Figure - available via license: Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International
Content may be subject to copyright.
Download
View publication
Video prediction results on KTH (64 × 64), predicting 30 and 40 frames using models trained to predict k frames at a time. All models condition on 10 past frames on 256 test videos.

Video prediction results on KTH (64 × 64), predicting 30 and 40 frames using models trained to predict k frames at a time. All models condition on 10 past frames on 256 test videos.

Source publication
Figure 1: Fig. (a) represents a naive adaptation of the diffusion model...
Figure 5: Figure represents qualitative results of our CVF model on the...
Video prediction results on KTH (64 × 64), predicting 30 and 40 frames...
BAIR dataset evaluation. Video prediction results on BAIR (64 × 64)...
Comparison with baselines on number of parameters, sampling steps and...
Efficient Continuous Video Flow Model for Video Prediction
Preprint
Full-text available
  • Dec 2024
Multi-step prediction models, such as diffusion and rectified flow models, have emerged as state-of-the-art solutions for generation tasks. However, these models exhibit higher latency in sampling new frames compared to single-step methods. This latency issue becomes a significant bottleneck when adapting such methods for video prediction tasks, gi...
Cite
Download full-text

Contexts in source publication

Context 1
... choice aligns with prior methodologies and allows a fair comparison. The results of our evaluation are summarized in Table 1. ...
Context 2
... Table 1, it is evident that our model achieves superior performance while requiring fewer training frames. Unlike other approaches that rely on a larger number of frames for both context and future predictions (e.g., 10 context frames plus k future frames), our model operates effectively with just 4 context frames and 1 future frame. ...
Context 3
... best results under each metric are marked in bold. The results, as presented in Table 1, confirm that our method delivers state-of-the-art performance relative to baseline models. Qualitative results of our CVF model on the KTH dataset are shown in Fig. 4. ...

Similar publications

HSLC
Flowchart of the proposed method (HSLC)
Illustrating intra-class and inter-class discriminative structure...
Parameter sensitivity analysis for α\documentclass[12pt]{minimal}...
+3 Parameter sensitivity analysis for β\documentclass[12pt]{minimal}...
Hybrid structure with label consistency for unsupervised domain adaptation
Article
Full-text available
  • Mar 2025
Unsupervised domain adaptation (UDA) is a technique for learning from a label-rich source domain and transferring the learned knowledge to an unlabeled target domain. Current researches on feature-based UDA methods usually utilize the pseudo labels to find new feature representations that can minimize the distribution difference between the two dom...
View