b'Liqiang Wang'

research

∙ 07/13/2023

FF-LINS: A Consistent Frame-to-Frame Solid-State-LiDAR-Inertial State Estimator

Most of the existing LiDAR-inertial navigation systems are based on fram...

0 Hailiang Tang, et al. ∙

research

∙ 05/22/2023

PO-VINS: An Efficient Pose-Only LiDAR-Enhanced Visual-Inertial State Estimator

The pose-only (PO) visual representation has been proven to be equivalen...

0 Hailiang Tang, et al. ∙

research

∙ 12/22/2022

On Calibrating Semantic Segmentation Models: Analysis and An Algorithm

We study the problem of semantic segmentation calibration. For image cla...

9 Dongdong Wang, et al. ∙

research

∙ 12/03/2021

CTIN: Robust Contextual Transformer Network for Inertial Navigation

Recently, data-driven inertial navigation approaches have demonstrated t...

0 Bingbing Rao, et al. ∙

research

∙ 09/18/2021

Anti-Neuron Watermarking: Protecting Personal Data Against Unauthorized Neural Model Training

In this paper, we raise up an emerging personal data protection problem ...

6 Zihang Zou, et al. ∙

research

∙ 07/24/2021

A Survey of Semantics-Aware Performance Optimization for Data-Intensive Computing

We are living in the era of Big Data and witnessing the explosion of dat...

0 Bingbing Rao, et al. ∙

research

∙ 07/24/2021

SODA: A Semantics-Aware Optimization Framework for Data-Intensive Applications Using Hybrid Program Analysis

In the era of data explosion, a growing number of data-intensive computi...

0 Bingbing Rao, et al. ∙

research

∙ 01/20/2021

Deep Epidemiological Modeling by Black-box Knowledge Distillation: An Accurate Deep Learning Model for COVID-19

An accurate and efficient forecasting system is imperative to the preven...

0 Dongdong Wang, et al. ∙

research

∙ 11/23/2020

Ranking Neural Checkpoints

This paper is concerned with ranking many pre-trained deep neural networ...

2 Yandong Li, et al. ∙

research

∙ 11/13/2020

Cross-Domain Learning for Classifying Propaganda in Online Contents

As news and social media exhibit an increasing amount of manipulative po...

4 Liqiang Wang, et al. ∙

research

∙ 10/23/2020

Beyond the Deep Metric Learning: Enhance the Cross-Modal Matching with Adversarial Discriminative Domain Regularization

Matching information across image and text modalities is a fundamental c...

0 Li Ren, et al. ∙

research

∙ 07/17/2020

Improving Object Detection with Selective Self-supervised Self-training

We study how to leverage Web images to augment human-curated object dete...

32 Yandong Li, et al. ∙

research

∙ 07/02/2020

Trace-Norm Adversarial Examples

White box adversarial perturbations are sought via iterative optimizatio...

0 Ehsan Kazemi, et al. ∙

research

∙ 03/31/2020

Neural Networks Are More Productive Teachers Than Human Raters: Active Mixup for Data-Efficient Knowledge Distillation from a Blackbox Model

We study how to train a student deep neural network for visual recogniti...

2 Dongdong Wang, et al. ∙

research

∙ 03/26/2020

BachGAN: High-Resolution Image Synthesis from Salient Object Layout

We propose a new task towards more practical application for image gener...

7 Yandong Li, et al. ∙

research

∙ 03/24/2020

Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition from a Domain Adaptation Perspective

Object frequency in the real world often follows a power law, leading to...

5 Muhammad Abdullah Jamal, et al. ∙

research

∙ 02/13/2020

Self-supervised learning for audio-visual speaker diarization

Speaker diarization, which is to find the speech segments of specific sp...

10 Yifan Ding, et al. ∙

research

∙ 11/21/2019

AdaFilter: Adaptive Filter Fine-tuning for Deep Transfer Learning

There is an increasing number of pre-trained deep neural network models....

0 Yunhui Guo, et al. ∙

research

∙ 06/16/2019

Defending Against Adversarial Attacks Using Random Forests

As deep neural networks (DNNs) have become increasingly important and po...

1 Yifan Ding, et al. ∙

research

∙ 05/30/2019

Robust Sparse Regularization: Simultaneously Optimizing Neural Network Robustness and Compactness

Deep Neural Network (DNN) trained by the gradient descent method is know...

0 Adnan Siraj Rakin, et al. ∙

research

∙ 05/08/2019

Frame-Recurrent Video Inpainting by Robust Optical Flow Inference

In this paper, we present a new inpainting framework for recovering miss...

0 Yifan Ding, et al. ∙

research

∙ 05/01/2019

NATTACK: Learning the Distributions of Adversarial Examples for an Improved Black-Box Attack on Deep Neural Networks

Powerful adversarial attack methods are vital for understanding how to c...

10 Yandong Li, et al. ∙

research

∙ 02/15/2019

Learning to Adaptively Scale Recurrent Neural Networks

Recent advancements in recurrent neural network (RNN) research have demo...

0 Hao Hu, et al. ∙

research

∙ 02/05/2019

Asynchronous Delay-Aware Accelerated Proximal Coordinate Descent for Nonconvex Nonsmooth Problems

Nonconvex and nonsmooth problems have recently attracted considerable at...

0 Ehsan Kazemi, et al. ∙

research

∙ 02/03/2019

Depthwise Convolution is All You Need for Learning Multiple Visual Domains

There is a growing interest in designing models that can deal with image...

0 Yunhui Guo, et al. ∙

research

∙ 01/14/2019

AET vs. AED: Unsupervised Representation Learning by Auto-Encoding Transformations rather than Data

The success of deep neural networks often relies on a large amount of la...

0 Liheng Zhang, et al. ∙

research

∙ 10/17/2018

A Proximal Zeroth-Order Algorithm for Nonconvex Nonsmooth Problems

In this paper, we focus on solving an important class of nonconvex optim...

0 Ehsan Kazemi, et al. ∙

research

∙ 07/11/2018

How Local is the Local Diversity? Reinforcing Sequential Determinantal Point Processes with Dynamic Ground Sets for Supervised Video Summarization

The large volume of video content and high viewing frequency demand auto...

8 Yandong Li, et al. ∙

research

∙ 03/05/2018

Improving the Improved Training of Wasserstein GANs: A Consistency Term and Its Dual Effect

Despite being impactful on a variety of problems and applications, the g...

0 Xiang Wei, et al. ∙

research

∙ 02/08/2018

A Semi-Supervised Two-Stage Approach to Learning from Noisy Labels

The recent success of deep neural networks is powered in part by large-s...

0 Yifan Ding, et al. ∙

Liqiang Wang

Featured Co-authors