AI Paper Atlas

Research map / Video / Action recognition

MMAD: Multi-label Micro-Action Detection in Videos

Kun Li, Pengyu Liu, Dan Guo, Fei Wang, Zhiliang Wu, Hehe Fan, Meng Wang

ICCV 2025 · Video › Action recognition · approach: Temporal action segmentation · 55 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 the temporal-informative adapter with the dual-path spatial-temporal adapter (DSTA)AdaTAD with VideoMAE-S · MMA-52 action-levelmAP Avg: 16.25 -> 18.16Improved
replace AdaTAD with DSTAAdaTAD with VideoMAE-B · MMA-52 (action/body average)AVG mAP: 23.08 -> 25.34Improved
replace AdaTAD with DSTAAdaTAD with VideoMAE-S · MMA-52 (action/body average)AVG mAP: 21.80 -> 23.43Improved
add spatial path to temporal adapter (DSTA vs TIA)AdaTAD with VideoMAE-S · MMA-52 action-levelmAP@0.7: 10.93 -> 9.03Mixed
use DSTA instead of full fine-tuning (ablation)VideoMAE-S snippet features · MMA-52 action-levelmAP: 15.40 -> 18.16Improved
use DSTA instead of a standard adapter (ablation)VideoMAE-S · MMA-52 action-levelmAP: 15.87 -> 18.16Improved
adapt the backbone (full fine-tuning) rather than frozen snippet features (ablation)VideoMAE-S · MMA-52 action-levelmAP: 10.60 -> 15.40Improved
insert adapter in all layers rather than only layers 1-4 (ablation)DSTA VideoMAE-S · MMA-52 action-levelmAP Avg: 10.38 -> 18.16Improved
insert adapter in middle or latter layers rather than early layers (ablation)DSTA VideoMAE-S · MMA-52 action-levelmAP Avg: 10.38 -> 13.83Improved
use larger backbone VideoMAE-B instead of VideoMAE-SDSTA · MMA-52 (action/body average)AVG mAP: 23.43 -> 25.34Improved
use multi-label detectors (MS-TCT, PointTAD) rather than feature-based single-label detectorsMMAD baselines · MMA-52 (action/body average)AVG mAP: 5.64 and 8.32 vs 20.34Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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