Lifting from the Deep: Convolutional 3D Pose Estimation from a Single Image(CVPR2017)
[project]
A simple yet effective baseline for 3d human pose estimation(ICCV2017)
Julieta Martinez, Rayat Hossain, Javier Romero, James J. Little
[paper]
Learning body-affordances to simplify action spaces
Nicholas Guttenberg, Martin Biehl, Ryota Kanai
[paper]
[code]
Extreme Low Resolution Activity Recognition with Multi-Siamese Embedding Learning
Michael S. Ryoo, Kiyoon Kim, Hyun Jong Yang
[paper]
Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Pose
[project]
Detecting and Recognizing Human-Object Interactions
Georgia Gkioxari, Ross Girshick, Piotr Dollár, Kaiming He
[paper]
Realtime_Multi-Person_Pose_Estimation
[code]
[qiita]
**動的な人物/物体認識技術 -Dense Trajectories- **
[slide]
Going Deeper into Action Recognition: A Survey
Samitha Herath, Mehrtash Harandi, Fatih Porikli
[paper]
A Large-Scale Video Benchmark for Human Activity Understanding
[link]
Automatic Action Annotation in Weakly Labeled Videos
Waqas Sultani, Mubarak Shah
paper]
Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition
Francisco Javier Ordóñez and Daniel Roggen
[paper]
Action Recognition using Visual Attention (Arxiv,2016,ICLR2016 under review)
hikhar Sharma, Ryan Kiros, Ruslan Salakhutdinov (University of Toronto)
[GitXiv]
Unsupervised Learning of Video Representations using LSTMs
[GitXiv]
Latent Hierarchical Model for Activity Recognition
[GitXiv]
Recurrent Neural Networks and Transfer Learning for Action Recognition
[GitXiv]
Efficient feature extraction, encoding and classification for action recognition
[GitXiv]