2020 Dec
- Wi-Go: Accurate and Scalable Vehicle Positioning using WiFi Fine Timing Measurement, MobiSys 2020 [paper] [my repo] (1)
- Active Vision for Early Recognition of Human Actions, CVPR 2020 [paper] [my repo] (1)
2020 Nov
2020 Oct
- Recurrent Space-time Graph Neural Networks, NeurIPS 2019 [paper] [code] [my repo] (1)
- 3D Graph Neural Networks for RGBD Semantic Segmentation, ICCV 2017 [paper] [my repo] (1)
- A Behavioral Approach to Visual Navigation with Graph Localization Networks, RSS 2019 [paper] [blog] [video] [code] [my repo] (1)
- Zero-Shot Multi-View Indoor Localization via Graph Location Networks, MM 2020 [paper] [code] [my repo] (1)
- SceneGraphNet: Neural Message Passing for 3D Indoor Scene Augmentation, ICCV 2019 [paper] [code] [my repo] (1)
- A Comprehensive Survey on Graph Neural Networks, NNLS 2021 [paper] [my repo] (1)
- MotionTransformer: Transferring Neural Inertial Tracking between Domains, AAAI 2019 [paper] [my repo] (1)
2020 Sep
- Enabling Identity-Aware Tracking via Fusion of Visual and Inertial Features, ICRA 2019 [paper] [my repo] (1)
- Person Re-ID by Fusion of Video Silhouettes and Wearable Signals for Home Monitoring Applications, Sensors 2020 [paper] [my repo] (1)
- A Survey of Human-Sensing: Methods for Detecting Presence, Count, Location, Track, and Identity, CS 2010 [paper] [my repo] (1)
- Automatic Synchronization of Markerless Video and Wearable Sensors for Walking Assessment, Sensors 2019 [paper] [my repo] (1)
- Tasking Networked CCTV Cameras and Mobile Phones to Identify and Localize Multiple People, UbiComp 2010
C3M3E3L3
(Vis, IMU, Multi-modal) [paper] [my repo] - Tagging Wearable Accelerometers in Camera Frames through Information Translation between Vision Sensors and Accelerometers, ICCPS 2019 [paper] [my repo] (2)
2020 Jul
Self-Supervised Learning
- Self-Supervised Dueling Networks for Deep Reinforcement Learning, NIPS 2016 [paper] [my repo] (1)
- Self-supervised Visual Feature Learning with Deep Neural Networks: A Survey, TPAMI 2020 [paper] [my repo] (1)
- CURL: Contrastive Unsupervised Representations for Reinforcement Learning, ICML 2020 [paper] [code] [my repo] (1)
- Unsupervised Domain Adaptation through Self-Supervision - REJECT, ICLR 2020 [paper] [forum] [my repo] (1)
- S4L: Self-Supervised Semi-Supervised Learning, ICCV 2019 [paper ICCV] [paper arxiv] [my repo] (1)
- Self-Supervised Representation Learning, Lil'Log 2019 [blog] (1)
- Prioritized Experience Replay, ICLR 2016 [paper] [my repo] (1)
- End-to-End Robotic Reinforcement Learning without Reward Engineering, RSS 2019 [paper] [my repo] (1)
- Meta-Sim: Learning to Generate Synthetic Datasets, ICCV 2019 [paper ICCV] [paper arxiv] [blog] [code] [my repo] (1)
- SIM2Real Transfer [slide] (1)
- VR-Goggles for Robots: Real-to-sim Domain Adaptation for Visual Control [paper] [my repo] (1)
- CycleGAN for sim2real Domain Adaptation [paper] [video] [my repo] (1)
- Learning to Simulate, ICLR 2019 [paper] [forum] [my repo] (1)
- Policy Transfer With Strategy Optimization, ICLR 2019 [paper] [forum] [my repo] (2)
- Domain Randomization for Sim2Real Transfer [blog] (1)
- RL-CycleGAN: Reinforcement Learning Aware Simulation-To-Real, CVPR 2020 [paper CVPR] [paper arxiv] [my repo] (1)
- ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation, CVPR 2019 [paper] [video] [code] [my repo] (1)
- Unsupervised Intra-domain Adaptation for Semantic Segmentation through Self-Supervision, CVPR 2020
C3M4E1L2
[paper] [blog] [video] [code] [my repo] (3) - A Visual Guide to Evolution Strategies 2019 [blog] (2)
2020 May
Graph Neural Network
- GCAN: Graph Convolutional Adversarial Network for Unsupervised Domain Adaptation, CVPR 2019 [paper] [my repo] (1)
- Symmetric Graph Convolutional Autoencoder for Unsupervised Graph Representation Learning, ICCV 2019 [paper] [my repo] (1)
- Semantic Graph Convolutional Networks for 3D Human Pose Regression, CVPR 2019 [paper] [my repo] (1)
- A Convex Relaxation for Multi-Graph Matching, CVPR 2019 [paper] [my repo] (1)
- Edge-Labeling Graph Neural Network for Few-shot Learning, CVPR 2019 [paper] [my repo] (1)
2020 Apr
Neural Architecture Search
- Neural Architecture Search with Reinforcement Learning, ICLR 2017 [paper] [my repo] (1)
- DARTS: Differentiable Architecture Search, ICLR 2019 [paper] [my repo] (2)
- EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks, ICML 2019 [paper] [my repo] (1)
- Exploring Randomly Wired Neural Networks for Image Recognition, ICCV 2019 [paper] [my repo] (1)
- AssembleNet: Searching for Multi-Stream Neural Connectivity in Video Architectures, ICLR 2020 [paper] [my repo] (2)
Flow Models
- Glow: Generative Flow with Invertible 1×1 Convolutions, NeurIPS 2018 [paper] [my repo] (1)
- C-Flow: Conditional Generative Flow Models for Images and 3D Point Clouds, CVPR 2020 [paper] [my repo] (1)
- Implicit Generation and Modeling with Energy-Based Models, NeurIPS 2019 [paper] [my repo] (1)
- Your Classifier Is Secretly an Energy Based Model and You Should Treat It Like One, ICLR 2020 [paper] [my repo] (1)
- Do Deep Generative Models Know What They Don't Know?, ICLR 2019 [paper] [my repo] (1)
Optimal Transport
- Wasserstein GAN, ICML 2017 [paper] [my repo] (1)
- Improved Training of Wasserstein GANs, NeurIPS 2018 [paper] [my repo] (1)
- Spectral Normalization for Generative Adversarial Networks, ICLR 2018 [paper] [my repo] (1)
Visual SLAM
- ORB-SLAM: a Versatile and Accurate Monocular SLAM System, T-RO 2015 [paper] [my repo] (1)
- DTAM: Dense Tracking and Mapping in Real-Time, ICCV 2011 [paper] [my repo] (1)
- Learning Meshes for Dense Visual SLAM, ICCV 2019 [paper] [my repo] (1)
Scene Text Recognition
- Convolutional Character Networks, ICCV 2019 [paper] [my repo] (1)
- ABCNet: Real-time Scene Text Spotting with Adaptive Bezier-Curve Network, CVPR 2020 [paper] [my repo] (1)
- Real-time Scene Text Detection with Differentiable Binarization, AAAI 2020 [paper] [my repo] (1)
- TextField: Learning A Deep Direction Field for Irregular Scene Text Detection, TIP 2019 [paper] [my repo] (1)
2020 Mar
Self-Supervised Learning
- Unsupervised Visual Representation Learning by Context Prediction, ICCV 2015 [paper] [my repo] (1)
- Context Encoders: Feature Learning by Inpainting, CVPR 2016 [paper] [my repo] (1)
- Shuffle and Learn: Unsupervised Learning using Temporal Order Verification, ECCV 2016 [paper] [my repo] (1)
- Learning and Using the Arrow of Time, CVPR 2018 [paper] [my repo] (1)
- Grasp2Vec: Learning Object Representations from Self-Supervised Grasping, CoRL 2018 [paper] [my repo] (1)
- Evolving Losses for Unsupervised Video Representation Learning, CVPR 2020 [paper] [my repo] (1)
2020 Feb
Cloud Counting
- Leveraging Unlabeled Data for Crowd Counting by Learning to Rank, CVPR 2018 [paper] [my repo] (1)
- Bayesian Loss for Crowd Count Estimation with Point Supervision, ICCV 2019 [paper] [my repo] (1)
Video Representation
- Temporal Gaussian Mixture Layer for Videos, ICML 2019 [paper] [slide] [code] [my repo] (1)
- Videos as Space-Time Region Graphs, ECCV 2018 [paper] [my repo] (1)
- Non-local Neural Networks, CVPR 2018 [paper] [code] [my repo] (1)
- End-to-end Learning of Action Detection from Frame Glimpses in Videos, CVPR 2016
C2M2E1L1
[paper] [blog] [code] [my repo] - Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset, CVPR 2017 [paper] [my repo] (1)
Tracking
- Cross-Classification Clustering: An Efficient Multi-Object Tracking Technique for 3-D Instance Segmentation in Connectomics, CVPR 2019 [paper] [my repo] (1)
- Physical Adversarial Textures That Fool Visual Object Tracking, ICCV 2019 [paper] [my repo] (1)
- Efficient Online Multi-Person 2D Pose Tracking with Recurrent Spatio-Temporal Affinity Fields, CVPR 2019 [paper] [my repo] (1)
- Learning Aberrance Repressed Correlation Filters for Real-Time UAV Tracking, ICCV 2019 [paper] [code] [my repo] (1)
- Learning Discriminative Model Prediction for Tracking, ICCV 2019 [paper] [code] [my repo] (1)
Generative Models
- SinGAN: Learning a Generative Model from a Single Natural Image, ICCV 2019 [paper] [code] [my repo] (1)
- A Style-Based Generator Architecture for Generative Adversarial Networks, CVPR 2019 [paper] [code] [my repo] (1)
- Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks, CVPR 2017 [paper] [blog] [code] [my repo] (1)
- Generating Diverse High-Fidelity Images with VQ-VAE-2, NeurIPS 2019 [paper] [my repo] (1)
- Autoencoding Beyond Pixels using a Learned Similarity Metric, ICML 2016 [paper] [my repo] (1)
- Auto-Encoding Variational Bayes, ICLR 2014 [paper] [video] [my repo] (1)
- Contextual Imagined Goals for Self-Supervised Robotic Learning, CoRL 2019 [paper] [blog] [video] [code] [my repo] (1)
- HRL4IN: Hierarchical Reinforcement Learning for Interactive Navigation with Mobile Manipulators, CoRL 2019 [paper] [blog] [code] [my repo] (1)
- Relay Policy Learning: Solving Long-Horizon Tasks via Imitation and Reinforcement Learning, CoRL 2019 [paper] [blog] [my repo] (1)
- Learning Navigation Subroutines from Egocentric Videos, CoRL 2019 [paper] [blog] [video] [my repo] (1)
- ROBEL: Robotics Benchmarks for Learning with Low-Cost Robots, CoRL 2019 [paper] [blog] [my repo] (1)
- RoboNet: Large-Scale Multi-Robot Learning, CoRL 2019 [paper] [blog] [video] [code] [my repo] (1)
- Adversarial Active Exploration for Inverse Dynamics Model Learning, CoRL 2019 [paper] [my repo] (1)
- Learning Locomotion Skills for Cassie: Iterative Design and Sim-to-Real, CoRL 2019 [paper] [my repo] (1)
- Learning Latent Plans from Play, CoRL 2019 [paper] [blog] [video] [my repo] (1)
- To Follow or not to Follow: Selective Imitation Learning from Observations, CoRL 2019 [paper] [blog] [video] [my repo] (1)
- Active Domain Randomization, CoRL 2019 [paper] [code] [my repo] (1)
- TuneNet: One-Shot Residual Tuning for System Identification and Sim-to-Real Robot Task Transfer, CoRL 2019 [paper] [video] [code] [my repo] (1)
- A Survey on Reproducibility by Evaluating Deep Reinforcement Learning Algorithms on Real-World Robots, CoRL 2019 [paper] [code] [my repo] (1)
- Asynchronous Methods for Model-Based Reinforcement Learning, CoRL 2019 [paper] [my repo] (1)
- Learning to Manipulate Object Collections Using Grounded State Representations, CoRL 2019 [paper] [blog] [code] [video0] [video1] [my repo] (1)
- Multi-Frame GAN: Image Enhancement for Stereo Visual Odometry in Low Light, CoRL 2019 [paper] [my repo] (1)
- Not All Areas Are Equal: Transfer Learning for Semantic Segmentation via Hierarchical Region Selection, CVPR 2019 [paper] [my repo] (1)
- CRAVES: Controlling Robotic Arm with a Vision-based Economic System, CVPR 2019 [paper] [my repo] (1)
- Pyramid Feature Attention Network for Saliency detection, CVPR 2019 [paper] [my repo] (1)
- Universal Domain Adaptation, CVPR 2019 [paper] [code] [my repo] (1)
- Bidirectional Learning for Domain Adaptation of Semantic Segmentation, CVPR 2019 [paper] [code] [my repo] (1)
- Representation Similarity Analysis for Efficient Task taxonomy & Transfer Learning, CVPR 2019 [paper] [code] [my repo] (1)
- Scene Memory Transformer for Embodied Agents in Long-Horizon Tasks, CVPR 2019 [paper] [video] [my repo] (1)
- Gaussian Temporal Awareness Networks for Action Localization, CVPR 2019 [paper] [my repo] (1)
- Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation, CVPR 2019 [paper] [code] [my repo] (1)
2020 Jan
- Temporal Cycle-Consistency Learning, CVPR 2019 [paper] [my repo] (1)
- Actor-Critic Instance Segmentation, CVPR 2019 [paper] [code] [my repo] (1)
- Vision-based Navigation with Language-based Assistance via Imitation Learning with Indirect Intervention, CVPR 2019 [paper] [code] [video] [my repo] (1)
- Tactical Rewind: Self-Correction via Backtracking in Vision-and-Language Navigation [paper] [my repo] (1)
- The Regretful Agent: Heuristic-Aided Navigation through Progress Estimation [paper] [code] [my repo] (1)
- Learning to Learn How to Learn: Self-Adaptive Visual Navigation using Meta-Learning [paper] [code] [my repo] (1)
- Learning to Navigate Using Mid-Level Visual Priors [paper] [code] [my repo] (1)
- Are We Making Real Progress in Simulated Environments? Measuring the Sim2Real Gap in Embodied Visual Navigation [paper] [my repo] (1)
- DD-PPO: Learning Near-Perfect PointGoal Navigators From 2.5 Billion Frames [paper] [blog] [my repo] (1)
- Continuous Control with Deep Reinforcement Learning [paper] [blog0] [blog1] [code] [my repo] (1)