Papers › Training a Large Video Model on a Single Machine in a Day

Training a Large Video Model on a Single Machine in a Day

28 Sep 2023arXiv:2309.16669archive 2025-07-28

Yue Zhao, Philipp Krähenbühl

Videos are big, complex to pre-process, and slow to train on. State-of-the-art large-scale video models are trained on clusters of 32 or more GPUs for several days. As a consequence, academia largely ceded the training of large video models to industry. In this paper, we show how to still train a state-of-the-art video model on a single machine with eight consumer-grade GPUs in a day. We identify three bottlenecks, IO, CPU, and GPU computation, and optimize each. The result is a highly efficient video training pipeline. For comparable architectures, our pipeline achieves higher accuracies with 1/8 of the computation compared to prior work. Code is available at https://github.com/zhaoyue-zephyrus/AVION.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

zhaoyue-zephyrus/avion officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Action RecognitionMulti-Instance Retrieval

2 archive task tags without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Recognition EPIC-KITCHENS-100 Avion (ViT-L) Action@1 54.4 #3 of 32 Archive leaderboard report
Action Recognition EPIC-KITCHENS-100 Avion (ViT-L) Noun@1 65.4 #3 of 32 Archive leaderboard report
Action Recognition EPIC-KITCHENS-100 Avion (ViT-L) Verb@1 73.0 #3 of 32 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections