Versions Compared

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.

...

Center

Fall 2019

Week/DatePapersSlidesPresenter
8/30

Video Segmentation:

MaskTrack:http://openaccess.thecvf.com/content_cvpr_2017/papers/Perazzi_Learning_Video_Object_CVPR_2017_paper.pdf

FEELVOS: http://openaccess.thecvf.com/content_CVPR_2019/papers/Voigtlaender_FEELVOS_Fast_End-To-End_Embedding_Learning_for_Video_Object_Segmentation_CVPR_2019_paper.pdf

MOTS: https://arxiv.org/abs/1902.03604

Video Instance Segmentation: https://arxiv.org/abs/1905.04804

 Fengting
9/6

Topic: Active Vision System

Embodied Visual Recognition: https://arxiv.org/pdf/1904.04404.pdf

Learning_to_look_around: http://www.cs.utexas.edu/~grauman/papers/lookaround_cvpr2018.pdf

RL_Manipulating_Objects: https://arxiv.org/pdf/1811.08067.pdf

Active Vision SystemZihao
9/13DaML Study Group  
9/20

Topic: Human Trajectory Prediction

20190920 Human Motion Trajectory Prediction.pdfRui
9/27  Lizhen
10/4

Topic: 3D geometric recovery

GeoNet: Qi, Xiaojuan, et al. "Geonet: Geometric neural network for joint depth and surface normal estimation." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018.
Sfm-learner: Zhou, Tinghui, et al. "Unsupervised learning of depth and ego-motion from video." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2017.
LEGO: Yang, Zhenheng, et al. "Lego: Learning edge with geometry all at once by watching videos." Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018.
3D geometric learning.pptxJiachen
10/11DaML Study Group  
10/18  Fengting
10/25  Rui
11/1  Zihao
11/8DaML Study Group  
11/15CVPR deadline  
11/22  Lizhen
11/29Thanksgiving holiday  
12/6DaML Study Group  
12/13  Jiachen

Fall 2018

Week/DatePapersPresenter
10/5

Learning to Navigate in Complex Environments https://arxiv.org/abs/1611.03673

Learning to Navigate in Cities Without a Map https://arxiv.org/abs/1804.00168

Zihan
10/12 Qian
10/19 Fengting
10/26Group Normalization. https://arxiv.org/abs/1803.08494Rui

Spring 2018

Week/DatePapersPresenter
1/19

You only look once: Unified, real-time object detection https://arxiv.org/pdf/1506.02640.pdf

YOLO9000: better, faster, stronger https://arxiv.org/pdf/1612.08242.pdf . YOLO.pptx
Fengting
1/26Learning Features by Watching Objects Move http://people.eecs.berkeley.edu/~pathak/unsupervised_video/Zihan
2/2Zero-Shot Visual Imitation https://openreview.net/forum?id=BkisuzWRWQian
2/9Focal Loss for Dense Object Detection https://arxiv.org/abs/1708.02002Dafang
2/16On the Convergence of Adam and Beyond, Adam.pptx. https://openreview.net/forum?id=ryQu7f-RZFengting
2/23ECCV deadline 
3/2ECCV deadline 
3/9Spring break 
3/16Learning to Parse Wireframes in Images of Man-Made EnvironmentsZihan
3/23

Detect-and-Track: Efficient Pose Estimation in Videos https://arxiv.org/abs/1712.09184

Qian
3/30Fully-Convolutional Siamese Networks for Object Tracking https://arxiv.org/abs/1606.09549Dafang
4/6Dynamic Routing Between Capsules, capsule_network.pptx . https://arxiv.org/abs/1710.09829Fengting

 

Fall 2017

Week/DatePapersPresenter
8/25

 Learning to See by Moving https://arxiv.org/abs/1505.01596

Zihan
9/1

Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue https://arxiv.org/abs/1603.04992

Zihan
9/8ORB-SLAM: A Versatile and Accurate Monocular SLAM System http://webdiis.unizar.es/~raulmur/orbslam/..ORB_slamFengting
9/15Unsupervised Learning of Depth and Ego-Motion from Video https://people.eecs.berkeley.edu/~tinghuiz/projects/SfMLearner/Zihan
9/22Semi-dense visual odometry for a monocular camera https://vision.in.tum.de/_media/spezial/bib/engel2013iccv.pdf

 

Qian/ Zihan
9/29LSD-SLAM: Large-Scale Direct Monocular SLAM https://vision.in.tum.de/_media/spezial/bib/engel14eccv.pdfQian
10/6
FlowNet: Learning Optical Flow with Convolutional Networks: https://github.com/liruoteng/FlowNet
Live Dense Reconstruction with a Single Moving Camera
Zihan
10/13

EVO: A Geometric Approach to Event-Based 6-DOF Parallel Tracking and Mapping in Real Time

http://ieeexplore.ieee.org/abstract/document/7797445/ . .EVO_presentation.pptx

Fengting
10/20Image-to-Image Translation with Conditional Adversarial Networks https://arxiv.org/abs/1611.07004Xi
10/27Diret sparse Odometry https://arxiv.org/abs/1607.02565Qian
11/3Diret sparse Odometry https://arxiv.org/abs/1607.02565Qian
11/10CVPR deadline 
11/17CVPR deadline 
11/24Thanksgiving holiday 
12/1Cancelled 
12/8

What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision? https://arxiv.org/abs/1703.04977

Zihan
12/15

DeepVO : Towards Visual Odometry with Deep Learning http://senwang.gitlab.io/DeepVO/

UnDeepVO : Monocular Visual Odometry through Unsupervised Deep Learning http://senwang.gitlab.io/UnDeepVO/, DeepVO&UnDeepVO.pptx

Fengting
12/22One-shot Imitation Learning https://arxiv.org/abs/1703.07326

Qian

...