AI Paper Atlas

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

Multi-Task Zero-Shot Action Recognition with Prioritised Data Augmentation

Xun Xu, Timothy M. Hospedales, Shaogang Gong

ECCV 2016 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Generative feature synthesis for zero-shot · 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
replace single-task ridge regression with multi-task embedding (MTE, latent matching)zero-shot action recognition · HMDB51accuracy: 18.3 -> 19.7Improved
replace single-task ridge regression with multi-task embedding (MTE, latent matching)zero-shot action recognition · UCF101accuracy: 14.5 -> 15.8Improved
replace single-task ridge regression with multi-task embedding (MTE, latent matching)zero-shot action recognition · Olympic Sportsaverage precision: 40.9 -> 44.3Improved
add latent-space matching (ablation)MTE · UCF101accuracy: 14.2 -> 15.8Improved
add latent-space matching (ablation)MTE · HMDB51accuracy: 18.7 -> 19.7Improved
add latent-space matching (ablation)MTE · Olympic Sportsaverage precision: 44.5 -> 44.3No clear effect
add naive data augmentation from other datasetsRR · HMDB51 (zero-shot, 5 splits)accuracy: 18.3 -> 21.9Improved
add naive data augmentation from other datasetsMTE · UCF101 (zero-shot, 5 splits)accuracy: 15.8 -> 20.9Improved
add category KLIEP weighting instead of naive DA (ablation)RR · Olympic Sports (zero-shot, 5 splits)average precision: 46.5 -> 51.8Improved
add full KLIEP weighting instead of naive DA (ablation)MTE · UCF101 (zero-shot, 5 splits)accuracy: 20.9 -> 21.9Improved
add full KLIEP weighting instead of naive DA (ablation)MTE · Olympic Sports (zero-shot, 5 splits)average precision: 49.4 -> 52.3Improved
add full KLIEP on top of visual or category weighting alone (ablation)MTE · HMDB51 (zero-shot, 5 splits)accuracy: 23.4 -> 23.9No 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