Detecting Text in Natural Image with Connectionist Text Proposal Network
- Zhi Tian, Weilin Huang, Tong He, Pan He, Y. Qiao
- Computer ScienceEuropean Conference on Computer Vision
- 12 September 2016
A novel Connectionist Text Proposal Network (CTPN) that accurately localizes text lines in natural image and develops a vertical anchor mechanism that jointly predicts location and text/non-text score of each fixed-width proposal, considerably improving localization accuracy.
Adversarial Examples: Attacks and Defenses for Deep Learning
- Xiaoyong Yuan, Pan He, Qile Zhu, Xiaolin Li
- Computer ScienceIEEE Transactions on Neural Networks and Learning…
- 19 December 2017
The methods for generating adversarial examples for DNNs are summarized, a taxonomy of these methods is proposed, and three major challenges in adversarialExamples are discussed and the potential solutions are discussed.
Single Shot Text Detector with Regional Attention
- Pan He, Weilin Huang, Tong He, Qile Zhu, Y. Qiao, Xiaolin Li
- Computer ScienceIEEE International Conference on Computer Vision
- 1 September 2017
A novel single-shot text detector that directly outputs word-level bounding boxes in a natural image and develops a hierarchical inception module which efficiently aggregates multi-scale inception features.
Reading Scene Text in Deep Convolutional Sequences
- Pan He, Weilin Huang, Y. Qiao, Chen Change Loy, Xiaoou Tang
- Computer ScienceAAAI Conference on Artificial Intelligence
- 14 June 2015
A deep recurrent model is developed to robustly recognize the generated CNN sequences, departing from most existing approaches recognising each character independently, achieving impressive results on several benchmarks, advancing the state-of-the-art substantially.
Efficient Iterative Amortized Inference for Learning Symmetric and Disentangled Multi-Object Representations
- Patrick Emami, Pan He, S. Ranka, A. Rangarajan
- Computer ScienceInternational Conference on Machine Learning
- 7 June 2021
This work introduces EfficientMORL, an efficient framework for the unsupervised learning of object-centric representation learning that demonstrates strong object decomposition and disentanglement on the standard multi-object benchmark while achieving nearly an order of magnitude faster training and test time inference over the previous state-of-theart model.
Adaptive Adversarial Attack on Scene Text Recognition
- Xiaoyong Yuan, Pan He, Xiaolin Li
- Computer ScienceConference on Computer Communications Workshops
- 9 July 2018
This work proposes an adaptive approach to speed up adversarial attacks, especially on sequential learning tasks, by leveraging the uncertainty of each task to directly learn the adaptive multi-task weightings, without manually searching hyper-parameters.
Intelligent Intersection: Two-Stream Convolutional Networks for Real-time Near Accident Detection in Traffic Video
- Xiaohui Huang, Pan He, Anand Rangarajan, S. Ranka
- Computer ScienceArXiv
- 4 January 2019
This paper proposes a two-stream Convolutional Network architecture that performs real-time detection, tracking, and near accident detection of road users in traffic video data and detects near accidents by incorporating appearance features and motion features from two- stream networks.
Learning Fast and Slow: Propedeutica for Real-Time Malware Detection
- Ruimin Sun, Xiaoyong Yuan, Xiaolin Li
- Computer ScienceIEEE Transactions on Neural Networks and Learning…
- 4 December 2017
This article introduces Propedeutica, a framework for efficient and effective real-time malware detection, leveraging the best of conventional machine learning (ML) and deep learning (DL) techniques, and introduces a novel DL architecture (DeepMalware) for PropedeUTica with multistream inputs.
Boosting up Scene Text Detectors with Guided CNN
- Xiaoyu Yue, Zhanghui Kuang, Wayne Zhang
- Computer ScienceBritish Machine Vision Conference
- 10 May 2018
This paper proposes a general framework for text detection called Guided CNN, which consists of one guidance subnetwork, where a guidance mask is learned from the input image itself, and one primary text detector, where every convolution and non-linear operation are conducted only in the guidance mask.
Self-Supervised Robust Scene Flow Estimation via the Alignment of Probability Density Functions
- Pan He, Patrick Emami, S. Ranka, A. Rangarajan
- Computer ScienceAAAI Conference on Artificial Intelligence
- 23 March 2022
This approach establishes soft and implicit point correspondences between point clouds and generates more robust and accurate scene flow in the presence of missing correspondences and outliers and achieves state-of-the-art performance among self-supervised learning methods on FlyingThings3D and KITTI.
...
...