Shiliang Pu

Text Perceptron: Towards End-to-End Arbitrary-Shaped Text Spotting

Many approaches have recently been proposed to detect irregular scene te...
02/17/2020 ∙ by Liang Qiao, et al. ∙ 12 ∙ share

read it
Neural Inheritance Relation Guided One-Shot Layer Assignment Search

Layer assignment is seldom picked out as an independent research topic i...
02/28/2020 ∙ by Rang Meng, et al. ∙ 7 ∙ share

read it
Scene Dynamics: Counterfactual Critic Multi-Agent Training for Scene Graph Generation

Scene graphs -- objects as nodes and visual relationships as edges -- de...
12/06/2018 ∙ by Long Chen, et al. ∙ 6 ∙ share

read it
Counterfactual Samples Synthesizing for Robust Visual Question Answering

Despite Visual Question Answering (VQA) has realized impressive progress...
03/14/2020 ∙ by Long Chen, et al. ∙ 5 ∙ share

read it
Arbitrarily-Oriented Text Recognition

Recognizing text from natural images is still a hot research topic in co...
11/12/2017 ∙ by Zhanzhan Cheng, et al. ∙ 0 ∙ share

read it
Cascade Region Proposal and Global Context for Deep Object Detection

Deep region-based object detector consists of a region proposal step and...
10/30/2017 ∙ by Qiaoyong Zhong, et al. ∙ 0 ∙ share

read it
Focusing Attention: Towards Accurate Text Recognition in Natural Images

Scene text recognition has been a hot research topic in computer vision ...
09/07/2017 ∙ by Zhanzhan Cheng, et al. ∙ 0 ∙ share

read it
All You Need is Beyond a Good Init: Exploring Better Solution for Training Extremely Deep Convolutional Neural Networks with Orthonormality and Modulation

Deep neural network is difficult to train and this predicament becomes w...
03/06/2017 ∙ by Di Xie, et al. ∙ 0 ∙ share

read it
Mixed context networks for semantic segmentation

Semantic segmentation is challenging as it requires both object-level in...
10/19/2016 ∙ by Haiming Sun, et al. ∙ 0 ∙ share

read it
Co-occurrence Feature Learning from Skeleton Data for Action Recognition and Detection with Hierarchical Aggregation

Skeleton-based human action recognition has recently drawn increasing at...
04/17/2018 ∙ by Chao Li, et al. ∙ 0 ∙ share

read it
Edit Probability for Scene Text Recognition

We consider the scene text recognition problem under the attention-based...
05/09/2018 ∙ by Fan Bai, et al. ∙ 0 ∙ share

read it
Small-scale Pedestrian Detection Based on Somatic Topology Localization and Temporal Feature Aggregation

A critical issue in pedestrian detection is to detect small-scale object...
07/04/2018 ∙ by Tao Song, et al. ∙ 0 ∙ share

read it
Extreme Network Compression via Filter Group Approximation

In this paper we propose a novel decomposition method based on filter gr...
07/30/2018 ∙ by Bo Peng, et al. ∙ 0 ∙ share

read it
Segregated Temporal Assembly Recurrent Networks for Weakly Supervised Multiple Action Detection

This paper proposes a segregated temporal assembly recurrent (STAR) netw...
11/19/2018 ∙ by Yunlu Xu, et al. ∙ 0 ∙ share

read it
Learning Incremental Triplet Margin for Person Re-identification

Person re-identification (ReID) aims to match people across multiple non...
12/17/2018 ∙ by Yingying Zhang, et al. ∙ 0 ∙ share

read it
A Layer Decomposition-Recomposition Framework for Neuron Pruning towards Accurate Lightweight Networks

Neuron pruning is an efficient method to compress the network into a sli...
12/17/2018 ∙ by Weijie Chen, et al. ∙ 0 ∙ share

read it
Cross-relation Cross-bag Attention for Distantly-supervised Relation Extraction

Distant supervision leverages knowledge bases to automatically label ins...
12/27/2018 ∙ by Yujin Yuan, et al. ∙ 0 ∙ share

read it
A practical convolutional neural network as loop filter for intra frame

Loop filters are used in video coding to remove artifacts or improve per...
05/16/2018 ∙ by Xiaodan Song, et al. ∙ 0 ∙ share

read it
Collaborative Spatio-temporal Feature Learning for Video Action Recognition

Spatio-temporal feature learning is of central importance for action rec...
03/04/2019 ∙ by Chao Li, et al. ∙ 0 ∙ share

read it
Efficient Video Scene Text Spotting: Unifying Detection, Tracking, and Recognition

This paper proposes an unified framework for efficiently spotting scene ...
03/08/2019 ∙ by Zhanzhan Cheng, et al. ∙ 0 ∙ share

read it
All You Need is a Few Shifts: Designing Efficient Convolutional Neural Networks for Image Classification

Shift operation is an efficient alternative over depthwise separable con...
03/13/2019 ∙ by Weijie Chen, et al. ∙ 0 ∙ share

read it
Extreme Image Compression via Multiscale Autoencoders With Generative Adversarial Optimization

We propose a MultiScale AutoEncoder(MSAE) based extreme image compressio...
04/08/2019 ∙ by Chao Huang, et al. ∙ 0 ∙ share

read it
Learned Quality Enhancement via Multi-Frame Priors for HEVC Compliant Low-Delay Applications

Networked video applications, e.g., video conferencing, often suffer fro...
05/03/2019 ∙ by Ming Lu, et al. ∙ 0 ∙ share

read it
Posterior-regularized REINFORCE for Instance Selection in Distant Supervision

This paper provides a new way to improve the efficiency of the REINFORCE...
04/17/2019 ∙ by Qi Zhang, et al. ∙ 0 ∙ share

read it
Adversarial Seeded Sequence Growing for Weakly-Supervised Temporal Action Localization

Temporal action localization is an important yet challenging research to...
08/07/2019 ∙ by Chengwei Zhang, et al. ∙ 0 ∙ share

read it
Refined Gate: A Simple and Effective Gating Mechanism for Recurrent Units

Recurrent neural network (RNN) has been widely studied in sequence learn...
02/26/2020 ∙ by Zhanzhan Cheng, et al. ∙ 0 ∙ share

read it
An End-to-End Audio Classification System based on Raw Waveforms and Mix-Training Strategy

Audio classification can distinguish different kinds of sounds, which is...
11/21/2019 ∙ by Jiaxu Chen, et al. ∙ 0 ∙ share

read it

Shiliang Pu

Featured Co-authors

Shih-Fu Chang

Yu Qiao

Chao Li

Kai Chen

Li Wang

Xiang Ren

Fei Wu

Qi Zhang

Xiangnan He

Hanwang Zhang

Long Chen

Text Perceptron: Towards End-to-End Arbitrary-Shaped Text Spotting

Neural Inheritance Relation Guided One-Shot Layer Assignment Search

Scene Dynamics: Counterfactual Critic Multi-Agent Training for Scene Graph Generation

Counterfactual Samples Synthesizing for Robust Visual Question Answering

Arbitrarily-Oriented Text Recognition

Cascade Region Proposal and Global Context for Deep Object Detection

Focusing Attention: Towards Accurate Text Recognition in Natural Images

All You Need is Beyond a Good Init: Exploring Better Solution for Training Extremely Deep Convolutional Neural Networks with Orthonormality and Modulation

Mixed context networks for semantic segmentation

Co-occurrence Feature Learning from Skeleton Data for Action Recognition and Detection with Hierarchical Aggregation

Edit Probability for Scene Text Recognition

Small-scale Pedestrian Detection Based on Somatic Topology Localization and Temporal Feature Aggregation

Extreme Network Compression via Filter Group Approximation

Segregated Temporal Assembly Recurrent Networks for Weakly Supervised Multiple Action Detection

Learning Incremental Triplet Margin for Person Re-identification

A Layer Decomposition-Recomposition Framework for Neuron Pruning towards Accurate Lightweight Networks

Cross-relation Cross-bag Attention for Distantly-supervised Relation Extraction

A practical convolutional neural network as loop filter for intra frame

Collaborative Spatio-temporal Feature Learning for Video Action Recognition

Efficient Video Scene Text Spotting: Unifying Detection, Tracking, and Recognition

All You Need is a Few Shifts: Designing Efficient Convolutional Neural Networks for Image Classification

Extreme Image Compression via Multiscale Autoencoders With Generative Adversarial Optimization

Learned Quality Enhancement via Multi-Frame Priors for HEVC Compliant Low-Delay Applications

Posterior-regularized REINFORCE for Instance Selection in Distant Supervision

Adversarial Seeded Sequence Growing for Weakly-Supervised Temporal Action Localization

Refined Gate: A Simple and Effective Gating Mechanism for Recurrent Units

An End-to-End Audio Classification System based on Raw Waveforms and Mix-Training Strategy