AI Paper Atlas

Research map / Video / Action recognition

Spatio-Temporal Decoupled Knowledge Compensator for Few-Shot Action Recognition

Hongyu Qu, Xiangbo Shu, Rui Yan, Hailiang Gao, Wenguan Wang, Jinhui Tang

TPAMI 2026 · Video › Action recognition · approach: Disentangled action recognition · 30 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 Temporal Knowledge Compensator (TKC) (ablation)DiST baseline · HMDB51 (5-way 1-shot)accuracy: 75.8 -> 81.0Improved
add Spatial Knowledge Compensator (SKC) (ablation)DiST baseline · HMDB51 (5-way 1-shot)accuracy: 75.8 -> 77.6Improved
add both SKC and TKC (ablation)DiST baseline · HMDB51 (5-way 1-shot)accuracy: 75.8 -> 82.6Improved
add SKC to TKC-only model (ablation)DiST · SSv2-small (5-way 1-shot)accuracy: 56.1 -> 57.5Improved
replace class names with LLM-generated knowledge for spatial and temporal attributes (ablation)DiST · HMDB51 (5-way 1-shot)accuracy: 80.0 -> 82.6Improved
use SKC/TKC injection instead of concatenation (ablation)DiST · HMDB51 (5-way 1-shot)accuracy: 80.7 -> 82.6Improved
use LLM-generated prompts in CLIP-FSAR plus knowledge compensators (ablation)CLIP-FSAR · HMDB51 (5-way 1-shot)accuracy: 81.0 -> 82.6Improved
use 6 spatial attributes instead of 1 (ablation)DiST · HMDB51 (5-way 1-shot)accuracy: 81.8 -> 82.6Improved
use 12 spatial attributes instead of 6 (ablation)DiST · HMDB51 (5-way 1-shot)accuracy: 82.6 -> 82.3Hurt
use 3 temporal attributes instead of 6 (ablation)DiST · HMDB51 (5-way 1-shot)accuracy: 81.5 -> 82.6Improved
use 9 object-level prototypes instead of 1 (ablation)DiST · HMDB51 (5-way 1-shot)accuracy: 80.8 -> 82.6Improved
increase object-level prototypes from 9 to 16 (ablation)DiST · HMDB51 (5-way 1-shot)accuracy: 82.6 -> 82.1Hurt

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