AI Paper Atlas

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

Rethinking Zero-Shot Action Recognition: Learning from Latent Atomic Actions

Yijun Qian, Lijun Yu, Wenhe Liu, Alexander G. Hauptmann

ECCV 2022 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Transductive and semantic-dictionary zero-shot · 23 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 group-to-group alignment of video segments and verb phrases (ablation)JigsawNet · KineticsZSAR (3 splits)rank-1 accuracy: 41.7 -> 45.9Improved
add group-to-group alignment (ablation)JigsawNet · KineticsZSAR (3 splits)rank-5 accuracy: 73.4 -> 78.8Improved
add consistency loss (ablation)JigsawNet · KineticsZSAR (3 splits)rank-1 accuracy: 43.2 -> 45.9Improved
add consistency loss (ablation)JigsawNet · KineticsZSAR (3 splits)rank-5 accuracy: 76.2 -> 78.8Improved
optimize consistency loss on aggregated instead of spatio-temporal features (ablation)JigsawNet · KineticsZSAR (3 splits)rank-1 accuracy: 45.1 -> 45.9Improved
add GE module (ablation)JigsawNet · KineticsZSAR (3 splits)rank-1 accuracy: 42.7 -> 45.9Improved
add GE module (ablation)JigsawNet · KineticsZSAR (3 splits)rank-5 accuracy: 72.9 -> 78.8Improved
deeper backbone R(2+1)D-34 instead of R(2+1)D-18 (ablation)JigsawNet · KineticsZSAR (3 splits)rank-1 accuracy: 42.9 -> 45.9Improved
deeper backbone R(2+1)D-34 instead of R(2+1)D-18 (ablation)JigsawNet · KineticsZSAR (3 splits)rank-5 accuracy: 73.0 -> 78.8Improved
TSM ResNet50 backbone vs R(2+1)D-34 (ablation)JigsawNet · KineticsZSAR (3 splits)rank-1 accuracy: 45.3 vs 45.9No clear effect
JigsawNet vs ER with same TSM extractor and inputsJigsawNet · KineticsZSAR (3 splits)rank-1 accuracy: 3.2 gainsImproved
JigsawNet vs ERJigsawNet · HMDB51 / UCF101rank-1 accuracy: 3.4 and 4.2 gainsImproved

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