AI Paper Atlas

Research map / Video / Action recognition

DynamoNet: Dynamic Action and Motion Network

Ali Diba, Vivek Sharma, Luc Van Gool, Rainer Stiefelhagen

ICCV 2019 · Video › Action recognition · approach: Spatiotemporal CNNs for action recognition · 114 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add frame prediction loss to train dynamic motion filters (ablation)DynamoNet · UCF101 (trained on UCF101)accuracy (%): 43.2 -> 50.2Improved
add dynamic motion filters with frame prediction to STC-ResNext101 (16 frames)STC-ResNext101 · Kinetics-400 valtop-1 accuracy (%): 66.2 -> 67.6Improved
add dynamic motion filters to 3D ResNext101 (16 frames)3D ResNext101 · Kinetics-400 valtop-1 accuracy (%): 65.1 -> 66.3Improved
increase input from 32 to 64 frames in DynamoNet (STCnet) (ablation)DynamoNet (STCnet) · Kinetics-400 valtop-1 accuracy (%): 69.9 -> 77.9Improved
add dynamic motion filters to STC-ResNext101 trained on half of KineticsSTC-ResNext101 · Kinetics-400 val (half training data)top-1 accuracy (%): 55.4 -> 63.6Improved
add dynamic motion filters to STC-ResNext101 trained on full KineticsSTC-ResNext101 · Kinetics-400 val (full training data)top-1 accuracy (%): 66.2 -> 67.6Improved
add self-supervised frame-prediction pre-training vs scratch STC-ResNet101STC-ResNet 101 · UCF101 (self-supervised pre-training, split-1)accuracy (%): 56.7 -> 88.1Improved
add self-supervised frame-prediction pre-training vs scratch STC-ResNet101STC-ResNet 101 · HMDB51 (self-supervised pre-training, split-1)accuracy (%): 30.8 -> 59.9Improved
add dynamic motion filters to STC-ResNext101 (UCF101, Kinetics pre-trained)STC-ResNext101 · UCF101 (Kinetics pre-trained, 3 splits)accuracy (%): 92.3 -> 96.6Improved
vary dynamic filter size away from 5x5 (3,4,6,7) (ablation)DynamoNet · action classificationclassification accuracy: drop of approx 2-3%Hurt
add motion filters to predict frames for next-frame prediction vs Mathieu et al.Mathieu et al. · UCF101 test videos (frame prediction)SSIM: 0.92 -> 0.95Improved

Later papers that compared with this method

1 later accepted paper reports DynamoNet (64) as a baseline in their results tables; 0 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy