Get our free extension to see links to code for papers anywhere online!

 Add to Chrome

 Add to Firefox

CatalyzeX Code Finder - Browser extension linking code for ML papers across the web! | Product Hunt Embed
Unsupervised Monocular Depth Learning in Dynamic Scenes

Nov 07, 2020
Hanhan Li, Ariel Gordon, Hang Zhao, Vincent Casser, Anelia Angelova

* Accepted at 4th Conference on Robot Learning (CoRL 2020) 

  Access Paper or Ask Questions

AssembleNet++: Assembling Modality Representations via Attention Connections

Aug 18, 2020
Michael S. Ryoo, AJ Piergiovanni, Juhana Kangaspunta, Anelia Angelova

* ECCV 2020 
* ECCV 2020 camera-ready version 

  Access Paper or Ask Questions

Adversarial Generative Grammars for Human Activity Prediction

Aug 14, 2020
AJ Piergiovanni, Anelia Angelova, Alexander Toshev, Michael S. Ryoo

* ECCV 2020 (Oral) 

  Access Paper or Ask Questions

AttentionNAS: Spatiotemporal Attention Cell Search for Video Classification

Jul 31, 2020
Xiaofang Wang, Xuehan Xiong, Maxim Neumann, AJ Piergiovanni, Michael S. Ryoo, Anelia Angelova, Kris M. Kitani, Wei Hua

* ECCV 2020 

  Access Paper or Ask Questions

Mask2CAD: 3D Shape Prediction by Learning to Segment and Retrieve

Jul 26, 2020
Weicheng Kuo, Anelia Angelova, Tsung-Yi Lin, Angela Dai

* ECCV 2020 (Spotlight) 

  Access Paper or Ask Questions

What Matters in Unsupervised Optical Flow

Jun 08, 2020
Rico Jonschkowski, Austin Stone, Jonathan T. Barron, Ariel Gordon, Kurt Konolige, Anelia Angelova

* Source code is available at https://github.com/google-research/google-research/tree/master/uflow 

  Access Paper or Ask Questions

Differentiable Mapping Networks: Learning Structured Map Representations for Sparse Visual Localization

May 19, 2020
Peter Karkus, Anelia Angelova, Vincent Vanhoucke, Rico Jonschkowski

* ICRA 2020 

  Access Paper or Ask Questions

Taskology: Utilizing Task Relations at Scale

May 14, 2020
Yao Lu, Sören Pirk, Jan Dlabal, Anthony Brohan, Ankita Pasad, Zhao Chen, Vincent Casser, Anelia Angelova, Ariel Gordon


  Access Paper or Ask Questions

X-Ray: Mechanical Search for an Occluded Object by Minimizing Support of Learned Occupancy Distributions

Apr 20, 2020
Michael Danielczuk, Anelia Angelova, Vincent Vanhoucke, Ken Goldberg

* 8 pages, 6 figures 

  Access Paper or Ask Questions

Improving Semantic Segmentation through Spatio-Temporal Consistency Learned from Videos

Apr 11, 2020
Ankita Pasad, Ariel Gordon, Tsung-Yi Lin, Anelia Angelova


  Access Paper or Ask Questions

Evolving Losses for Unsupervised Video Representation Learning

Feb 26, 2020
AJ Piergiovanni, Anelia Angelova, Michael S. Ryoo

* CVPR 2020 
* arXiv admin note: text overlap with arXiv:1906.03248 

  Access Paper or Ask Questions

SPIN: A High Speed, High Resolution Vision Dataset for Tracking and Action Recognition in Ping Pong

Dec 13, 2019
Steven Schwarcz, Peng Xu, David D'Ambrosio, Juhana Kangaspunta, Anelia Angelova, Huong Phan, Navdeep Jaitly


  Access Paper or Ask Questions

KeyPose: Multi-view 3D Labeling and Keypoint Estimation for Transparent Objects

Dec 05, 2019
Xingyu Liu, Rico Jonschkowski, Anelia Angelova, Kurt Konolige


  Access Paper or Ask Questions

Tiny Video Networks

Oct 15, 2019
AJ Piergiovanni, Anelia Angelova, Michael S. Ryoo


  Access Paper or Ask Questions

Unsupervised Monocular Depth and Ego-motion Learning with Structure and Semantics

Jun 12, 2019
Vincent Casser, Soeren Pirk, Reza Mahjourian, Anelia Angelova

* CVPR Workshop on Visual Odometry & Computer Vision Applications Based on Location Clues (VOCVALC), 2019. This is an extension of arXiv:1811.06152: Depth Prediction Without the Sensors: Leveraging Structure for Unsupervised Learning from Monocular Videos. Thirty-Third AAAI Conference on Artificial Intelligence (AAAI'19) 

  Access Paper or Ask Questions

Evolving Losses for Unlabeled Video Representation Learning

Jun 07, 2019
AJ Piergiovanni, Anelia Angelova, Michael S. Ryoo

* Non-archival abstract for CVPR Workshop on Learning from Unlabeled Videos 

  Access Paper or Ask Questions

AssembleNet: Searching for Multi-Stream Neural Connectivity in Video Architectures

May 30, 2019
Michael S. Ryoo, AJ Piergiovanni, Mingxing Tan, Anelia Angelova


  Access Paper or Ask Questions

Depth from Videos in the Wild: Unsupervised Monocular Depth Learning from Unknown Cameras

Apr 10, 2019
Ariel Gordon, Hanhan Li, Rico Jonschkowski, Anelia Angelova


  Access Paper or Ask Questions

ShapeMask: Learning to Segment Novel Objects by Refining Shape Priors

Apr 05, 2019
Weicheng Kuo, Anelia Angelova, Jitendra Malik, Tsung-Yi Lin


  Access Paper or Ask Questions

Learning Differentiable Grammars for Continuous Data

Feb 01, 2019
AJ Piergiovanni, Anelia Angelova, Michael S. Ryoo


  Access Paper or Ask Questions

Future Segmentation Using 3D Structure

Nov 28, 2018
Suhani Vora, Reza Mahjourian, Soeren Pirk, Anelia Angelova


  Access Paper or Ask Questions

Evolving Space-Time Neural Architectures for Videos

Nov 26, 2018
AJ Piergiovanni, Anelia Angelova, Alexander Toshev, Michael S. Ryoo


  Access Paper or Ask Questions

Depth Prediction Without the Sensors: Leveraging Structure for Unsupervised Learning from Monocular Videos

Nov 15, 2018
Vincent Casser, Soeren Pirk, Reza Mahjourian, Anelia Angelova

* Thirty-Third AAAI Conference on Artificial Intelligence (AAAI'19) 

  Access Paper or Ask Questions

Object category learning and retrieval with weak supervision

Jul 23, 2018
Steven Hickson, Anelia Angelova, Irfan Essa, Rahul Sukthankar

* Camera-ready version for NIPS 2017 workshop Learning with Limited Labeled Data 

  Access Paper or Ask Questions

Unsupervised Learning of Depth and Ego-Motion from Monocular Video Using 3D Geometric Constraints

Jun 09, 2018
Reza Mahjourian, Martin Wicke, Anelia Angelova

* Upload CVPR camera-ready 

  Access Paper or Ask Questions

Deep Value Networks Learn to Evaluate and Iteratively Refine Structured Outputs

Aug 08, 2017
Michael Gygli, Mohammad Norouzi, Anelia Angelova

* Published at ICML 2017 

  Access Paper or Ask Questions

Geometry-Based Next Frame Prediction from Monocular Video

Jun 12, 2017
Reza Mahjourian, Martin Wicke, Anelia Angelova

* To appear in 2017 IEEE Intelligent Vehicles Symposium 

  Access Paper or Ask Questions