Search Results - "Zhu, Menglong"
-
1
Sparse Representation for 3D Shape Estimation: A Convex Relaxation Approach
Published in IEEE transactions on pattern analysis and machine intelligence (01-08-2017)“…We investigate the problem of estimating the 3D shape of an object defined by a set of 3D landmarks, given their 2D correspondences in a single image. A…”
Get full text
Journal Article -
2
Multi-image Matching via Fast Alternating Minimization
Published in 2015 IEEE International Conference on Computer Vision (ICCV) (01-12-2015)“…In this paper we propose a global optimization-based approach to jointly matching a set of images. The estimated correspondences simultaneously maximize…”
Get full text
Conference Proceeding Journal Article -
3
From Actemes to Action: A Strongly-Supervised Representation for Detailed Action Understanding
Published in 2013 IEEE International Conference on Computer Vision (01-12-2013)“…This paper presents a novel approach for analyzing human actions in non-scripted, unconstrained video settings based on volumetric, x-y-t, patch classifiers,…”
Get full text
Conference Proceeding Journal Article -
4
Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference
Published in 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (01-06-2018)“…The rising popularity of intelligent mobile devices and the daunting computational cost of deep learning-based models call for efficient and accurate on-device…”
Get full text
Conference Proceeding -
5
Giant second-harmonic generation in ferroelectric NbOI2
Published in Nature photonics (01-09-2022)“…Implementing nonlinear optical components in nanoscale photonic devices is challenged by phase-matching conditions requiring thicknesses in the order of…”
Get full text
Journal Article -
6
Speed/Accuracy Trade-Offs for Modern Convolutional Object Detectors
Published in 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (01-07-2017)“…The goal of this paper is to serve as a guide for selecting a detection architecture that achieves the right speed/memory/accuracy balance for a given…”
Get full text
Conference Proceeding -
7
Localization from semantic observations via the matrix permanent
Published in The International journal of robotics research (01-01-2016)“…Most approaches to robot localization rely on low-level geometric features such as points, lines, and planes. In this paper, we use object recognition to…”
Get full text
Journal Article -
8
Automatic Spatially-Aware Fashion Concept Discovery
Published in 2017 IEEE International Conference on Computer Vision (ICCV) (01-10-2017)“…This paper proposes an automatic spatially-aware concept discovery approach using weakly labeled image-text data from shopping websites. We first fine-tune…”
Get full text
Conference Proceeding -
9
End-to-End Unsupervised 4D Cardiac Motion Tracking With Spatiotemporal Optical Flow Networks
Published in IEEE access (2024)“…Cardiac motion tracking from echocardiography can be used to estimate and quantify myocardial motion within a cardiac cycle. It is a cost-efficient and…”
Get full text
Journal Article -
10
High‐Performance Organic Heterojunction Phototransistors Based on Highly Ordered Copper Phthalocyanine/para‐Sexiphenyl Thin Films
Published in Advanced functional materials (10-02-2017)“…High‐performance organic heterojunction phototransistors are fabricated using highly ordered copper phthalocyanine (CuPc) and para‐sexiphenyl (p‐6P) thin…”
Get full text
Journal Article -
11
Sparseness Meets Deepness: 3D Human Pose Estimation from Monocular Video
Published in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (01-06-2016)“…This paper addresses the challenge of 3D full-body human pose estimation from a monocular image sequence. Here, two cases are considered: (i) the image…”
Get full text
Conference Proceeding -
12
Efficient and Anisotropic Second Harmonic Generation in Few‐Layer SnS Film
Published in Advanced optical materials (01-11-2021)“…Group‐IV monochalcogenide ferroelectric materials possess fascinating nonlinear optical properties and electro‐optical effects which play a vital role in 2D…”
Get full text
Journal Article -
13
Broadband nonlinear optical properties of red fluorescent carbon dots
Published in Results in physics (01-07-2022)“…Carbon dots (CDs) provide ideal platforms for applications in bioimaging, sensing, and photocatalysis. Herein, a new type of red fluorescent carbon dot (RCD)…”
Get full text
Journal Article -
14
Gigantic blue shift of two-photon–induced photoluminescence of interpenetrated metal–organic framework (MOF)
Published in Nanophotonics (Berlin, Germany) (28-09-2023)“…As an important means of modern science and technology, multiphoton fluorescence plays an essential role in high-resolution imaging, photochemistry, micro- and…”
Get full text
Journal Article -
15
Single Image Pop-Up from Discriminatively Learned Parts
Published in 2015 IEEE International Conference on Computer Vision (ICCV) (01-12-2015)“…We introduce a new approach for estimating a fine grained 3D shape and continuous pose of an object from a single image. Given a training set of view…”
Get full text
Conference Proceeding Journal Article -
16
Van Der Waals Heterostructures between Small Organic Molecules and Layered Substrates
Published in Crystals (01-09-2016)“…Two dimensional atomic crystals, like grapheme (G) and molybdenum disulfide (MoS2), exhibit great interest in electronic and optoelectronic applications. The…”
Get full text
Journal Article Book Review -
17
Mobile Video Object Detection with Temporally-Aware Feature Maps
Published in 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (01-06-2018)“…This paper introduces an online model for object detection in videos designed to run in real-time on low-powered mobile and embedded devices. Our approach…”
Get full text
Conference Proceeding -
18
Single image 3D object detection and pose estimation for grasping
Published in 2014 IEEE International Conference on Robotics and Automation (ICRA) (01-05-2014)“…We present a novel approach for detecting objects and estimating their 3D pose in single images of cluttered scenes. Objects are given in terms of 3D models…”
Get full text
Conference Proceeding -
19
MobileNetV2: Inverted Residuals and Linear Bottlenecks
Published in 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (01-06-2018)“…In this paper we describe a new mobile architecture, MobileNetV2, that improves the state of the art performance of mobile models on multiple tasks and…”
Get full text
Conference Proceeding -
20
Rethinking RGB-D Salient Object Detection: Models, Data Sets, and Large-Scale Benchmarks
Published in IEEE transaction on neural networks and learning systems (01-05-2021)“…The use of RGB-D information for salient object detection (SOD) has been extensively explored in recent years. However, relatively few efforts have been put…”
Get full text
Journal Article