We lifted 1 functions out of this paper's own repositories and ran 1 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| yuz1wan/video_distillation | canonical | 1 of 1 |
| Function | Status | Where it lives |
|---|---|---|
| distance_wb | Ran | yuz1wan/video_distillation/utils.py pointer only (licence: NONE) · get_code("50da380b9332efe9") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
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.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2312.00362")
get_code_for_paper("2312.00362")
have("2312.00362")
Connect an agent — have() is free.