Skip to content

Latest commit

 

History

History
69 lines (62 loc) · 18.9 KB

Y2019.md

File metadata and controls

69 lines (62 loc) · 18.9 KB
Raw

2019 Dec

2019 Nov

  • Visual Semantic Navigation Using Scene Priors [paper] [my repo] (1)
  • Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learning [paper] [my repo] (2)
  • Multi-Agent Manipulation via Locomotion using Hierarchical Sim2Real [paper] [my repo] (1)
  • Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World [paper] [my repo] (1)
  • On Evaluation of Embodied Navigation Agents [paper] [my repo] (1)
  • Data-Efficient Hierarchical Reinforcement Learning [paper] [my repo] (2)
  • Holistic++ Scene Understanding: Single-view 3D Holistic Scene Parsing and Human Pose Estimation with Human-Object Interaction and Physical Commonsense [paper] [my repo] (1)
  • An Empirical Study of Example Forgetting during Deep Neural Network Learning [paper] [my repo] (1)
  • Deep Hough Voting for 3D Object Detection in Point Clouds [paper] [code] [my repo] (1)
  • Motion Perception in Reinforcement Learning with Dynamic Objects [paper] [code] [my repo] (1)
  • Tiny Video Networks [paper] [my repo] (1)
  • SplitNet: Sim2Sim and Task2Task Transfer for Embodied Visual Navigation [paper] [code] [my repo] (2)
  • Model-based Behavioral Cloning with Future Image Similarity Learning, CoRL 2019 [paper] [code] [my repo] (3)

2019 Oct

  • Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution, CVPR 2019 [paper] [my repo] (1)
  • Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression, CVPR 2019 [paper] [my repo] (1)
  • Model-Based Robot Imitation with Future Image Similarity, IJCV 2019 [paper] [my repo] (1)

2019 Sep

  • Asymmetric Actor Critic for Image-Based Robot Learning, RSS 2018 [paper] [my repo] (1)
  • Asynchronous Methods for Deep Reinforcement Learning, ICML 2016 [paper] [my repo] (2)
  • Unsupervised Image-to-Image Translation Networks, NIPS 2017 [paper] [code] [my repo] (1)
  • Reinforcement Learning With Unsupervised Auxiliary Tasks, ICLR 2017 [paper] [blog] [forum] [my repo] (2)
  • Sim-to-Real Reinforcement Learning for Deformable Object Manipulation, CoRL 2018 [paper] [my repo] (2)
  • Sim-to-Real Transfer with Neural-Augmented Robot Simulation, CoRL 2018 [paper] [my repo] (1)
  • Sim-to-Real via Sim-to-Sim: Data-efficient Robotic Grasping via Randomized-to-Canonical Adaptation Networks, CVPR 2019 [paper] [my repo] (4)
  • Sim-Real Joint Reinforcement Transfer for 3D Indoor Navigation, CVPR 2019 [paper] [my repo] (3)
  • Deep Drone Racing: Learning Agile Flight in Dynamic Environments [paper] [my repo] (1)
  • End to End Learning for Self-Driving Cars [paper] [code0] [code1] [my repo] (4)
  • Learning to Drive from Simulation without Real World Labels [paper] [blog] [my repo] (3)

2019 Aug

  • An Integrity Framework for Image-Based Navigation Systems [paper] [my repo] (1)
  • Forman-Ricci Flow for Change Detection in Large Dynamic Data Sets [paper] [my repo] (1)
  • Guiding Image Segmentation On The Fly: Interactive Segmentation From A Feedback Control Perspective [paper] [my repo] (1)
  • Non-Rigid 2D-3D Pose Estimation and 2D Image Segmentation [paper] [my repo] (1)
  • Robust Physical-World Attacks on Deep Learning Visual Classification [paper] [my repo] (1)
  • Learning Robot Activities from First-Person Human Videos Using Convolutional Future Regression [paper] [my repo] (1)
  • Learning Real-World Robot Policies by Dreaming [paper] [my repo] (2)

2019 Jul

  • Learning Latent Super-Events to Detect Multiple Activities in Videos [paper] [code] [my repo] (1)
  • AssembleNet: Searching for Multi-Stream Neural Connectivity in Video Architectures [paper] [my repo] (1)

2019 Apr

  • Path Aggregation Network for Instance Segmentation [paper] [code] [pwd] [my repo] (1)
  • M2Det: A Single-Shot Object Detector based on Multi-Level Feature Pyramid Network [paper] [my repo] (1)
  • PoTion: Pose MoTion Representation for Action Recognition [paper] [my repo] (1)
  • ContextVP: Fully Context-Aware Video Prediction [paper] [my repo] (1)
  • Flow-Grounded Spatial-Temporal Video Prediction from Still Images [paper] [my repo] (1)
  • Two-Stream Convolutional Networks for Action Recognition in Videos [paper] [my repo] (1)
  • MoCoGAN: Decomposing Motion and Content for Video Generation [paper] [code] [my repo] (1)
  • FoldingNet: Point Cloud Auto-encoder via Deep Grid Deformation [paper] [my repo] (1)
  • Action Anticipation with RBF Kernelized Feature Mapping RNN [paper] [my repo] (2)

2019 Mar

  • Decomposing Motion and Content for Natural Video Sequence Prediction [note] [paper] [review] [code] [my slide] [my repo] (3)
  • Reward Learning from Human Preferences and Demonstrations in Atari [paper] [my repo] (1)
  • Fast R-CNN [paper] [slide] [code] [my repo] (1)
  • SDC-Net: Video Prediction Using Spatially-Displaced Convolution [paper] [my repo] (1)
  • R-CNN, Fast R-CNN, Faster R-CNN, YOLO — Object Detection Algorithms [article] (3)
  • Automatic Delineation of the Myocardial Wall from CT Images via Shape Segmentation and Variational Region Growing [paper] [my repo] (1)
  • Active Contours Without Edges [paper] [my repo] (3)