Search Results for author: Lei Zhou

Found 55 papers, 24 papers with code

GasMono: Geometry-Aided Self-Supervised Monocular Depth Estimation for Indoor Scenes

no code implementations ICCV 2023 Chaoqiang Zhao, Matteo Poggi, Fabio Tosi, Lei Zhou, Qiyu Sun, Yang Tang, Stefano Mattoccia

This paper tackles the challenges of self-supervised monocular depth estimation in indoor scenes caused by large rotation between frames and low texture.

Monocular Depth Estimation

Transcending the Acceleration-Bandwidth Trade-off: Lightweight Precision Stages with Active Control of Flexible Dynamics

no code implementations25 Sep 2023 Jingjie Wu, Lei Zhou

In recent years, the drastically growing demand for higher throughput and reduced power consumption in various IC manufacturing equipment calls for the development of next-generation precision positioning systems with unprecedented acceleration capability while maintaining exceptional positioning accuracy and high control bandwidth.

FleXstage: Lightweight Magnetically Levitated Precision Stage with Over-Actuation towards High-Throughput IC Manufacturing

no code implementations21 Sep 2023 Jingjie Wu, Lei Zhou

For these systems, the motion control bandwidth is limited by the first structural resonance frequency of the stage, which enforces a fundamental trade-off between the stage's bandwidth and acceleration capability.

DR-Pose: A Two-stage Deformation-and-Registration Pipeline for Category-level 6D Object Pose Estimation

1 code implementation5 Sep 2023 Lei Zhou, Zhiyang Liu, Runze Gan, Haozhe Wang, Marcelo H. Ang Jr

In the second stage, a novel registration network is designed to extract pose-sensitive features and predict the representation of object partial point cloud in canonical space based on the deformation results from the first stage.

6D Pose Estimation using RGB Point Cloud Completion

Unsupervised Recognition of Unknown Objects for Open-World Object Detection

1 code implementation31 Aug 2023 Ruohuan Fang, Guansong Pang, Lei Zhou, Xiao Bai, Jin Zheng

Open-World Object Detection (OWOD) extends object detection problem to a realistic and dynamic scenario, where a detection model is required to be capable of detecting both known and unknown objects and incrementally learning newly introduced knowledge.

object-detection Open World Object Detection +1

Exploring the Limits of Historical Information for Temporal Knowledge Graph Extrapolation

no code implementations29 Aug 2023 Yi Xu, Junjie Ou, Hui Xu, Luoyi Fu, Lei Zhou, Xinbing Wang, Chenghu Zhou

To this end, we investigate the limits of historical information for temporal knowledge graph extrapolation and propose a new event forecasting model called Contrastive Event Network (CENET) based on a novel training framework of historical contrastive learning.

Contrastive Learning Knowledge Graphs

Learning Adversarial Semantic Embeddings for Zero-Shot Recognition in Open Worlds

1 code implementation7 Jul 2023 Tianqi Li, Guansong Pang, Xiao Bai, Jin Zheng, Lei Zhou, Xin Ning

Open-Set Recognition (OSR) is dedicated to addressing the unknown class issue, but existing OSR methods are not designed to model the semantic information of the unseen classes.

Open Set Learning Zero-Shot Learning

Token Sparsification for Faster Medical Image Segmentation

1 code implementation11 Mar 2023 Lei Zhou, Huidong Liu, Joseph Bae, Junjun He, Dimitris Samaras, Prateek Prasanna

To this end, we reformulate segmentation as a sparse encoding -> token completion -> dense decoding (SCD) pipeline.

Image Segmentation Medical Image Segmentation +1

Bokeh Rendering Based on Adaptive Depth Calibration Network

no code implementations21 Feb 2023 Lu Liu, Lei Zhou, Yuhan Dong

This allows the camera to capture images with shallow depth-of-field, in which only a small area of the image is in sharp focus, while the rest of the image is blurred.

Monocular Depth Estimation

Sequential Structure and Control Co-design of Lightweight Precision Stages with Active control of flexible modes

no code implementations10 Jan 2023 Jingjie Wu, Lei Zhou

To overcome this challenge, this paper proposes a new hardware design and control framework for lightweight precision motion stages with the stage's low-frequency flexible modes actively controlled.

Cross-Modal Similarity-Based Curriculum Learning for Image Captioning

no code implementations14 Dec 2022 Hongkuan Zhang, Saku Sugawara, Akiko Aizawa, Lei Zhou, Ryohei Sasano, Koichi Takeda

Moreover, the higher model performance on difficult examples and unseen data also demonstrates the generalization ability.

Image Captioning Language Modelling

Spatially Exclusive Pasting: A General Data Augmentation for the Polyp Segmentation

no code implementations15 Nov 2022 Lei Zhou

Automated polyp segmentation technology plays an important role in diagnosing intestinal diseases, such as tumors and precancerous lesions.

Data Augmentation Medical Image Segmentation

ASpanFormer: Detector-Free Image Matching with Adaptive Span Transformer

1 code implementation30 Aug 2022 Hongkai Chen, Zixin Luo, Lei Zhou, Yurun Tian, Mingmin Zhen, Tian Fang, David McKinnon, Yanghai Tsin, Long Quan

Generating robust and reliable correspondences across images is a fundamental task for a diversity of applications.

Homography Estimation

Learning Prototype via Placeholder for Zero-shot Recognition

1 code implementation29 Jul 2022 Zaiquan Yang, Yang Liu, Wenjia Xu, Chong Huang, Lei Zhou, Chao Tong

Specifically, we combine seen classes to hallucinate new classes which play as placeholders of the unseen classes in the visual and semantic space.

Zero-Shot Learning

PEGG-Net: Pixel-Wise Efficient Grasp Generation in Complex Scenes

1 code implementation30 Mar 2022 Haozhe Wang, Zhiyang Liu, Lei Zhou, Huan Yin, Marcelo H Ang Jr

Vision-based grasp estimation is an essential part of robotic manipulation tasks in the real world.

Grasp Generation

Self Pre-training with Masked Autoencoders for Medical Image Classification and Segmentation

1 code implementation10 Mar 2022 Lei Zhou, Huidong Liu, Joseph Bae, Junjun He, Dimitris Samaras, Prateek Prasanna

Masked Autoencoder (MAE) has recently been shown to be effective in pre-training Vision Transformers (ViT) for natural image analysis.

Brain Tumor Segmentation Image Classification +4

Control Co-design of Actively Controlled Lightweight Structures for High-acceleration Precision Motion Systems

no code implementations15 Feb 2022 Jingjie Wu, Lei Zhou

Precision motion stages are an essential part of a wide range of manufacturing equipment, and their motion performance are critical to the quality and throughput of the systems.

Self-Sensing Hysteresis-Type Bearingless Motor

no code implementations9 Feb 2022 Laura Homiller, Lei Zhou

Bearingless motors use a single stator assembly to apply torque and magnetic suspension forces on the rotor, making these machines compact with frictionless operation and thus well suited to high-speed applications.

Vocal Bursts Type Prediction

Efficient Semi-Discrete Optimal Transport Using the Maximum Relative Error between Distributions

no code implementations29 Sep 2021 Huidong Liu, Ke Ma, Lei Zhou, Dimitris Samaras

If the \texttt{MRE} is smaller than 1, then every target point is guaranteed to have an area in the source distribution that is mapped to it.

Half a Dozen Real-World Applications of Evolutionary Multitasking, and More

no code implementations27 Sep 2021 Abhishek Gupta, Lei Zhou, Yew-Soon Ong, Zefeng Chen, Yaqing Hou

Until recently, the potential to transfer evolved skills across distinct optimization problem instances (or tasks) was seldom explored in evolutionary computation.

Learning to Match Features with Seeded Graph Matching Network

1 code implementation ICCV 2021 Hongkai Chen, Zixin Luo, Jiahui Zhang, Lei Zhou, Xuyang Bai, Zeyu Hu, Chiew-Lan Tai, Long Quan

2) Seeded Graph Neural Network, which utilizes seed matches to pass messages within/across images and predicts assignment costs.

Graph Matching

Self-Guided Curriculum Learning for Neural Machine Translation

no code implementations ACL (IWSLT) 2021 Lei Zhou, Liang Ding, Kevin Duh, Shinji Watanabe, Ryohei Sasano, Koichi Takeda

In the field of machine learning, the well-trained model is assumed to be able to recover the training labels, i. e. the synthetic labels predicted by the model should be as close to the ground-truth labels as possible.

Machine Translation NMT +1

Goal-Oriented Gaze Estimation for Zero-Shot Learning

1 code implementation CVPR 2021 Yang Liu, Lei Zhou, Xiao Bai, Yifei HUANG, Lin Gu, Jun Zhou, Tatsuya Harada

Therefore, we introduce a novel goal-oriented gaze estimation module (GEM) to improve the discriminative attribute localization based on the class-level attributes for ZSL.

Gaze Estimation Generalized Zero-Shot Learning

Unraveling disorder-induced optical dephasing in an atomic ensemble

no code implementations26 Jan 2021 Yizun He, Qingnan Cai, Lingjing Ji, Zhening Fang, Yuzhuo Wang, Liyang Qiu, Lei Zhou, Saijun Wu, Stefano Grava, Darrick E. Chang

Most of our understanding and modeling of such systems are based upon macroscopic theories, wherein the atoms are treated as a smooth, quantum polarizable medium.

Atomic Physics Quantum Physics

Zero-Shot Translation Quality Estimation with Explicit Cross-Lingual Patterns

no code implementations WMT (EMNLP) 2020 Lei Zhou, Liang Ding, Koichi Takeda

In response to this issue, we propose to expose explicit cross-lingual patterns, \textit{e. g.} word alignments and generation score, to our proposed zero-shot models.


Information Bottleneck Constrained Latent Bidirectional Embedding for Zero-Shot Learning

no code implementations16 Sep 2020 Yang Liu, Lei Zhou, Xiao Bai, Lin Gu, Tatsuya Harada, Jun Zhou

Though many ZSL methods rely on a direct mapping between the visual and the semantic space, the calibration deviation and hubness problem limit the generalization capability to unseen classes.

Zero-Shot Learning

Stochastic Bundle Adjustment for Efficient and Scalable 3D Reconstruction

1 code implementation ECCV 2020 Lei Zhou, Zixin Luo, Mingmin Zhen, Tianwei Shen, Shiwei Li, Zhuofei Huang, Tian Fang, Long Quan

In this work, we propose a stochastic bundle adjustment algorithm which seeks to decompose the RCS approximately inside the LM iterations to improve the efficiency and scalability.

3D Reconstruction Clustering

Self-Supervised Monocular 3D Face Reconstruction by Occlusion-Aware Multi-view Geometry Consistency

1 code implementation ECCV 2020 Jiaxiang Shang, Tianwei Shen, Shiwei Li, Lei Zhou, Mingmin Zhen, Tian Fang, Long Quan

Recent learning-based approaches, in which models are trained by single-view images have shown promising results for monocular 3D face reconstruction, but they suffer from the ill-posed face pose and depth ambiguity issue.

3D Face Reconstruction Depth Estimation +2

KFNet: Learning Temporal Camera Relocalization using Kalman Filtering

1 code implementation CVPR 2020 Lei Zhou, Zixin Luo, Tianwei Shen, Jiahui Zhang, Mingmin Zhen, Yao Yao, Tian Fang, Long Quan

Temporal camera relocalization estimates the pose with respect to each video frame in sequence, as opposed to one-shot relocalization which focuses on a still image.

Camera Relocalization

D3Feat: Joint Learning of Dense Detection and Description of 3D Local Features

2 code implementations CVPR 2020 Xuyang Bai, Zixin Luo, Lei Zhou, Hongbo Fu, Long Quan, Chiew-Lan Tai

In this paper, we leverage a 3D fully convolutional network for 3D point clouds, and propose a novel and practical learning mechanism that densely predicts both a detection score and a description feature for each 3D point.

Point Cloud Registration

BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networks

2 code implementations CVPR 2020 Yao Yao, Zixin Luo, Shiwei Li, Jingyang Zhang, Yufan Ren, Lei Zhou, Tian Fang, Long Quan

Compared with other computer vision tasks, it is rather difficult to collect a large-scale MVS dataset as it requires expensive active scanners and labor-intensive process to obtain ground truth 3D structures.

3D Reconstruction

Self-Supervised Learning of Depth and Motion Under Photometric Inconsistency

1 code implementation19 Sep 2019 Tianwei Shen, Lei Zhou, Zixin Luo, Yao Yao, Shiwei Li, Jiahui Zhang, Tian Fang, Long Quan

The self-supervised learning of depth and pose from monocular sequences provides an attractive solution by using the photometric consistency of nearby frames as it depends much less on the ground-truth data.

Pose Estimation Self-Supervised Learning

Learning Two-View Correspondences and Geometry Using Order-Aware Network

1 code implementation ICCV 2019 Jiahui Zhang, Dawei Sun, Zixin Luo, Anbang Yao, Lei Zhou, Tianwei Shen, Yurong Chen, Long Quan, Hongen Liao

First, to capture the local context of sparse correspondences, the network clusters unordered input correspondences by learning a soft assignment matrix.

Vocal Bursts Valence Prediction

A One-step Pruning-recovery Framework for Acceleration of Convolutional Neural Networks

no code implementations18 Jun 2019 Dong Wang, Lei Zhou, Xiao Bai, Jun Zhou

Our method accelerates the network in one-step pruning-recovery manner with a novel optimization objective function, which achieves higher accuracy with much less cost compared with existing pruning methods.

ContextDesc: Local Descriptor Augmentation with Cross-Modality Context

1 code implementation CVPR 2019 Zixin Luo, Tianwei Shen, Lei Zhou, Jiahui Zhang, Yao Yao, Shiwei Li, Tian Fang, Long Quan

Most existing studies on learning local features focus on the patch-based descriptions of individual keypoints, whereas neglecting the spatial relations established from their keypoint locations.

Geometric Matching

Beyond Photometric Loss for Self-Supervised Ego-Motion Estimation

1 code implementation25 Feb 2019 Tianwei Shen, Zixin Luo, Lei Zhou, Hanyu Deng, Runze Zhang, Tian Fang, Long Quan

Accurate relative pose is one of the key components in visual odometry (VO) and simultaneous localization and mapping (SLAM).

Motion Estimation Self-Supervised Learning +2

Matchable Image Retrieval by Learning from Surface Reconstruction

1 code implementation26 Nov 2018 Tianwei Shen, Zixin Luo, Lei Zhou, Runze Zhang, Siyu Zhu, Tian Fang, Long Quan

Convolutional Neural Networks (CNNs) have achieved superior performance on object image retrieval, while Bag-of-Words (BoW) models with handcrafted local features still dominate the retrieval of overlapping images in 3D reconstruction.

3D Reconstruction Image Retrieval +2

GeoDesc: Learning Local Descriptors by Integrating Geometry Constraints

1 code implementation ECCV 2018 Zixin Luo, Tianwei Shen, Lei Zhou, Siyu Zhu, Runze Zhang, Yao Yao, Tian Fang, Long Quan

Learned local descriptors based on Convolutional Neural Networks (CNNs) have achieved significant improvements on patch-based benchmarks, whereas not having demonstrated strong generalization ability on recent benchmarks of image-based 3D reconstruction.

3D Reconstruction

Learning and Matching Multi-View Descriptors for Registration of Point Clouds

no code implementations ECCV 2018 Lei Zhou, Siyu Zhu, Zixin Luo, Tianwei Shen, Runze Zhang, Mingmin Zhen, Tian Fang, Long Quan

Critical to the registration of point clouds is the establishment of a set of accurate correspondences between points in 3D space.

Temporal Hallucinating for Action Recognition With Few Still Images

no code implementations CVPR 2018 Yali Wang, Lei Zhou, Yu Qiao

To mimic this capacity, we propose a novel Hybrid Video Memory (HVM) machine, which can hallucinate temporal features of still images from video memory, in order to boost action recognition with few still images.

Action Recognition In Still Images Domain Adaptation

Very Large-Scale Global SfM by Distributed Motion Averaging

no code implementations CVPR 2018 Siyu Zhu, Runze Zhang, Lei Zhou, Tianwei Shen, Tian Fang, Ping Tan, Long Quan

This work proposes a divide-and-conquer framework to solve very large global SfM at the scale of millions of images.

Exploring Linear Relationship in Feature Map Subspace for ConvNets Compression

no code implementations15 Mar 2018 Dong Wang, Lei Zhou, Xueni Zhang, Xiao Bai, Jun Zhou

In this way, most of the representative information in the network can be retained in each cluster.


Fast Subspace Clustering Based on the Kronecker Product

no code implementations15 Mar 2018 Lei Zhou, Xiao Bai, Xianglong Liu, Jun Zhou, Hancock Edwin

Therefore, the efficiency and scalability of traditional spectral clustering methods can not be guaranteed for large scale datasets.


Progressive Large Scale-Invariant Image Matching in Scale Space

no code implementations ICCV 2017 Lei Zhou, Siyu Zhu, Tianwei Shen, Jinglu Wang, Tian Fang, Long Quan

In this paper, we propose a scale-invariant image matching approach to tackling the very large scale variation of views.

Image Retrieval Retrieval

Face Parsing via a Fully-Convolutional Continuous CRF Neural Network

no code implementations12 Aug 2017 Lei Zhou, Zhi Liu, Xiangjian He

In this work, we address the face parsing task with a Fully-Convolutional continuous CRF Neural Network (FC-CNN) architecture.

Face Parsing

Parallel Structure from Motion from Local Increment to Global Averaging

no code implementations28 Feb 2017 Siyu Zhu, Tianwei Shen, Lei Zhou, Runze Zhang, Jinglu Wang, Tian Fang, Long Quan

In this paper, we tackle the accurate and consistent Structure from Motion (SfM) problem, in particular camera registration, far exceeding the memory of a single computer in parallel.


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