Research map / Video / Action recognition
T-C3D: Temporal Convolutional 3D Network for Real-Time Action Recognition
Read the paperCheck 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 |
|---|---|---|---|
| consecutive instead of non-consecutive frame sampling (ablation) | T-C3D · UCF101 split1 | accuracy: 89.2 -> 89.5 | Helped |
| attention pooling instead of max pooling aggregation (ablation) | T-C3D · UCF101 split1 | accuracy: 88.1 -> 89.5 | Helped |
| attention pooling instead of average pooling (ablation) | T-C3D · UCF101 split1 | accuracy: 89.4 -> 89.5 | No clear effect |
| pretrain on Kinetics vs training from scratch (ablation) | T-C3D · UCF101 split1 | accuracy: 68.3 -> 92.5 | Helped |
| pretrain on clean Kinetics instead of noisy Sports-1M (ablation) | T-C3D · UCF101 split1 | accuracy: 89.5 -> 92.5 | Helped |
| increase number of clips (temporal encoding) beyond 1 (ablation) | T-C3D · UCF101 split1 | accuracy | Helped |
| multi-scale testing on all clips (ablation) | T-C3D · UCF101 split1 | accuracy: 92.5 -> 92.8 | Helped |
| multi-scale testing on all clips (ablation) | T-C3D · UCF101 split1 | FPS: 220 -> 45 | Hurt |
Closest papers by meaning
- Deep Analysis of CNN-Based Spatio-Temporal Representations for Action Recognition (CVPR 2021 · similarity 0.93)
- Temporal Convolutional Networks for Action Segmentation and Detection (CVPR 2017 · similarity 0.91)
- Temporal Pyramid Network for Action Recognition (CVPR 2020 · similarity 0.91)
- MiCT: Mixed 3D/2D Convolutional Tube for Human Action Recognition (CVPR 2018 · similarity 0.91)
- PA3D: Pose-Action 3D Machine for Video Recognition (CVPR 2019 · similarity 0.90)
- MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation (CVPR 2019 · similarity 0.90)
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.