paper-with-me

Papers

Strokelets: A Learned Multi-Scale Representation for Scene Text Recognition

2014-06-01 · CVPR 2014 6 · Cong Yao, Xiang Bai, Baoguang Shi, Wenyu Liu

Driven by the wide range of applications, scene text detection and recognition have become active research topics in computer vision. Though extensively studied, localizing and reading text in uncontrolled environments remain extremely challenging, due to various interference factors. In this paper, we propose a novel multi-scale representation for scene text recognition. This representation consists of a set of detectable primitives, termed as strokelets, which capture the essential substructures of characters at different granularities. Strokelets possess four distinctive advantages: (1) Usability: automatically learned from bounding box labels; (2) Robustness: insensitive to interference factors; (3) Generality: applicable to variant languages; and (4) Expressivity: effective at describing characters. Extensive experiments on standard benchmarks verify the advantages of strokelets and demonstrate the effectiveness of the proposed algorithm for text recognition.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Scene Text DetectionScene Text RecognitionText Detection

Similar Papers 제목 키워드 기반

Visuomotor Understanding for Representation Learning of Driving Scenes

2019-09-16 · Seokju Lee, Junsik Kim, Tae-Hyun Oh, Yongseop Jeong 외

Dashboard cameras capture a tremendous amount of driving scene video each day. These videos are purposefully coupled with vehicle sensing data, such as from the speedometer and inertial sensors, providing an additional s…

Optical Flow EstimationRepresentation LearningScene UnderstandingSemantic Segmentation

Shape2Scene: 3D Scene Representation Learning Through Pre-training on Shape Data

2024-07-14 · Tuo Feng, Wenguan Wang, Ruijie Quan, Yi Yang

Current 3D self-supervised learning methods of 3D scenes face a data desert issue, resulting from the time-consuming and expensive collecting process of 3D scene data. Conversely, 3D shape datasets are easier to collect.…

3D Object Detection3D Semantic Segmentationobject-detectionObject Detection+4

Block-NeRF: Scalable Large Scene Neural View Synthesis

2022-02-10 · CVPR 2022 1 · Matthew Tancik, Vincent Casser, Xinchen Yan, Sabeek Pradhan 외

We present Block-NeRF, a variant of Neural Radiance Fields that can represent large-scale environments. Specifically, we demonstrate that when scaling NeRF to render city-scale scenes spanning multiple blocks, it is vita…

NeRF

SceneDreamer: Unbounded 3D Scene Generation from 2D Image Collections

2023-02-02 · Zhaoxi Chen, Guangcong Wang, Ziwei Liu

In this work, we present SceneDreamer, an unconditional generative model for unbounded 3D scenes, which synthesizes large-scale 3D landscapes from random noise. Our framework is learned from in-the-wild 2D image collecti…

Scene Generation

Multimodal Scale Consistency and Awareness for Monocular Self-Supervised Depth Estimation

2021-03-03 · Hemang Chawla, Arnav Varma, Elahe Arani, Bahram Zonooz

Dense depth estimation is essential to scene-understanding for autonomous driving. However, recent self-supervised approaches on monocular videos suffer from scale-inconsistency across long sequences. Utilizing data from…

Autonomous DrivingDepth EstimationMonocular Depth EstimationScene Understanding