Research map / Video / Action recognition
NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use P-LSTM part-based memory cells instead of standard LSTM memory | LSTM · NTU RGB+D cross-subject | accuracy: 60.69% -> 62.93% | Helped |
| use P-LSTM part-based memory cells instead of standard LSTM memory | LSTM · NTU RGB+D cross-view | accuracy: 67.29% -> 70.27% | Helped |
| add a second recurrent layer | RNN · NTU RGB+D cross-subject | accuracy: 56.02% -> 56.29% | Helped |
| add a second recurrent layer | RNN · NTU RGB+D cross-view | accuracy: 60.24% -> 64.09% | Helped |
| add a second recurrent layer | LSTM · NTU RGB+D cross-subject | accuracy: 59.14% -> 60.69% | Helped |
| add a second recurrent layer | LSTM · NTU RGB+D cross-view | accuracy: 66.81% -> 67.29% | Helped |
| add a second recurrent layer (ablation) | P-LSTM · NTU RGB+D cross-subject | accuracy: 62.05% -> 62.93% | Helped |
| add a second recurrent layer (ablation) | P-LSTM · NTU RGB+D cross-view | accuracy: 69.40% -> 70.27% | Helped |
| use 2 Layer P-LSTM instead of FTP Dynamic Skeletons | NTU RGB+D action recognition · NTU RGB+D cross-subject | accuracy: 60.23% -> 62.93% | Helped |
| use 2 Layer P-LSTM instead of FTP Dynamic Skeletons | NTU RGB+D action recognition · NTU RGB+D cross-view | accuracy: 65.22% -> 70.27% | Helped |
Closest papers by meaning
- Deep Analysis of CNN-Based Spatio-Temporal Representations for Action Recognition (CVPR 2021 · similarity 0.87)
- UCF-STAR: A Large Scale Still Image Dataset for Understanding Human Actions (AAAI 2020 · similarity 0.87)
- Scene Flow to Action Map: A New Representation for RGB-D Based Action Recognition With Convolutional Neural Networks (CVPR 2017 · similarity 0.87)
- InfoGCN: Representation Learning for Human Skeleton-Based Action Recognition (CVPR 2022 · similarity 0.87)
- T-C3D: Temporal Convolutional 3D Network for Real-Time Action Recognition (AAAI 2018 · similarity 0.87)
- HARDVS: Revisiting Human Activity Recognition with Dynamic Vision Sensors (AAAI 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.