Research map / Video / Video segmentation and tracking
Dynamic Temporal Filtering In Video Models
Fuchen Long, Zhaofan Qiu, Yingwei Pan, Ting Yao, Chong-Wah Ngo, Tao Mei
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| replace temporal 1D convolution with dynamic 1D convolution per location (ablation) | DTF-Net (res5) · Kinetics-400 val (ablation, 16 frames) | top-1 accuracy: 73.2 -> 74.2 | Improved |
| move temporal modeling to frequency domain with a fixed filter (ablation) | DTF-Net (res5) · Kinetics-400 val (ablation, 16 frames) | top-1 accuracy: 74.2 -> 75.0 | Improved |
| make the frequency filter dynamic per spatial location (ablation) | DTF-Net (res5) · Kinetics-400 val (ablation, 16 frames) | top-1 accuracy: 75.0 -> 75.7 | Improved |
| add DTF block to 2D-ResNet at res5 (ablation) | ResNet-50 · Kinetics-400 val (ablation, 16 frames) | top-1 accuracy: 72.0 -> 75.7 | Improved |
| add frame-wise aggregation before FFT (ablation) | DTF-baseline · Kinetics-400 val (ablation, 16 frames) | top-1 accuracy: 74.9 -> 75.4 | Improved |
| add correlation feature to filter learning (ablation) | DTF-baseline · Kinetics-400 val (ablation, 16 frames) | top-1 accuracy: 74.9 -> 75.2 | Improved |
| combine frame-wise aggregation and correlation feature (ablation) | DTF-baseline · Kinetics-400 val (ablation, 16 frames) | top-1 accuracy: 74.9 -> 75.7 | Improved |
| insert DTF into res4 in addition to res5 (ablation) | DTF-Net ResNet-50 · Kinetics-400 val (ablation, 16 frames) | top-1 accuracy: 75.7 -> 76.5 | Improved |
| insert DTF into all four stages (ablation) | DTF-Net ResNet-50 · Kinetics-400 val (ablation, 16 frames) | top-1 accuracy: 76.5 -> 77.7 | Improved |
| use DTF instead of Temporal Difference for temporal modeling | ResNet-50 · Kinetics-400 val (ablation, 16 frames) | top-1 accuracy: 76.6 -> 77.7 | Improved |
| increase input clip length from 16 to 64 frames (ablation) | DTF-Net ResNet-50 · Kinetics-400 val | top-1 accuracy: 77.7 -> 80.9 | Improved |
| replace Video-Swin with DTF-Transformer (add DTF to Swin-B) | Swin-B · Kinetics-400 val | top-1 accuracy: 82.7 -> 83.5 | Improved |
Closest papers by meaning
- Temporal Residual Networks for Dynamic Scene Recognition (CVPR 2017 · similarity 0.86)
- DFDNet: Disentangling and Filtering Dynamics for Enhanced Video Prediction (AAAI 2025 · similarity 0.86)
- Exploring Spatial-Temporal Multi-Frequency Analysis for High-Fidelity and Temporal-Consistency Video Prediction (CVPR 2020 · similarity 0.86)
- Frequency Dynamic Convolution for Dense Image Prediction (CVPR 2025 · similarity 0.85)
- Wavelet-Driven Spatiotemporal Predictive Learning: Bridging Frequency and Time Variations (AAAI 2024 · similarity 0.85)
- FreeLong: Training-Free Long Video Generation with SpectralBlend Temporal Attention (NeurIPS 2024 · similarity 0.85)
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.
