Research map / Video / Video segmentation and tracking
Deep Learning in Latent Space for Video Prediction and Compression
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 latent-space prediction and compression for anomaly detection | Video prediction and compression framework · UCSD Ped1 | AUC (%): 89.9 -> 90.9 | Helped |
| Use latent-space prediction and compression for anomaly detection | Video prediction and compression framework · UCSD Ped2 | AUC (%): 95.4 -> 93.6 | Hurt |
| Use latent-space prediction and compression for anomaly detection | Video prediction and compression framework · Subway Entrance | AUC (%): 94.3 -> 88.2 | Hurt |
| Use latent-space prediction and compression for anomaly detection | Video prediction and compression framework · Subway Exit | AUC (%): 94.0 -> 94.5 | Helped |
| Use latent-space prediction and compression for anomaly detection | Video prediction and compression framework · CUHK Avenue | AUC (%): 84.9 -> 85.4 | Helped |
| Add discriminator loss during prediction-network training (ablation) | Latent-space video prediction network · Video compression | PSNR | No clear effect |
| Add discriminator loss during prediction-network training (ablation) | Latent-space video prediction network · Video compression | Subjective reconstruction quality | Helped |
Closest papers by meaning
- Deep Hierarchical Video Compression (AAAI 2024 · similarity 0.87)
- Video Compression With Entropy-Constrained Neural Representations (CVPR 2023 · similarity 0.86)
- Decomposing Motion and Content for Natural Video Sequence Prediction (ICLR 2017 · similarity 0.86)
- Predicting Future Frames Using Retrospective Cycle GAN (CVPR 2019 · similarity 0.86)
- Improved Video VAE for Latent Video Diffusion Model (CVPR 2025 · similarity 0.85)
- CV-VAE: A Compatible Video VAE for Latent Generative Video Models (NeurIPS 2024 · similarity 0.84)
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.