Search Results for author:
Found 58 papers, 25 papers with code
You Only Scan Once: A Dynamic Scene Reconstruction Pipeline for 6-DoF Robotic Grasping of Novel Objects
In the realm of robotic grasping, achieving accurate and reliable interactions with the environment is a pivotal challenge.
Is Reference Necessary in the Evaluation of NLG Systems? When and Where?
The majority of automatic metrics for evaluating NLG systems are reference-based.
Nonsmooth-Optimization-Based Bandwidth Optimal Control for Precision Motion Systems
Precision motion systems are at the core of various manufacturing equipment.
GasMono: Geometry-Aided Self-Supervised Monocular Depth Estimation for Indoor Scenes
This paper tackles the challenges of self-supervised monocular depth estimation in indoor scenes caused by large rotation between frames and low texture.
Transcending the Acceleration-Bandwidth Trade-off: Lightweight Precision Stages with Active Control of Flexible Dynamics
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
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
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.
Unsupervised Recognition of Unknown Objects for Open-World Object Detection
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.
Exploring the Limits of Historical Information for Temporal Knowledge Graph Extrapolation
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.
Learning Adversarial Semantic Embeddings for Zero-Shot Recognition in Open Worlds
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.
Token Sparsification for Faster Medical Image Segmentation
To this end, we reformulate segmentation as a sparse encoding -> token completion -> dense decoding (SCD) pipeline.
Bokeh Rendering Based on Adaptive Depth Calibration Network
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.
Sequential Structure and Control Co-design of Lightweight Precision Stages with Active control of flexible modes
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
Moreover, the higher model performance on difficult examples and unseen data also demonstrates the generalization ability.
Spatially Exclusive Pasting: A General Data Augmentation for the Polyp Segmentation
Automated polyp segmentation technology plays an important role in diagnosing intestinal diseases, such as tumors and precancerous lesions.
Ranked #4 on
Medical Image Segmentation
on Kvasir-SEG
ASpanFormer: Detector-Free Image Matching with Adaptive Span Transformer
Generating robust and reliable correspondences across images is a fundamental task for a diversity of applications.
Learning Prototype via Placeholder for Zero-shot Recognition
Specifically, we combine seen classes to hallucinate new classes which play as placeholders of the unseen classes in the visual and semantic space.
Economical Precise Manipulation and Auto Eye-Hand Coordination with Binocular Visual Reinforcement Learning
Previous methods achieved good performance on such manipulation tasks.
PEGG-Net: Pixel-Wise Efficient Grasp Generation in Complex Scenes
Vision-based grasp estimation is an essential part of robotic manipulation tasks in the real world.
Self Pre-training with Masked Autoencoders for Medical Image Classification and Segmentation
Masked Autoencoder (MAE) has recently been shown to be effective in pre-training Vision Transformers (ViT) for natural image analysis.
Control Co-design of Actively Controlled Lightweight Structures for High-acceleration Precision Motion Systems
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
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.
Lung Swapping Autoencoder: Learning a Disentangled Structure-texture Representation of Chest Radiographs
Well-labeled datasets of chest radiographs (CXRs) are difficult to acquire due to the high cost of annotation.
Efficient Semi-Discrete Optimal Transport Using the Maximum Relative Error between Distributions
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
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
2) Seeded Graph Neural Network, which utilizes seed matches to pass messages within/across images and predicts assignment costs.
Self-Guided Curriculum Learning for Neural Machine Translation
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.
Cascaded Feature Warping Network for Unsupervised Medical Image Registration
In this paper, we pre-sent a cascaded feature warping network to perform the coarse-to-fine registration.
PointDSC: Robust Point Cloud Registration using Deep Spatial Consistency
Removing outlier correspondences is one of the critical steps for successful feature-based point cloud registration.
Goal-Oriented Gaze Estimation for Zero-Shot Learning
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.
Superradiant detection of microscopic optical dipolar interactions
The interaction between light and cold atoms is a complex phenomenon potentially featuring many-body resonant dipole interactions.
Atomic Physics Quantum Physics
Zero-Shot Translation Quality Estimation with Explicit Cross-Lingual Patterns
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
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.
Learning Discriminative Feature with CRF for Unsupervised Video Object Segmentation
In this paper, we introduce a novel network, called discriminative feature network (DFNet), to address the unsupervised video object segmentation task.
Ranked #1 on
Video Object Segmentation
on FBMS
Stochastic Bundle Adjustment for Efficient and Scalable 3D Reconstruction
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.
Self-Supervised Monocular 3D Face Reconstruction by Occlusion-Aware Multi-view Geometry Consistency
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.
Ranked #6 on
3D Face Reconstruction
on REALY (side-view)
Joint Semantic Segmentation and Boundary Detection using Iterative Pyramid Contexts
In this paper, we present a joint multi-task learning framework for semantic segmentation and boundary detection.
KFNet: Learning Temporal Camera Relocalization using Kalman Filtering
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.
ASLFeat: Learning Local Features of Accurate Shape and Localization
This work focuses on mitigating two limitations in the joint learning of local feature detectors and descriptors.
D3Feat: Joint Learning of Dense Detection and Description of 3D Local Features
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.
Ranked #2 on
Point Cloud Registration
on KITTI
BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networks
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.
Self-Supervised Learning of Depth and Motion Under Photometric Inconsistency
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.
Learning Two-View Correspondences and Geometry Using Order-Aware Network
First, to capture the local context of sparse correspondences, the network clusters unordered input correspondences by learning a soft assignment matrix.
A One-step Pruning-recovery Framework for Acceleration of Convolutional Neural Networks
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.
Learning Fully Dense Neural Networks for Image Semantic Segmentation
On the other hand, it learns more efficiently with the more efficient gradient backpropagation.
Ranked #73 on
Semantic Segmentation
on NYU Depth v2
ContextDesc: Local Descriptor Augmentation with Cross-Modality Context
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.
Beyond Photometric Loss for Self-Supervised Ego-Motion Estimation
Accurate relative pose is one of the key components in visual odometry (VO) and simultaneous localization and mapping (SLAM).
Matchable Image Retrieval by Learning from Surface Reconstruction
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.
GeoDesc: Learning Local Descriptors by Integrating Geometry Constraints
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.
Learning and Matching Multi-View Descriptors for Registration of Point Clouds
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
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.
Very Large-Scale Global SfM by Distributed Motion Averaging
This work proposes a divide-and-conquer framework to solve very large global SfM at the scale of millions of images.
Fast Subspace Clustering Based on the Kronecker Product
Therefore, the efficiency and scalability of traditional spectral clustering methods can not be guaranteed for large scale datasets.
Exploring Linear Relationship in Feature Map Subspace for ConvNets Compression
In this way, most of the representative information in the network can be retained in each cluster.
Progressive Large Scale-Invariant Image Matching in Scale Space
In this paper, we propose a scale-invariant image matching approach to tackling the very large scale variation of views.
Face Parsing via a Fully-Convolutional Continuous CRF Neural Network
In this work, we address the face parsing task with a Fully-Convolutional continuous CRF Neural Network (FC-CNN) architecture.
Parallel Structure from Motion from Local Increment to Global Averaging
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.
