Research map / Video / Video segmentation and tracking
Video Prediction via Selective Sampling
Jingwei Xu, Bingbing Ni, Xiaokang Yang
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 |
|---|---|---|---|
| increase K (candidates fused) from 1 to 2 at N=4 (ablation) | VPSS · Human3.6M | PSNR: 24.96 -> 25.21 | Improved |
| increase N (proposals) from 3 to 5 at K=2 (ablation) | VPSS · Human3.6M | Inception Score: 1.95 -> 2.01 | Improved |
| increase N from 4 to 5 at K=2 (ablation) | VPSS · Human3.6M | PSNR: 25.21 -> 25.13 | Hurt |
| add selector module (remove selector, K=N) (ablation) | VPSS · Human3.6M | PSNR | Improved |
| add combiner module (remove combiner, K=1) (ablation) | VPSS · Human3.6M | PSNR | Improved |
| increase adversarial loss weight lambda in lambda*L_Adv + L_Reg | MCNet, DrNet, SAVP · video prediction training | L_Reg after 50K iterations: 0.04/0.05/0.07 (MCNet) | Hurt |
Closest papers by meaning
- High Fidelity Video Prediction with Large Stochastic Recurrent Neural Networks (NeurIPS 2019 · similarity 0.85)
- Structure Preserving Video Prediction (CVPR 2018 · similarity 0.85)
- Predicting Future Frames Using Retrospective Cycle GAN (CVPR 2019 · similarity 0.85)
- Flexible Spatio-Temporal Networks for Video Prediction (CVPR 2017 · similarity 0.85)
- Dual Motion GAN for Future-Flow Embedded Video Prediction (ICCV 2017 · similarity 0.85)
- OSV: One Step is Enough for High-Quality Image to Video Generation (CVPR 2025 · similarity 0.83)
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.
