The classification of articles may be inaccurate due to personal limited knowledge level.

Content

• Data Structure
  • Tree
• Machine Learning
  • Algorithm
• Neural Network
  • Framework
  • Network Architecture
  • Neural Network Component
  • Optimizer
• Computer Vision
  • Dataset
  • 2D Object Detection
    • Algorithm
  • 3D Object Detection
    • Algorithm
  • 2D Segmentation
    • Algorithm
  • 3D Segmentation
    •   Algorithm
  • 2D Pose
    • Algorithm
  • 3D Pose
    •   Algorithm
  • Video
    • Segmentation
    • Motion Representation
• Generative Model
  • VAE (Variational Auto-Encoder)
    • Models
    • Applications
  • GAN (Generative Adversarial Networks)
    • Models
    • Applications
• Reinforcement Learning
  • Environment
  • Algorithm
  • RL in Games
  • Distributional RL
• Transfer Learning & Meta Learning
  • Algorithm or Model
  • Zero Shot Learning
• Robot
  • Dataset
  • Hardware
  • Grasping
    • Grasping with RL
    • Grasping Unknown Objects
    • Grasping in Cluttered Environment
    • Grasping via Segmentation
    • Grasping Points Selection
  • Machine Vision
    • Active Perception
    • Motion Prediction
  • Interactive Perception

Data Structure

Tree

• 【Kd-tree】Multidimensional binary search trees used for associative searching (1975)

• 【Oc-tree】Octree encoding: A new technique for the representation, manipulation and display of arbitrary 3-d objects by computer (1980)

Machine Learning

Algorithm

• 【SVM】Least squares support vector machine classifiers (Springer 1999)

• 【PCA】Singular value decomposition and principal component analysis (Springer 2003)

Neural Network

Framework

• Torch7: A MATLAB-like environment for machine learning (NIPS workshop 2011)

• Caffe: Convolutional Architecture for Fast Feature Embedding (arxiv 2014)

• TensorFlow: A System for Large-Scale Machine Learning (OSDI 2016)

Network Architecture

• Long Short Term Memory Network (Journals 1997)

• 【VGG16】Very Deep Convolutional Networks for Large-Scale Image Recognition (arxiv 2014)

• Dueling Network Architectures for Deep Reinforcement Learning (arxiv 2015)

• 【STN】Recurrent Spatial Transformer Networks (arxiv 2015)

• 【FCN】Fully Convolutional Networks for Semantic Segmentation (cv-foundation 2015)

• FaceNet: A Unified Embedding for Face Recognition and Clustering (cv-foundation 2015)

• 【C3D】Learning Spatiotemporal Features with 3D Convolutional Networks (ICCV 2015)

• 【ResNet】Deep Residual Learning for Image Recognition (openaccess.thecvf 2016)

• 【GCN】Semi-supervised classification with graph convolutional networks (ICLR 2017)

• Non-local Neural Networks (arxiv 2017)

• 【SPN】Learning Affinity via Spatial Propagation Networks (NIPS 2017)

• 【Capsule】Dynamic Routing Between Capsules (NIPS 2017)

• MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications (arxiv 2017)

• PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning (arxiv 2017)

• PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes (arxiv 2017)

• 【PSMNet】Pyramid Stereo Matching Network (CVPR 2018)

• PlaneNet: Piece-wise Planar Reconstruction from a Single RGB Image (CVPR 2018)

• SBNet: Sparse Blocks Network for Fast Inference (arxiv 2018)

Neural Network Component

• 【ReLu】Rectified Linear Units Improve Restricted Boltzmann Machines (ICML 2010)

• Dropout: a simple way to prevent neural networks from overfitting (jmlr 2014)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (ICML 2015)

• 【center loss】A Discriminative Feature Learning Approach for Deep Face Recognition (ECCV 2016)

• Group Normalization (arxiv 2018)

Optimizer

• 【ASGD】Acceleration of stochastic approximation by averaging (Journals 1992)

• 【Adagrad】Adaptive Subgradient Methods for Online Learning and Stochastic Optimization (jmlr 2011)

• ADADELTA: An Adaptive Learning Rate Method (arxiv 2012)

• 【RMSprop】Generating Sequences With Recurrent Neural Networks (arxiv 2013)

• Adam: A Method for Stochastic Optimization (ICLR 2015)

• Learning to learn by gradient descent by gradient descent (NIPS 2016)

Computer Vision

Dataset

• ImageNet: A large-scale hierarchical image database (CVPR 2009)

• 【NYUV2】Indoor segmentation and support inference from rgbd images (ECCV 2012)

• 【KITTI】Vision meets robotics: The KITTI dataset (IJRR 2013)

• 【Daimler Urban Segmentation】Efficient Multi-Cue Scene Segmentation (GCPR 2013)

• 【Pascal Context】The Role of Context for Object Detection and Semantic Segmentation in the Wild (CVPR 2014)

• 【Pascal VOC】The Pascal Visual Object Classes Challenge: A Retrospective (IJCV 2014)

• 【COCO】Microsoft COCO: Common Objects in Context (ECCV 2014)

• 【ILSVRC】ImageNet Large Scale Visual Recognition Challenge (IJCV 2015)

• 【ModelNet40】3D ShapeNets: A Deep Representation for Volumetric Shapes (CVPR 2015) Dataset is available at [website].

• 【Cityscapes】The Cityscapes Dataset for Semantic Urban Scene Understanding (CVPR 2016)

• 【S3DIS】3d semantic parsing of largescale indoor spaces (CVPR 2016)

• 【ScanNet】ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes (CVPR workshop 2018)

2D Object Detection

Algorithm

• 【R-CNN】Rich feature hierarchies for accurate object detection and semantic segmentation (CVPR 2014)

• Fast R-CNN (ICCV 2015)

• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks (NIPS 2015)

• SSD: Single Shot MultiBox Detector (ECCV 2016)

• R-FCN: Object Detection via Region-based Fully Convolutional Networks (NIPS 2016)

• 【YOLO】You Only Look Once: Unified, Real-Time Object Detection (CVPR 2016)

• YOLO9000: Better, Faster, Stronger (openaccess.thecvf 2017)

• FSSD: Feature Fusion Single Shot Multibox Detector (arxiv 2017)

• 【RFB-SSD】Receptive Field Block Net for Accurate and Fast Object Detection (arxiv 2017)

• 【RefineDet】Single-Shot Refinement Neural Network for Object Detection (arxiv 2017)

• MegDet: A Large Mini-Batch Object Detector (arxiv 2017)

• Light-Head R-CNN: In Defense of Two-Stage Object Detector (arxiv 2017)

• 【RetinaNet / Focal Loss】Focal Loss for Dense Object Detection (ICCV 2017)

• YOLOv3: An Incremental Improvement (?? 2018)

3D Object Detection

Algorithm

• SSD-6D: Making RGB-based 3D detection and 6D pose estimation great again (openaccess.thecvf 2017)

• 【Frustum PointNets】Frustum PointNets for 3D Object Detection from RGB-D Data (arxiv 2017)

2D Segmentation

Algorithm

• 【U-Net】U-net: Convolutional networks for biomedical image segmentation (arxiv 2015)

• 【DeepMask】Learning to Segment Object Candidates (arxiv 2015)

• Instance-aware Semantic Segmentation via Multi-task Network Cascades (CVPR 2016)

• Mask R-CNN (ICCV 2017)

• 【W-Net】W-Net: A Deep Model for Fully Unsupervised Image Segmentation (arxiv 2017)

• 【RefineNet】RefineNet: Multi-Path Refinement Networks for High-Resolution Semantic Segmentation (CVPR 2017)

• Semantic Instance Segmentation with a Discriminative Loss Function (CVPR workshop 2017)

• Deep Extreme Cut: From Extreme Points to Object Segmentation (CVPR 2018)

• Weakly Supervised Instance Segmentation using Class Peak Response (CVPR 2018)

• 【Mask^X RCNN】Learning to Segment Every Thing (CVPR 2018)

3D Segmentation

Algorithm

• Deep learning with sets and point clouds (ICLR 2017)

• PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation (CVPR 2017)

• 3DContextNet: K-d Tree Guided Hierarchical Learning of Point Clouds Using Local and Global Contextual Cues (CVPR 2017)

• PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space (NIPS 2017)

• Escape from cells: Deep kd-networks for the recognition of 3d point cloud models (ICCV 2017)

• 【PointSIFT】PointSIFT: A SIFT-like Network Module for 3D Point Cloud Semantic Segmentation (arxiv 2018)

• 【Kd-network】PointCNN (arxiv 2018)

• 【SO-Net】SO-Net: Self-Organizing Network for Point Cloud Analysis (CVPR 2018)

• 【SGPN】SGPN: Similarity Group Proposal Network for 3D Point Cloud Instance Segmentation (CVPR 2018)

• 【DGCNN】Dynamic Graph CNN for Learning on Point Clouds

2D Pose

Algorithm

• 【open pose】Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields (CVPR 2017)

• 【G-RMI】Towards accurate multi-person pose estimation in the wild (CVPR 2017)

• Joint Multi-Person Pose Estimation and Semantic Part Segmentation (CVPR 2017)

• RMPE: Regional Multi-Person Pose Estimation (ICCV 2017)

• Vnect: Real-time 3d human pose estimation with a single rgb camera (SIGGRAPH 2017)

• 【CPN】Cascaded Pyramid Network for Multi-Person Pose Estimation (CVPR 2018)

3D Pose

Algorithm

• Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Pose (CVPR 2017)

Video

Segmentation

• Learning to Segment Instances in Videos with Spatial Propagation Network (CVPR workshop 2017)

• SegFlow: Joint Learning for Video Object Segmentation and Optical Flow (CVPR 2017)

• Learning Features by Watching Objects Move (CVPR 2017)

Motion Representation

• 【TVnet】End-to-End Learning of Motion Representation for Video Understanding (CVPR 2018)

Generative Model

VAE (Variational Auto-Encoder)

Models

Applications

• Attribute2Image: Conditional Image Generation from Visual Attributes (ECCV 2016)

GAN (Generative Adversarial Networks)

Models

• 【GAN】Generative Adversarial Networks (NIPS 2014)

• 【CGAN】Conditional Generative Adversarial Nets (arxiv 2014)

• 【AAE】Adversarial Autoencoders (arxiv 2015)

• 【DCGAN】Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks (arxiv 2015)

Applications

Reinforcement Learning

Environment

• MuJoCo: A physics engine for model-based control (International Conference on Intelligent Robots and Systems 2012)

• OpenAI Gym (arxiv 2016)

• 【rllab】Benchmarking Deep Reinforcement Learning for Continuous Control (jmlr 2016)

• DeepMind Lab (arxiv 2016)

• StarCraft II: A New Challenge for Reinforcement Learning (arxiv 2017)

• MAgent: A Many-Agent Reinforcement Learning Platform for Artificial Collective Intelligence (arxiv 2017)

Algorithm

• Q-learning (Springer 1992)

• 【DQN】Playing Atari with Deep Reinforcement Learning (NIPS workshop 2013)

• 【DPG】Deterministic Policy Gradient Algorithms (ICML 2014)

• 【TRPO】Trust Region Policy Optimization (ICML 2015)

• 【Double-DQN】Deep Reinforcement Learning with Double Q-learning (AAAI 2016)

• 【h-DQN】Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation (NIPS 2016)

• 【A3C】Asynchronous Methods for Deep Reinforcement Learning (ICML 2016)

• 【DDPG】Continuous control with deep reinforcement learning (ICLR 2016)

• 【NAF】Continuous Deep Q-Learning with Model-based Acceleration (arxiv 2016)

• 【ACER】Sample Efficient Actor-Critic with Experience Replay (arxiv 2016)

• 【GAIL】Generative Adversarial Imitation Learning (NIPS 2016)

• Neural Episodic Control (arxiv 2017)

• Q-PROP: SAMPLE-EFFICIENT POLICY GRADIENT WITH AN OFF-POLICY CRITIC (ICLR 2017)

• 【PPO】Proximal Policy Optimization Algorithms (arxiv 2017)

• Emergence of Locomotion Behaviours in Rich Environments (arxiv 2017)

• 【ACKTR】Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (NIPS 2017)

• 【HER】Hindsight Experience Replay (NIPS 2017)

• Noisy Networks for Exploration (ICLR 2018)

RL in Games

• Control of Memory, Active Perception, and Action in Minecraft (arxiv 2016)

Distributional RL

• A Distributional Perspective on Reinforcement Learning (arxiv 2017)

Curiosity-Driven RL

• Curiosity-driven Exploration by Self-supervised Prediction (ICML 2017)

• Intrinsically motivated model learning for developing curious robots (Artificial Intelligence 2017)

• Computational Theories of Curiosity-Driven Learning (arxiv 2018)

• Emergence of Structured Behaviors from Curiosity-Based Intrinsic Motivation (arxiv 2018)

Transfer Learning & Meta Learning

Algorithm or Model

• 【MAML】Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks (arxiv 2017)

• OPTIMIZATION AS A MODEL FOR FEW-SHOT LEARNING (ICLR 2017)

• 【SNAIL】A Simple Neural Attentive Meta-Learner (ICLR 2018)

Zero Shot Learning

• ADAPT: Zero-Shot Adaptive Policy Transfer for Stochastic Dynamical Systems (isrr 2017)

• Zero-Shot Object Detection (arxiv 2018)

• Zero-shot Recognition via Semantic Embeddings and Knowledge Graphs (CVPR 2018)

Robot

Hardware

Grasping

Dataset

• Deep Grasp: Detection and Localization of Grasps with Deep Neural Networks (arxiv 2018)

• Jacquard: A Large Scale Dataset for Robotic Grasp Detection (arxiv 2018)

Grasping with RL

Grasping Unknown Objects

• Ranking the good points: A comprehensive method for humanoid robots to grasp unknown objects (International Conference on Advanced Robotics 2013)

• Model-Free Segmentation and Grasp Selection of Unknown Stacked Objects (ECCV 2014)

• Pick and Place Without Geometric Object Models (ICRA 2018)

Grasping in Cluttered Environment

• Real-Time 3D Segmentation of Cluttered Scenes for Robot Grasping (ICHR 2012)

• 【GPD】High precision grasp pose detection in dense clutter (IROS 2016)

• Robotic Pick-and-Place of Novel Objects in Clutter with Multi-Affordance Grasping and Cross-Domain Image Matching (arxiv 2017)

Grasping via Segmentation

• Grasping novel objects with depth segmentation (IROS 2010)

• 3D scene segmentation for autonomous robot grasping (IROS 2012)

Grasping Points Selection

• GP-GPIS-OPT: Grasp planning with shape uncertainty using Gaussian process implicit surfaces and Sequential Convex Programming (ICRA 2015)

• Using Geometry to Detect Grasp Poses in 3D Point Clouds (ISRR 2015)

• Dex-Net 1.0: A Cloud-Based Network of 3D Objects for Robust Grasp Planning Using a Multi-Armed Bandit Model with Correlated Rewards (ICRA 2016)

• Dex-Net 2.0: Deep Learning to Plan Robust Grasps with Synthetic Point Clouds and Analytic Grasp Metrics (arxiv 2017)

• Dex-Net 3.0: Computing Robust Robot Suction Grasp Targets in Point Clouds using a New Analytic Model and Deep Learning (arxiv 2017)

Machine Vision

Active Perception

• Active Perception: Interactive Manipulation for Improving Object Detection (Standford University Journal 2018)

• Learning Instance Segmentation by Interaction (CVPR 2018)

Motion Prediction

• 【SE3-Net】SE3-Nets: Learning Rigid Body Motion using Deep Neural Networks (ICRA 2017)

Interactive Perception

• Better Vision through Manipulation (Adaptive Behavior 2003)

• Interactive Perception: Closing the Gap Between Action and Perception (ICRA 2007)

• BIRTH OF THE OBJECT: DETECTION OF OBJECTNESS AND EXTRACTION OF OBJECT SHAPE THROUGH OBJECT–ACTION COMPLEXES (International Journal of Humanoid Robotics 2008)

• Interactive Segmentation for Manipulation in Unstructured Environments (ICRA 2009)

• Generating Object Hypotheses in Natural Scenes through Human-Robot Interaction (IROS 2011)

• Segmentation and learning of unknown objects through physical interaction (IEEE/RAS Int. Conf. on Humanoid Robots (Humanoids) 2011)

• Clearing a Pile of Unknown Objects using Interactive Perception (?? 2012)

• Segmentation of Cluttered Scenes through Interactive Perception (ICRA 2012)

• Interactive singulation of objects from a pile (ICRA 2012)

• Tracking-based Interactive Segmentation of Textureless Objects (ICRA 2013)

• Probabilistic Segmentation and Targeted Exploration of Objects in Cluttered Environments (Robotics, IEEE Transactions 2014)

• Interactive perception: Leveraging action in perception and perception in action (arxiv 2016)

• Segmenting objects through an autonomous agnostic exploration conducted by a robot (IRC 2017)

• Learning Instance Segmentation by Interaction (CVPR 2018)