Hao Li

verfied profile

∙ 1 follower
University of Maryland ∙ Zhejiang University ∙ Shanghai Jiao Tong University ∙ Tencent ∙ The Chinese University of Hong Kong ∙ Anhui USTC iFLYTEK Co ∙ NetEase, Inc

CEO/Co-Founder of Pinscreen, Computer Science Professor at USC, Director at the USC Institute for Creative Technologies

Featured Co-authors

Yang Liu
344 publications
Chunhua Shen
267 publications
Wei Zhang
220 publications
Wei Chen
200 publications
Hao Wang
180 publications
Jiashi Feng
177 publications
Liang Lin
167 publications
Yang Wang
159 publications
Qi Tian
150 publications
Xiaogang Wang
149 publications
Xin Li
147 publications

Fine-Grained AutoAugmentation for Multi-Label Classification

Data augmentation is a commonly used approach to improving the generaliz...
07/12/2021 ∙ by Ya Wang, et al. ∙ 7 ∙ share

read it
A Cloud-Edge-Terminal Collaborative System for Temperature Measurement in COVID-19 Prevention

To prevent the spread of coronavirus disease 2019 (COVID-19), preliminar...
07/11/2021 ∙ by Zheyi Ma, et al. ∙ 10 ∙ share

read it
LIFE: A Generalizable Autodidactic Pipeline for 3D OCT-A Vessel Segmentation

Optical coherence tomography (OCT) is a non-invasive imaging technique w...
07/09/2021 ∙ by Dewei Hu, et al. ∙ 6 ∙ share

read it
Normalized Avatar Synthesis Using StyleGAN and Perceptual Refinement

We introduce a highly robust GAN-based framework for digitizing a normal...
06/21/2021 ∙ by Huiwen Luo, et al. ∙ 2 ∙ share

read it
Task-Generic Hierarchical Human Motion Prior using VAEs

A deep generative model that describes human motions can benefit a wide ...
06/07/2021 ∙ by Jiaman Li, et al. ∙ 15 ∙ share

read it
An Efficient Training Approach for Very Large Scale Face Recognition

Face recognition has achieved significant progress in deep-learning era ...
05/21/2021 ∙ by Kai Wang, et al. ∙ 10 ∙ share

read it
An Empirical Study of Vehicle Re-Identification on the AI City Challenge

This paper introduces our solution for the Track2 in AI City Challenge 2...
05/20/2021 ∙ by Hao Luo, et al. ∙ 11 ∙ share

read it
Maximizing Mutual Information Across Feature and Topology Views for Learning Graph Representations

Recently, maximizing mutual information has emerged as a powerful method...
05/14/2021 ∙ by Xiaolong Fan, et al. ∙ 5 ∙ share

read it
Importance Weighted Adversarial Discriminative Transfer for Anomaly Detection

Previous transfer methods for anomaly detection generally assume the ava...
05/14/2021 ∙ by Cangning Fan, et al. ∙ 5 ∙ share

read it
City-Scale Multi-Camera Vehicle Tracking Guided by Crossroad Zones

Multi-Target Multi-Camera Tracking has a wide range of applications and ...
05/14/2021 ∙ by Chong Liu, et al. ∙ 12 ∙ share

read it
DBNet: A Dual-branch Network Architecture Processing on Spectrum and Waveform for Single-channel Speech Enhancement

In real acoustic environment, speech enhancement is an arduous task to i...
05/06/2021 ∙ by Kanghao Zhang, et al. ∙ 0 ∙ share

read it
Learning to Cluster Faces via Transformer

Face clustering is a useful tool for applications like automatic face an...
04/23/2021 ∙ by Jinxing Ye, et al. ∙ 46 ∙ share

read it
Spatiotemporal Entropy Model is All You Need for Learned Video Compression

The framework of dominant learned video compression methods is usually c...
04/13/2021 ∙ by Zhenhong Sun, et al. ∙ 21 ∙ share

read it
Augmented Transformer with Adaptive Graph for Temporal Action Proposal Generation

Temporal action proposal generation (TAPG) is a fundamental and challeng...
03/30/2021 ∙ by Shuning Chang, et al. ∙ 9 ∙ share

read it
Guided Training: A Simple Method for Single-channel Speaker Separation

Deep learning has shown a great potential for speech separation, especia...
03/26/2021 ∙ by Hao Li, et al. ∙ 0 ∙ share

read it
Equivariant Point Network for 3D Point Cloud Analysis

Features that are equivariant to a larger group of symmetries have been ...
03/25/2021 ∙ by Haiwei Chen, et al. ∙ 8 ∙ share

read it
AutoLoss-Zero: Searching Loss Functions from Scratch for Generic Tasks

Significant progress has been achieved in automating the design of vario...
03/25/2021 ∙ by Hao Li, et al. ∙ 13 ∙ share

read it
PlenOctrees for Real-time Rendering of Neural Radiance Fields

We introduce a method to render Neural Radiance Fields (NeRFs) in real t...
03/25/2021 ∙ by Alex Yu, et al. ∙ 4 ∙ share

read it
Instant-Teaching: An End-to-End Semi-Supervised Object Detection Framework

Supervised learning based object detection frameworks demand plenty of l...
03/21/2021 ∙ by Qiang Zhou, et al. ∙ 18 ∙ share

read it
Accuracy of spectral element method for wave, parabolic and Schrödinger equations

The spectral element method constructed by the Q^k (k≥ 2) continuous fin...
02/28/2021 ∙ by Hao Li, et al. ∙ 0 ∙ share

read it
TransReID: Transformer-based Object Re-Identification

In this paper, we explore the Vision Transformer (ViT), a pure transform...
02/08/2021 ∙ by Shuting He, et al. ∙ 28 ∙ share

read it
A linearized framework and a new benchmark for model selection for fine-tuning

Fine-tuning from a collection of models pre-trained on different domains...
01/29/2021 ∙ by Aditya Deshpande, et al. ∙ 21 ∙ share

read it
Robust Representation Learning with Feedback for Single Image Deraining

A deraining network may be interpreted as a condition generator. Image d...
01/29/2021 ∙ by Chenghao Chen, et al. ∙ 1 ∙ share

read it
Object Detection Made Simpler by Eliminating Heuristic NMS

We show a simple NMS-free, end-to-end object detection framework, of whi...
01/28/2021 ∙ by Qiang Zhou, et al. ∙ 13 ∙ share

read it
1st Place Solution to ECCV-TAO-2020: Detect and Represent Any Object for Tracking

We extend the classical tracking-by-detection paradigm to this tracking-...
01/20/2021 ∙ by Fei Du, et al. ∙ 11 ∙ share

read it
1st Place Solution to VisDA-2020: Bias Elimination for Domain Adaptive Pedestrian Re-identification

This paper presents our proposed methods for domain adaptive pedestrian ...
12/25/2020 ∙ by Jianyang Gu, et al. ∙ 3 ∙ share

read it
AsymptoticNG: A regularized natural gradient optimization algorithm with look-ahead strategy

Optimizers that further adjust the scale of gradient, such as Adam, Natu...
12/24/2020 ∙ by Zedong Tang, et al. ∙ 9 ∙ share

read it
Blurring Fools the Network – Adversarial Attacks by Feature Peak Suppression and Gaussian Blurring

Existing pixel-level adversarial attacks on neural networks may be defic...
12/21/2020 ∙ by Chenchen Zhao, et al. ∙ 11 ∙ share

read it
Amplifying the Anterior-Posterior Difference via Data Enhancement – A More Robust Deep Monocular Orientation Estimation Solution

Existing deep-learning based monocular orientation estimation algorithms...
12/21/2020 ∙ by Chenchen Zhao, et al. ∙ 5 ∙ share

read it
Exploiting Vulnerability of Pooling in Convolutional Neural Networks by Strict Layer-Output Manipulation for Adversarial Attacks

Convolutional neural networks (CNN) have been more and more applied in m...
12/21/2020 ∙ by Chenchen Zhao, et al. ∙ 14 ∙ share

read it
AU-Guided Unsupervised Domain Adaptive Facial Expression Recognition

The domain diversities including inconsistent annotation and varied imag...
12/18/2020 ∙ by Kai Wang, et al. ∙ 2 ∙ share

read it
An Event Correlation Filtering Method for Fake News Detection

Nowadays, social network platforms have been the prime source for people...
12/10/2020 ∙ by Hao Li, et al. ∙ 7 ∙ share

read it
SGD_Tucker: A Novel Stochastic Optimization Strategy for Parallel Sparse Tucker Decomposition

Sparse Tucker Decomposition (STD) algorithms learn a core tensor and a g...
12/07/2020 ∙ by Hao Li, et al. ∙ 0 ∙ share

read it
Hierarchical Semantic Aggregation for Contrastive Representation Learning

Self-supervised learning based on instance discrimination has shown rema...
12/04/2020 ∙ by Haohang Xu, et al. ∙ 3 ∙ share

read it
Heterogeneous Contrastive Learning: Encoding Spatial Information for Compact Visual Representations

Contrastive learning has achieved great success in self-supervised visua...
11/19/2020 ∙ by Xinyue Huo, et al. ∙ 5 ∙ share

read it
ULSD: Unified Line Segment Detection across Pinhole, Fisheye, and Spherical Cameras

Line segment detection is essential for high-level tasks in computer vis...
11/06/2020 ∙ by Hao Li, et al. ∙ 2 ∙ share

read it
Center-wise Local Image Mixture For Contrastive Representation Learning

Recent advances in unsupervised representation learning have experienced...
11/05/2020 ∙ by Hao Li, et al. ∙ 2 ∙ share

read it
Data Augmentation for End-to-end Code-switching Speech Recognition

Training a code-switching end-to-end automatic speech recognition (ASR) ...
11/04/2020 ∙ by Chenpeng Du, et al. ∙ 11 ∙ share

read it
DeviceTTS: A Small-Footprint, Fast, Stable Network for On-Device Text-to-Speech

With the number of smart devices increasing, the demand for on-device te...
10/29/2020 ∙ by Zhiying Huang, et al. ∙ 0 ∙ share

read it
Speakerfilter-Pro: an improved target speaker extractor combines the time domain and frequency domain

This paper introduces an improved target speaker extractor, referred to ...
10/25/2020 ∙ by Shulin He, et al. ∙ 10 ∙ share

read it
Auto Seg-Loss: Searching Metric Surrogates for Semantic Segmentation

We propose a general framework for searching surrogate losses for mainst...
10/15/2020 ∙ by Hao Li, et al. ∙ 10 ∙ share

read it
Domain Agnostic Learning for Unbiased Authentication

Authentication is the task of confirming the matching relationship betwe...
10/11/2020 ∙ by Jian Liang, et al. ∙ 6 ∙ share

read it
Position-Aware Tagging for Aspect Sentiment Triplet Extraction

Aspect Sentiment Triplet Extraction (ASTE) is the task of extracting the...
10/06/2020 ∙ by Lu Xu, et al. ∙ 0 ∙ share

read it
Dynamic Facial Asset and Rig Generation from a Single Scan

The creation of high-fidelity computer-generated (CG) characters used in...
10/01/2020 ∙ by Jiaman Li, et al. ∙ 5 ∙ share

read it
Efficient Kernel Transfer in Knowledge Distillation

Knowledge distillation is an effective way for model compression in deep...
09/30/2020 ∙ by Qi Qian, et al. ∙ 77 ∙ share

read it
AIM 2020 Challenge on Real Image Super-Resolution: Methods and Results

This paper introduces the real image Super-Resolution (SR) challenge tha...
09/25/2020 ∙ by Pengxu Wei, et al. ∙ 7 ∙ share

read it
Semi-Anchored Detector for One-Stage Object Detection

A standard one-stage detector is comprised of two tasks: classification ...
09/10/2020 ∙ by Lei Chen, et al. ∙ 5 ∙ share

read it
Hybrid Differentially Private Federated Learning on Vertically Partitioned Data

We present HDP-VFL, the first hybrid differentially private (DP) framewo...
09/06/2020 ∙ by Chang Wang, et al. ∙ 1 ∙ share

read it
A Federated Multi-View Deep Learning Framework for Privacy-Preserving Recommendations

Privacy-preserving recommendations are recently gaining momentum, since ...
08/25/2020 ∙ by Mingkai Huang, et al. ∙ 26 ∙ share

read it
Modular End-to-end Automatic Speech Recognition Framework for Acoustic-to-word Model

End-to-end (E2E) systems have played a more and more important role in a...
07/31/2020 ∙ by Qi Liu, et al. ∙ 0 ∙ share

read it