Papers › DistInit: Learning Video Representations Without a Single Labeled Video

DistInit: Learning Video Representations Without a Single Labeled Video

26 Jan 2019ICCV 2019 10arXiv:1901.09244archive 2025-07-28

Rohit Girdhar, Du Tran, Lorenzo Torresani, Deva Ramanan

Video recognition models have progressed significantly over the past few years, evolving from shallow classifiers trained on hand-crafted features to deep spatiotemporal networks. However, labeled video data required to train such models have not been able to keep up with the ever-increasing depth and sophistication of these networks. In this work, we propose an alternative approach to learning video representations that require no semantically labeled videos and instead leverages the years of effort in collecting and labeling large and clean still-image datasets. We do so by using state-of-the-art models pre-trained on image datasets as "teachers" to train video models in a distillation framework. We demonstrate that our method learns truly spatiotemporal features, despite being trained only using supervision from still-image networks. Moreover, it learns good representations across different input modalities, using completely uncurated raw video data sources and with different 2D teacher models. Our method obtains strong transfer performance, outperforming standard techniques for bootstrapping video architectures with image-based models by 16%. We believe that our approach opens up new approaches for learning spatiotemporal representations from unlabeled video data.

PaperPDFConference PDF

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

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

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

Tasks

Action RecognitionTemporal Action LocalizationVideo Recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Action Recognition HMDB-51 R(2+1)D-18 (DistInit pretraining) Average accuracy of 3 splits 54.8 #72 of 77 Archive leaderboard report
Action Recognition UCF101 R(2+1)D-18 (DistInit pretraining) 3-fold Accuracy 85.8 #78 of 91 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