AI Paper Atlas

Research map / Video / Action recognition

Knowledge is Power: Advancing Few-shot Action Recognition with Multimodal Semantics from MLLMs

Jiazheng Xing, Chao Xu, Hangjie Yuan, Mengmeng Wang, Jun Dan, Hangwei Qian, Yong Liu

IJCV 2026 · Video › Action recognition · approach: Disentangled action recognition · 0 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 hidden features directly instead of caption then encode (ablation)FSAR-LLaVA (Unknown) · HMDB51 5-way 1-shotaccuracy: 69.8 -> 79.5Improved
use hidden features directly instead of caption then encode (ablation)FSAR-LLaVA (Unknown) · Kinetics 5-way 1-shotaccuracy: 85.7 -> 88.1Improved
decouple visual and textual branches before pooling (ablation)Video-LLaVA features · Kinetics 5-way 1-shotaccuracy: 79.3 -> 82.1Improved
add spatiotemporal self-attention in MFM (ablation)FSAR-LLaVA (Unknown) · SSv2-Small 5-way 1-shotaccuracy: 48.5 -> 49.5Improved
add text-lead cross-attention in MFM (ablation)FSAR-LLaVA (Known) · SSv2-Full 5-way 1-shotaccuracy: 65.2 -> 69.4Improved
add local prototype construction (ablation)FSAR-LLaVA (Unknown) · Kinetics 5-way 1-shotaccuracy: 90.1 -> 94.5Improved
add global prototype construction to local (ablation)FSAR-LLaVA (Known) · SSv2-Small 5-way 1-shotaccuracy: 60.6 -> 65.5Improved
use MPMM instead of Bi-MHM (ablation)FSAR-LLaVA (Unknown) · SSv2-Small 5-way 1-shotaccuracy: 48.9 -> 51.0Improved
use MPMM instead of Hausdorff distance (ablation)FSAR-LLaVA (Unknown) · Kinetics 5-way 1-shotaccuracy: 92.0 -> 94.8Improved
increase mapping dimension from 128 to 256 (ablation)FSAR-LLaVA (Unknown) · Kinetics 5-way 1-shotaccuracy: 94.0 -> 94.8Improved
raise alpha from 0.1 to 0.9 (more local prototype weight) (ablation)FSAR-LLaVA (Unknown) · SSv2-Small vs Kinetics 5-way 1-shotaccuracy: 51.0 -> 49.2Mixed
switch from Unknown to Known promptsFSAR-LLaVA · SSv2-Small 5-way 1-shotaccuracy: 51.0 -> 65.5Improved

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