AI Paper Atlas

Research map / Video / Action recognition

Prediction of Manipulation Actions

Cornelia M. Fermuller, Fang Wang, Yezhou Yang, Konstantinos Zampogiannis, Yi Zhang, Francisco Barranco, Michael Pfeiffer

IJCV 2017 · Video › Action recognition · approach: Action anticipation and latent actions · 51 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
use VGG16 CNN features instead of HOG features as LSTM input (ablation)LSTM action classifier · MAD action classificationaccuracy: 59.2% -> 68.3%Improved
use LSTM with VGG16 features instead of HMMaction classifier · MAD action classificationaccuracy: 53.7% -> 68.3%Improved
use LSTM with VGG16 features instead of SVMaction classifier · MAD action classificationaccuracy: 48.1% -> 68.3%Improved
add predicted finger forces to vision featuresaction prediction LSTM · MAD action prediction (average)accuracy: 68.3% -> 70.5%Improved
add predicted finger forces to vision featuresaction prediction LSTM · MAD stoneaccuracy: 61.4% -> 75.1%Improved
add predicted finger forces to vision featuresaction prediction LSTM · MAD cupaccuracy: 82.4% -> 88.2%Improved
add predicted finger forces to vision featuresaction prediction LSTM · MAD spongeaccuracy: 61.6% -> 59.1%Hurt
add predicted finger forces to vision featuresaction prediction LSTM · MAD spoonaccuracy: 62.6% -> 57.5%Hurt
add predicted finger forces to vision featuresaction prediction LSTM · MAD knifeaccuracy: 73.3% -> 72.7%No clear effect
let human observers see more frames after contact (10 to 25 frames)human action prediction · MAD sponge human studyaccuracy: about 75% -> above 95% for four of five actionsImproved
give human observers feedback on correct actionhuman action prediction · MAD human study, spoon at 10 frames after contactaccuracyImproved

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