AI Paper Atlas

Research map / Video / Action recognition

Sympathy for the Details: Dense Trajectories and Hybrid Classification Architectures for Action Recognition

César Roberto de Souza, Adrien Gaidon, Eleonora Vig, Antonio Manuel López

ECCV 2016 · Video › Action recognition · approach: Disentangled action recognition · 47 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 data augmentation by feature stacking (DAFS) (ablation)iDT+STA+MIFS+DN · UCF-101mean accuracy (%): 89.2 -> 90.6Improved
add data augmentation by feature stacking (DAFS) (ablation)iDT+STA+MIFS+DN · HMDB-51mean accuracy (%): 65.4 -> 67.8Improved
add double normalization (ablation)iDT · HMDB-51mean accuracy (%): 57.0 -> 59.1Improved
add spatio-temporal augmentation (STA) (ablation)iDT · HMDB-51mean accuracy (%): 57.0 -> 60.3Improved
add fine-tuned C and Gaussian kernel to SVM (ablation)FV-SVM · five datasetsaccuracyNo clear effect
add a supervised deep network after unsupervised PCA reduction (depth 1)best FV-SVM · five datasets (average)relative improvement: 1.28%Improved
use two layers of width 4096 batch 128 after PCA (ablation)best FV-SVM · five datasets (average)relative improvement: 2.46%Improved
learn dimensionality reduction layer supervised instead of PCA (ablation)hybrid depth 1 · UCF-101mean accuracy (%): 91.9 -> 92.3Improved
learn dimensionality reduction layer supervised instead of PCA (ablation)hybrid depth 1 · Hollywood2mAP (%): 73.0 -> 72.5Hurt
transfer PCA weights from UCF-101 (ablation)hybrid · High-FivemAP+ (%): 73.1 -> 76.3Improved
transfer PCA weights from UCF-101 (ablation)hybrid · HMDB-51mean accuracy (%): 68.0 -> 66.5Hurt
transfer GMMs from UCF-101 (ablation)hybrid · Hollywood2mAP (%): 72.6 -> 72.4No clear effect

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