AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

Gamba: Mamba-based graph convolutional network with dynamic graph topology learning for action recognition

Rouyi Zhou, Yangzhi Wu, Jiajun Wen, Can Gao, Feng Liu, Zhihui Lai, Linlin Shen

CVPR 2026 · Graph learning › Knowledge and temporal graphs · approach: Graph reasoning for visual recognition

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 the Cls-Mamba module to the baseline (ablation)CTR-GC + Naive TCN baseline · NTU RGB+D 60 X-View (joint stream)accuracy (%): 95.8 -> 96.0Improved
add temporal Mamba (T-Mamba) alone (ablation)CTR-GC + Naive TCN baseline · NTU RGB+D 60 X-View (joint stream)accuracy (%)No clear effect
add node classification module (NCM) before spatial Mamba (ablation)Cls-Mamba · NTU RGB+D 60 X-View (joint stream)accuracy (%): +0.8Improved
use all modules together (NCM, S-Mamba, T-Mamba, TCN) (ablation)Gamba · NTU RGB+D 60 X-View (joint stream)accuracy (%): 95.8 -> 96.5Improved
insert Mamba after every GCN layer (9) instead of 3 or 6 (ablation)Gamba · NTU RGB+D 60 X-View (joint stream)accuracy (%): 95.4 (3) -> 95.6 (6) -> 96.5 (9)Improved
use TCN kernel size 5 instead of 3 or 7 (ablation)Mamba-TCN · NTU RGB+D 60 X-View (joint stream)accuracy (%): 95.6 (k=3), 96.5 (k=5), 95.7 (k=7)Improved
use 64 node categories instead of 32 or 128 (ablation)NCM · NTU RGB+D 60 X-View (joint stream)accuracy (%): 96.1 (32), 96.5 (64), 96.0 (128)Improved
use 64 node categories instead of 32 or 128 (ablation)NCM · NTU RGB+D 120 X-Sub (joint stream)accuracy (%): 86.0 (32), 86.3 (64), 85.5 (128)Improved
replace CTR-GCN with Gamba in the 4-stream ensembleCTR-GCN · NTU RGB+D 60 X-Subtop-1 accuracy (%): 92.4 -> 93.4Improved
replace BlockGCN with Gamba on NTU RGB+D 120 X-SubBlockGCN · NTU RGB+D 120 X-Subtop-1 accuracy (%): 90.3 -> 90.1Hurt
use Gamba instead of CTR-GCN for computationCTR-GCN · Model costFLOPs (G): 14.4 -> 11.1Improved
use Gamba instead of CTR-GCN for parameter countCTR-GCN · Model costtrainable parameters (M): 1.2 -> 4.5Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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