Search Results for author: Heng Yang

Found 25 papers, 13 papers with code

Back to Reality: Leveraging Pattern-driven Modeling to Enable Affordable Sentiment Dependency Learning

1 code implementation16 Oct 2021 Heng Yang, Biqing Zeng, Mayi Xu, Tianxing Wang

Experiments on four public datasets show that our models achieve state-of-the-art performance with especially improvement on learning sentiment cluster.

Dependency Parsing Sentiment Analysis

Certifiable Outlier-Robust Geometric Perception: Exact Semidefinite Relaxations and Scalable Global Optimization

2 code implementations7 Sep 2021 Heng Yang, Luca Carlone

Our third contribution is to solve the SDP relaxations at an unprecedented scale and accuracy by presenting STRIDE, a solver that blends global descent on the convex SDP with fast local search on the nonconvex POP.

Global Optimization Pose Estimation

Deep Tiny Network for Recognition-Oriented Face Image Quality Assessment

no code implementations9 Jun 2021 Baoyun Peng, Min Liu, Heng Yang, Zhaoning Zhang, Dongsheng Li

Based on the proposed quality measurement, we propose a deep Tiny Face Quality network (tinyFQnet) to learn a quality prediction function from data.

Face Recognition Image Quality Assessment

STRIDE along Spectrahedral Vertices for Solving Large-Scale Rank-One Semidefinite Relaxations

1 code implementation28 May 2021 Heng Yang, Ling Liang, Kim-Chuan Toh, Luca Carlone

STRIDE dominates a diverse set of five existing SDP solvers and is the only solver that can solve degenerate rank-one SDPs to high accuracy (e. g., KKT residuals below 1e-9), even in the presence of millions of equality constraints.

Optimal Pose and Shape Estimation for Category-level 3D Object Perception

no code implementations16 Apr 2021 Jingnan Shi, Heng Yang, Luca Carlone

Our first contribution is to provide the first certifiably optimal solver for pose and shape estimation.

Translation Vehicle Pose Estimation

Dynamical Pose Estimation

1 code implementation ICCV 2021 Heng Yang, Chris Doran, Jean-Jacques Slotine

We study the problem of aligning two sets of 3D geometric primitives given known correspondences.

Point Cloud Registration Pose Estimation

Self-supervised Geometric Perception

1 code implementation CVPR 2021 Heng Yang, Wei Dong, Luca Carlone, Vladlen Koltun

We present self-supervised geometric perception (SGP), the first general framework to learn a feature descriptor for correspondence matching without any ground-truth geometric model labels (e. g., camera poses, rigid transformations).

Point Cloud Registration Pose Estimation

ROBIN: a Graph-Theoretic Approach to Reject Outliers in Robust Estimation using Invariants

no code implementations7 Nov 2020 Jingnan Shi, Heng Yang, Luca Carlone

We also show that in practice the maximum k-core of the compatibility graph provides an approximation of the maximum clique, while being faster to compute in large problems.

Enhancing Fine-grained Sentiment Classification Exploiting Local Context Embedding

2 code implementations2 Oct 2020 Heng Yang, Biqing Zeng

Target-oriented sentiment classification is a fine-grained task of natural language processing to analyze the sentiment polarity of the targets.

Aspect-Based Sentiment Analysis Classification +1

Outlier-Robust Estimation: Hardness, Minimally Tuned Algorithms, and Applications

no code implementations29 Jul 2020 Pasquale Antonante, Vasileios Tzoumas, Heng Yang, Luca Carlone

We extend ADAPT and GNC to the case where the user does not have prior knowledge of the inlier-noise statistics (or the statistics may vary over time) and is unable to guess a reasonable threshold to separate inliers from outliers (as the one commonly used in RANSAC).

Object Detection

One Ring to Rule Them All: Certifiably Robust Geometric Perception with Outliers

1 code implementation NeurIPS 2020 Heng Yang, Luca Carlone

We propose the first general and practical framework to design certifiable algorithms for robust geometric perception in the presence of a large amount of outliers.

Pose Estimation

A Dynamical Perspective on Point Cloud Registration

no code implementations7 May 2020 Heng Yang

We provide a dynamical perspective on the classical problem of 3D point cloud registration with correspondences.

Point Cloud Registration

TEASER: Fast and Certifiable Point Cloud Registration

4 code implementations21 Jan 2020 Heng Yang, Jingnan Shi, Luca Carlone

We propose the first fast and certifiable algorithm for the registration of two sets of 3D points in the presence of large amounts of outlier correspondences.

Object Detection Point Cloud Registration +1

A Multi-task Learning Model for Chinese-oriented Aspect Polarity Classification and Aspect Term Extraction

4 code implementations17 Dec 2019 Heng Yang, Biqing Zeng, JianHao Yang, Youwei Song, Ruyang Xu

Aspect-based sentiment analysis (ABSA) task is a multi-grained task of natural language processing and consists of two subtasks: aspect term extraction (ATE) and aspect polarity classification (APC).

Aspect-Based Sentiment Analysis General Classification +1

Graduated Non-Convexity for Robust Spatial Perception: From Non-Minimal Solvers to Global Outlier Rejection

3 code implementations18 Sep 2019 Heng Yang, Pasquale Antonante, Vasileios Tzoumas, Luca Carlone

In this paper, we enable the simultaneous use of non-minimal solvers and robust estimation by providing a general-purpose approach for robust global estimation, which can be applied to any problem where a non-minimal solver is available for the outlier-free case.

Pose Estimation

A Quaternion-based Certifiably Optimal Solution to the Wahba Problem with Outliers

2 code implementations ICCV 2019 Heng Yang, Luca Carlone

Our first contribution is to formulate the Wahba problem using a Truncated Least Squares (TLS) cost that is insensitive to a large fraction of spurious correspondences.

A Polynomial-time Solution for Robust Registration with Extreme Outlier Rates

1 code implementation20 Mar 2019 Heng Yang, Luca Carlone

We propose a robust approach for the registration of two sets of 3D points in the presence of a large amount of outliers.


SCSP: Spectral Clustering Filter Pruning with Soft Self-adaption Manners

no code implementations14 Jun 2018 Huiyuan Zhuo, Xuelin Qian, Yanwei Fu, Heng Yang, xiangyang xue

In this paper, we proposed a novel filter pruning for convolutional neural networks compression, namely spectral clustering filter pruning with soft self-adaption manners (SCSP).

Model Compression

Training a Binary Weight Object Detector by Knowledge Transfer for Autonomous Driving

no code implementations17 Apr 2018 Jiaolong Xu, Peng Wang, Heng Yang, Antonio M. López

Autonomous driving has harsh requirements of small model size and energy efficiency, in order to enable the embedded system to achieve real-time on-board object detection.

Autonomous Driving Object Detection +1

An Empirical Study of Recent Face Alignment Methods

no code implementations16 Nov 2015 Heng Yang, Xuhui Jia, Chen Change Loy, Peter Robinson

In this paper, we carry out a rigorous evaluation of these methods by making the following contributions: 1) we proposes a new evaluation metric for face alignment on a set of images, i. e., area under error distribution curve within a threshold, AUC$_\alpha$, given the fact that the traditional evaluation measure (mean error) is very sensitive to big alignment error.

Face Alignment Face Detection

Human and Sheep Facial Landmarks Localisation by Triplet Interpolated Features

no code implementations16 Sep 2015 Heng Yang, Renqiao Zhang, Peter Robinson

Furthermore, we study the impact of training data imbalance on model performance and propose a training sample augmentation scheme that produces more initialisations for training samples from the minority.

Face Alignment Assisted by Head Pose Estimation

1 code implementation11 Jul 2015 Heng Yang, Wenxuan Mou, Yichi Zhang, Ioannis Patras, Hatice Gunes, Peter Robinson

In this paper we propose a supervised initialization scheme for cascaded face alignment based on explicit head pose estimation.

Face Alignment Head Pose Estimation

Mirror, mirror on the wall, tell me, is the error small?

no code implementations CVPR 2015 Heng Yang, Ioannis Patras

Our experiments lead to several interesting findings: 1) Surprisingly, most of state of the art methods struggle to preserve the mirror symmetry, despite the fact that they do have very similar overall performance on the original and mirror images; 2) the low mirrorability is not caused by training or testing sample bias - all algorithms are trained on both the original images and their mirrored versions; 3) the mirror error is strongly correlated to the localization/alignment error (with correlation coefficients around 0. 7).

Face Alignment Pose Estimation

Separation of Line Drawings Based on Split Faces for 3D Object Reconstruction

no code implementations CVPR 2014 Changqing Zou, Heng Yang, Jianzhuang Liu

Reconstructing 3D objects from single line drawings is often desirable in computer vision and graphics applications.

3D Object Reconstruction

Cannot find the paper you are looking for? You can Submit a new open access paper.