AI&CV paper notes

Paper classification coding:

• N: new papers, C: classic/highly cited papers, T: tutorial, B: baseline/benchmark, S: summary/list of papers in a field
• F: face modeling, P: pose estimation, V, general computer vision, G: general deep learning/representation learning/machine learning, R: 3D recon

2020-06

• CVPR 2020

2020-05

• [NR]Occupancy Networks: Learning 3D Reconstruction in Function Space - CVPR'19
• [NR]Implicit Functions in Feature Space for 3D Shape Reconstruction and Completion - CVPR'20
• [NP]15 Keypoints Is All You Need - CVPR'20

2020-04

• [CV]Cost-Effective Active Learning for Deep Image Classification
• [NP]VIBE: Video Inference for Human Body Pose and Shape Estimation
• [NP]Combining Detection and Tracking for Human Pose Estimation in Videos

2020-03

• [NP]Sim2real transfer learning for 3D human pose estimation: motion to the rescue - NIPS'19
• [NR]Multi-Garment Net: Learning to Dress 3D People from Images
• [NV]Momentum Contrast for Unsupervised Visual Representation Learning
• [NV]Efficientnet: Rethinking model scaling for convolutional neural networks
• [NV]Self-Training With Noisy Student Improves ImageNet Classification - CVPR'20
• [CV]MobileNetV2: Inverted Residuals and Linear Bottlenecks
  • [T]link
• [CV]Revisiting Unreasonable Effectiveness of Data in Deep Learning Era

2020-02

• [NP]HoloPose: Holistic 3D Human Reconstruction In-The-Wild
• [CP]Monocular 3d pose and shape estimation of multiple people in natural scenes-the importance of multiple scene constraints, CVPR'18
• [CP]Flowing ConvNets for Human Pose Estimation in Videos
• [S]Awesome Human Pose Estimation

2020-01

• [NP]On Boosting Single-Frame 3D Human Pose Estimation via Monocular Videos
• [NP]Optimizing Network Structure for 3D Human Pose Estimation
• [NP]Monocular 3D Human Pose Estimation by Generation and Ordinal Ranking

2019-12

• [NP]Learnable Triangulation of Human Pose, ICCV'19
• [CP]Simple Baselines for Human Pose Estimation and Tracking, ECCV'18

2019-11

• [NP]Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loop, ICCV'19
• [NV]Convolutional Sequence Generation for Skeleton-Based Action Synthesis, ICCV'19

2019-10

• [NP]Multi-person Articulated Tracking with Spatial and Temporal Embeddings
• [NP]Efficient Online Multi-Person 2D Pose Tracking with Recurrent Spatio-Temporal Affinity Fields
• [B]Person ReID baseline
• [NV]Spatial-Temporal Person Re-identification

2019-09

• [NP]Bottom-up Higher-Resolution Networks for Multi-Person Pose Estimation [code to-be-released]
• [NF]Face-to-Parameter Translation for Game Character Auto-Creation - ICCV'19
• [NP]Learning Temporal Pose Estimation from Sparsely-Labeled Videos - NIPS'19

2019-08

• [NP]Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Image

2019-07

• [CV]Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition

2019-06

• [NP]Action-Agnostic Human Pose Forecasting - WACV'19
• [NP]Learning 3D Human Dynamics from Video - CVPR'19

2019-05

• [CV]Deep image prior - CVPR'18
• [NP]LightTrack: A Generic Framework for Online Top-Down Human Pose Tracking - SOTA on pose tracking on PoseTrack2017

2019-04

• [CF]Face Alignment Across Large Poses: A 3D Solution - CVPR'16
• [CF]How Far Are We From Solving the 2D & 3D Face Alignment Problem? - ICCV'17

2019-03

• [NP]Deep High-Resolution Representation Learning for Human Pose Estimation - CVPR'19
• [NP]End-to-end Recovery of Human Shape and Pose - CVPR'18
• [NP]Exploiting temporal information for 3D human pose estimation - ECCV'18

2019-02

• [NP]3D human pose estimation in video with temporal convolutions and semi-supervised training - CVPR'19
• [NF]Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network - ECCV'18

2019-01

2018 and before