Frustum PointNets for 3D Object Detection From RGB-D Data

Frustum PointNets for 3D Object Detection from RGB-D Data Charles R. Qi1∗ Wei Liu2 Chenxia Wu2 Hao Su3 Leonidas J. Guibas1 1Stanford University 2Nuro, Inc. 3UC San Diego Abstract In this work, we study 3D object detection from RGB-D data in both indoor and outdoor scenes.

What Have We Learned From Deep Representations for …

what these powerful models actually have learned. In this paper we shed light on deep spatiotemporal net-works by visualizing what excites the learned models us-ing activation maximization by backpropagating on the in-put. We are the first to visualize the hierarchical features

  What, Have, Learned, What we have learned, Have learned

Finding Tiny Faces in the Wild With Generative Adversarial ...

faces, which are unfriendly for the face classifier. Toward-s this end, we design a refinement sub-network to recover some detailed information. In the discriminator network, the basic GAN [17, 12, 8] is trained to distinguish the real and fake high resolution images. To classify faces or non-

  Faces

Squeeze-and-Excitation Networks - openaccess.thecvf.com

Squeeze-and-Excitation Networks Jie Hu1∗ Li Shen2∗ Gang Sun1 hujie@momenta.ai lishen@robots.ox.ac.uk sungang@momenta.ai 1 Momenta 2 Department of Engineering Science, University of Oxford Abstract Convolutional neural networks are built upon the con-

  Network, Excitation, Squeeze and excitation networks, Squeeze

RegularFace: Deep Face Recognition via Exclusive ...

RegularFace: Deep Face Recognition via Exclusive Regularization Kai Zhao Jingyi Xu Ming-Ming Cheng ∗ TKLNDST, CS, Nankai University kaiz.xyz@gmail.com cmm@nankai.edu.cn

  Zhao

Protecting World Leaders Against Deep Fakes

Protecting World Leaders Against Deep Fakes Shruti Agarwal and Hany Farid University of California, Berkeley Berkeley CA, USA {shrutiagarwal, hfarid}@berkeley.edu

Auto-DeepLab: Hierarchical Neural Architecture Search for ...

Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation Chenxi Liu1∗, Liang-Chieh Chen 2, Florian Schroff2, Hartwig Adam2, Wei Hua2, Alan Yuille1, Li Fei-Fei3 1Johns Hopkins University 2Google 3Stanford University Abstract Recently, NeuralArchitectureSearch(NAS)hassuccess-

PointNet: Deep Learning on Point Sets ... - CVF Open Access

PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation Charles R. Qi* Hao Su* Kaichun Mo Leonidas J. Guibas Stanford University

  Open, Learning, Points, Deep, Sets, Pointnet, Deep learning on point sets

Class-Balanced Loss Based on Effective Number of Samples

and large-scale datasets including ImageNet and iNatural-ist. Our results show that when trained with the proposed class-balanced loss, the network is able to achieve signifi-cant performance gains on long-tailed datasets. 1. Introduction The recent success of deep Convolutional Neural Net-works (CNNs) for visual recognition [26, 37, 38, 16] owes

  Scale, Visual, Recognition, Visual recognition

ESRGAN: Enhanced Super-Resolution Generative Adversarial ...

ESRGAN: EnhancedSuper-Resolution Generative Adversarial Networks Xintao Wang 1, Ke Yu , Shixiang Wu2, Jinjin Gu3, Yihao Liu4, Chao Dong 2, Yu Qiao , and Chen Change Loy5 1 CUHK-SenseTime Joint Lab, The Chinese University of Hong Kong 2 Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences 3 The Chinese University of Hong Kong, …

  Network, Adversarial, Generative, Generative adversarial, Generative adversarial networks

Multiple Object Tracking Performance Metrics and ...

Multiple Object Tracking Performance Metrics and Evaluation in a Smart Room Environment ... • They should reflect its ability to consistently track ob-ject configurations through time, i.e. to correctly trace object trajectories, producing exactly one trajectory per object.

  Performance, Evaluation, Multiple, Tracking, Metrics, Object, Ject, Multiple object tracking performance metrics and, Multiple object tracking performance metrics and evaluation

Object Tracking: A Survey - UCF CRCV

analysis: detection of interesting moving objects, tracking of such objects from frame to frame, and analysis of object tracks to recognize their behavior. Therefore, the use of object tracking is pertinent in the tasks of: —motion-based recognition, that is, human identification based on gait, automatic ob-ject detection, etc;

  Tracking, Object, Ject, Object tracking

You Don't Only Look Once: Constructing Spatial-Temporal ...

directly use the bounding box regression modules from ob-ject detection for tracking. As for 3D object detection and tracking, [33,34] proposed a unified neural network to jointly perform 3D object detection, tracking and motion predic-tion. [24] proposed a joint detection and tracking system with monocular images input. [5] integrates a 3D Kalman

  Tracking, Ject

Generalized Intersection over Union: A Metric and A Loss ...

such as object localization, multiple object detection, ob-ject tracking and instance level segmentation rely on ac-curate bounding box regression. The dominant trend for improving performance of applications utilizing deep neu-ral networks is to propose either a better architecture back-bone [15, 13] or a better strategy to extract reliable local

  Tracking, Ject, Ob ject tracking

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE ...

cloud processing, including 3D shape classification, 3D ob-ject detection and tracking,3D point cloud segmentation, 3D point cloud registration, 6-DOF pose estimation, and 3D reconstruction [16], [17], [18]. Few surveys of deep learning ... detection and tracking, and 3D point cloud segmentation. In particular, the attributes of these datasets ...

  Tracking, Ject

Agilent OpenLAB CDS

ject to being changed, without notice, in future editions. Further, to the max- ... Tracking the Baseline 15 Allocating the Baseline 16 Definition of Terms 17 Principle of Operation 18 ... If the integrator does not ob tain a redefined initial baseline point,

  Tracking, Agilent, Ject, Openlab, Agilent openlab cds

Static and Dynamic Balancing Second Edition

only becomes apparent when the ob­ ject is rotating. bal Afte­r being anced dynamically, the object would be completely balanced in both static and dynamic conditions. The difference betwee baln stati­ c ance and dynamic balance is illus­ trated in Fig 1. I.t will be observed that when the rotor is stationary (static) the end masses may balance

  Dynamics, Static, Balancing, Ject, Static and dynamic balancing