• Publications
  • Influence
Robust Text Detection in Natural Scene Images
TLDR
An accurate and robust method for detecting texts in natural scene images using a fast and effective pruning algorithm to extract Maximally Stable Extremal Regions (MSERs) as character candidates using the strategy of minimizing regularized variations is proposed.
Robust Text Detection in Natural Scene Images.
TLDR
An accurate and robust method for detecting texts in natural scene images using a fast and effective pruning algorithm to extract Maximally Stable Extremal Regions (MSERs) as character candidates using the strategy of minimizing regularized variations is proposed.
GAT: Generative Adversarial Training for Adversarial Example Detection and Robust Classification
TLDR
This paper partition the input space into subspaces and train adversarial robust subspace detectors using asymmetrical adversarial training (AAT), and demonstrates that AAT promotes the learning of class-conditional distributions, which further gives rise to generative detection/classification approaches that are both robust and more interpretable.
Obj2Text: Generating Visually Descriptive Language from Object Layouts
TLDR
OBJ2TEXT is explored, a sequence-to-sequence model that encodes a set of objects and their locations as an input sequence using an LSTM network, and decodes this representation using anLSTM language model and shows that this model despite using a sequence encoder can effectively represent complex spatial object-object relationships.
A new framework to evaluate ecosystem health: a case study in the Wei River basin, China
TLDR
The index of ecosystem health is applied in the Guanzhong district, and thecosystem health was fair, and there is a trend that the ecosystem health in the upstream was better than that in the downstream.
Cell Image Classification: A Comparative Overview
TLDR
Three main approaches for cell image classification most often used are reviewed: numerical feature extraction, end‐to‐end classification with neural networks (NNs), and transport‐based morphometry (TBM), and comparison outcomes are discussed with the aim of clarifying the advantages and disadvantages of each method.
Adversarial Example Detection and Classification With Asymmetrical Adversarial Training
TLDR
This paper presents an adversarial example detection method that provides performance guarantee to norm constrained adversaries, and uses the learned class conditional generative models to define generative detection/classification models that are both robust and more interpretable.
Privacy Partitioning: Protecting User Data During the Deep Learning Inference Phase
TLDR
The experimental results indicate that this approach can be used to significantly attenuate the capacity for an adversary with access to the state-of-the-art deep network's intermediate states to learn privacy-sensitive inputs to the network.
Classifier comparison for MSER-based text classification in scene images
TLDR
This work argues that MSER based character candidates extraction and Bayesian Logistic Regression based text classification are two prominent and potential techniques in scene text detection.
Effective text localization in natural scene images with MSER, geometry-based grouping and AdaBoost
TLDR
A novel and effective approach to accurately localize scene texts in natural scene images by extracting Maximally stable extremal regions (MSER) and constructing candidate regions by grouping similar letter candidates using disjoint set.
...
...