AI Paper Atlas

Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning

Transductive Zero-Shot Action Recognition by Word-Vector Embedding

Xun Xu, Timothy M. Hospedales, Shaogang Gong

IJCV 2017 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Generative feature synthesis for zero-shot · 154 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 from auxiliary datasets (ablation)RR + NN · HMDB51accuracy (%): 14.5 -> 20.4Improved
add data augmentation from auxiliary datasets (ablation)RR + NN · UCF101accuracy (%): 11.7 -> 15.7Improved
add data augmentation from auxiliary datasets (ablation)RR + NN · CCVmAP (%): 20.7 -> 30.3Improved
add data augmentation from auxiliary datasets (ablation)RR + NN · USAAaccuracy (%): 29.5 -> 28.2Hurt
replace ridge regression with manifold regularized regression (with self-training) (ablation)NN matching · HMDB51accuracy (%): 17.0 -> 18.6Improved
replace ridge regression with manifold regularized regression (with self-training) (ablation)NN matching · UCF101accuracy (%): 15.9 -> 17.6Improved
add self-training of class prototypes (ablation)RR + NN · UCF101accuracy (%): 11.7 -> 15.9Improved
add normalised nearest neighbour hubness correction (ablation)RR · UCF101accuracy (%): 11.7 -> 13.9Improved
use NRM or GC instead of NN matching (ablation)mAP datasets · Olympic Sports and CCVmAP (%)No clear effect
add self-training and manifold regularization (ablation)RR + NN · TRECVID MED 2013mAP (%): 1.18 -> 1.38Improved
add self-training to SJE (ablation)SJE · HMDB51accuracy (%): 12.0 -> 10.5Hurt
add self-training to ConSE (ablation)ConSE · HMDB51accuracy (%): 15.0 -> 15.4Improved

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