Video Text Detection

Lu, Tiecheng; Palaiahnakote, Shivakumara; Tan, Chew Lim; Wenyin, Liu

doi:10.1007/978-1-4471-6515-6

Cited by 57 publications

(4 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We then combine the two representations to form the scene embedding (the late fusion as shown in the figure). This late fusion allows the downstream prediction to give more emphasis to the separated feature, which may be lost in early fusion (Lu et al [30]). Late fusion of the metric properties along with the hidden states of objects obtained through the GCN ensures that information like object position and size are available when predicting tool likelihoods.…”

Section: B Fusion Of Metric and Semantic Attributes (+Metric)mentioning

confidence: 99%

ToolNet: Using Commonsense Generalization for Predicting Tool Use for Robot Plan Synthesis

Rajas¹,

Tuli²,

Paul³

et al. 2020

Preprint

View full text Add to dashboard Cite

A robot working in a physical environment (like home or factory) needs to learn to use various available tools for accomplishing different tasks, for instance, a mop for cleaning and a tray for carrying objects. The number of possible tools is large and it may not be feasible to demonstrate usage of each individual tool during training. Can a robot learn commonsense knowledge and adapt to novel settings where some known tools are missing, but alternative unseen tools are present? We present a neural model that predicts the best tool from the available objects for achieving a given declarative goal. This model is trained by user demonstrations, which we crowd-source through humans instructing a robot in a physics simulator. This dataset maintains user plans involving multi-step object interactions along with symbolic state changes. Our neural model, TOOLNET, combines a graph neural network to encode the current environment state, and goal-conditioned spatial attention to predict the appropriate tool. We find that providing metric and semantic properties of objects, and pre-trained object embeddings derived from a commonsense knowledge repository such as ConceptNet, significantly improves the model's ability to generalize to unseen tools. The model makes accurate and generalizable tool predictions. When compared to a graph neural network baseline, it achieves 14-27% accuracy improvement for predicting known tools from new world scenes, and 44-67% improvement in generalization for novel objects not encountered during training.

show abstract

Section: B Fusion Of Metric and Semantic Attributes (+Metric)mentioning

confidence: 99%

ToolNet: Using Commonsense Generalization for Predicting Tool Use for Robot Plan Synthesis

Rajas¹,

Tuli²,

Paul³

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…In the last several years the leading positions in the area of text detection and recognition are occupied by neural networks methods [8] [9], but they have some drawbacks [5].…”

Section: Related Workmentioning

confidence: 99%

A low computational approach for price tag recognition

Aliev¹,

Nikolaev

Kunina³

et al. 2020

Twelfth International Conference on Machine Vision (ICMV 2019)

View full text Add to dashboard Cite

In this work we discuss the task of search, localization and recognition of price zone within a photograph of the price tag. The task is being addressed for the case when image is acquired by small-scale digital camera and calculation device has significant resource constraints. The proposed approach is based on Niblack binarization algorithm, analysis and clasterization of connected components in conditions of known price tag geometrical model. The algorithm was tested on a private dataset and has shown high quality.

show abstract

“…Recently, several approaches have been proposed to detect and recognize texts in videos and natural scene images [1,2,15,16].…”

Section: Literature Reviewmentioning

confidence: 99%

“…Prior work has addressed specific research problems that have bordered on printed and handwritten texts in scanned documents. Recently, embedded text in videos has received increasing attention as it often gives crucial information about the media content [1][2][3]. News videos generally contain two types of texts [2]: scene text and artificial text ( Figure 1).…”

Section: Introductionmentioning

confidence: 99%

Open Datasets and Tools for Arabic Text Detection and Recognition in News Video Frames

et al. 2018

View full text Add to dashboard Cite

Abstract:Recognizing texts in video is more complex than in other environments such as scanned documents. Video texts appear in various colors, unknown fonts and sizes, often affected by compression artifacts and low quality. In contrast to Latin texts, there are no publicly available datasets which cover all aspects of the Arabic Video OCR domain. This paper describes a new well-defined and annotated Arabic-Text-in-Video dataset called AcTiV 2.0. The dataset is dedicated especially to building and evaluating Arabic video text detection and recognition systems. AcTiV 2.0 contains 189 video clips serving as a raw material for creating 4063 key frames for the detection task and 10,415 cropped text images for the recognition task. AcTiV 2.0 is also distributed with its annotation and evaluation tools that are made open-source for standardization and validation purposes. This paper also reports on the evaluation of several systems tested under the proposed detection and recognition protocols.

show abstract

Video Text Detection

Cited by 57 publications

References 5 publications

ToolNet: Using Commonsense Generalization for Predicting Tool Use for Robot Plan Synthesis

ToolNet: Using Commonsense Generalization for Predicting Tool Use for Robot Plan Synthesis

A low computational approach for price tag recognition

Open Datasets and Tools for Arabic Text Detection and Recognition in News Video Frames

Contact Info

Product

Resources

About