Pith. sign in

REVIEW 1 cited by

Dancing with Still Images: Video Distillation via Static-Dynamic Disentanglement

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2312.00362 v2 pith:G75UOVZZ submitted 2023-12-01 cs.CV cs.LG

classification cs.CVcs.LG
keywords distillationtemporalvideodynamicinformationmemoryvideosdatasets
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Recently, dataset distillation has paved the way towards efficient machine learning, especially for image datasets. However, the distillation for videos, characterized by an exclusive temporal dimension, remains an underexplored domain. In this work, we provide the first systematic study of video distillation and introduce a taxonomy to categorize temporal compression. Our investigation reveals that the temporal information is usually not well learned during distillation, and the temporal dimension of synthetic data contributes little. The observations motivate our unified framework of disentangling the dynamic and static information in the videos. It first distills the videos into still images as static memory and then compensates the dynamic and motion information with a learnable dynamic memory block. Our method achieves state-of-the-art on video datasets at different scales, with a notably smaller memory storage budget. Our code is available at https://github.com/yuz1wan/video_distillation.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. CONCORD: Concept-Informed Diffusion for Dataset Distillation

    cs.CV 2025-05 conditional novelty 6.0 of 10

    A training-free concept-informed diffusion method, using LLM-retrieved and CLIP-filtered visual descriptions, improves dataset distillation accuracy on ImageNet subsets and ImageNet-1K.

Pith tools