within the detected box. ...
arXiv:2107.10466v2
fatcat:v74qs67sajakdm7xemmgifsgru
A Survey of Visual Transformers
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Because of their competitive modeling capabilities, the visual Transformers have achieved impressive performance improvements over multiple benchmarks as compared with modern Convolution Neural Networks ...
Furthermore, we have revealed a series of essential but unexploited aspects that may empower such visual Transformers to stand out from numerous architectures, e.g., slack high-level semantic embeddings ...
We use standard learnable 1D position embeddings, since we have not observed significant performance gains from using more advanced 2D-aware position embeddings (Appendix D.3). ...
arXiv:2111.06091v3
fatcat:a3fq6lvvzzgglb3qtus5qwrwpe
Quadbox: Quadrilateral Bounding Box Based Scene Text Detection Using Vector Regression
2021
IEEE Access
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Scene text appears with a wide range of sizes and arbitrary orientations. ...
For detecting such text in the scene image, the quadrilateral bounding boxes provide a much tight bounding box compared to the rotated rectangle. ...
With proposed properties, the model can detect horizontal, arbitrary oriented, and arbitrary shaped text. ...
doi:10.1109/access.2021.3063030
fatcat:2c2hezixrrejhhxt6p2uapqona
Context Encoders: Feature Learning by Inpainting
2016
2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
with removing arbitrary shapes vious methods.
from images, obtained from random masks in the PASCAL
VOC 2012 dataset [12]. ...
Input Context Context Encoder Content-Aware Fill
Figure 5: Comparison with Content-Aware Fill (Photoshop 5. Evaluation
feature based on [2]). ...
doi:10.1109/cvpr.2016.278
dblp:conf/cvpr/PathakKDDE16
fatcat:dpxpf3ircjgxzenfnmzyv6o6nu
Multimodal Learning with Transformers: A Survey
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Transformer is a promising neural network learner, and has achieved great success in various machine learning tasks. ...
CONCLUSION This survey focuses on multimodal machine learning with Transformers. We reviewed the landscape by introducing the Transformer designs and training in the multimodal contexts. ...
this survey gives a helpful and detailed overview for new researchers and practitioners, provides a convenient reference for relevant experts (e.g., multimodal machine learning researchers, Transformer network ...
arXiv:2206.06488v1
fatcat:6aoaczzbtvc43my2kmobo7glvy
2021 Index IEEE Transactions on Image Processing Vol. 30
2021
IEEE Transactions on Image Processing
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
., +, TIP 2021 1116-1129 MABAN: Multi-Agent Boundary-Aware Network for Natural Language Moment Retrieval. ...
Yang, L., +, TIP 2021 39-54 MABAN: Multi-Agent Boundary-Aware Network for Natural Language Moment Retrieval. ...
doi:10.1109/tip.2022.3142569
fatcat:z26yhwuecbgrnb2czhwjlf73qu
Learning Neural Textual Representations for Citation Recommendation
2021
2020 25th International Conference on Pattern Recognition (ICPR)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Qian, Xijun; Liu, Yifan; Yang Yu-
Bin
924
PS T4.2
An Accurate Threshold Insensitive Kernel Detector for Arbitrary
Shaped Text
DAY 4 -Jan 15, 2021 -DAY 2 -Jan 13, 2021
Live
Dasgupta, Kinjal; ...
4.2
An Accurate Threshold Insensitive Kernel Detector for Arbitrary
Shaped Text
DAY 4 -Jan 15, 2021 -DAY 2 -Jan 13, 2021
Dasgupta, Kinjal; Das, Sudip;
Bhattacharya, Ujjwal
955
OS T 4.2
Stratified ...
doi:10.1109/icpr48806.2021.9412725
fatcat:3vge2tpd2zf7jcv5btcixnaikm
A Survey of Deep Learning-based Object Detection
2019
IEEE Access
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
With the rapid development of deep learning networks for detection tasks, the performance of object detectors has been greatly improved. ...
Afterwards and primarily, we provide a comprehensive overview of a variety of object detection methods in a systematic manner, covering the one-stage and two-stage detectors. ...
These methods have difficulties to deal with the large aspect ratios and arbitrary-orientation of scene text. ...
doi:10.1109/access.2019.2939201
fatcat:jesz2av2tjbkxfpaqyecptgls4
Oriented Object Detection in Remote Sensing Images with Anchor-Free Oriented Region Proposal Network
2022
Remote Sensing
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Currently, mainstream oriented object detectors are based on densely placed predefined anchors. ...
To address the problem, this paper proposes a novel anchor-free two-stage oriented object detector. ...
Based on Faster-RCNN [13] , RRPN [23] uses Rotation RPN and Rotation RoI pooling for arbitrary-oriented text detection. ...
doi:10.3390/rs14051246
fatcat:hsnpxrds45a5dbkgkfgbdrc43u
« Previous
Showing results 1 — 15 out of 186 results