AI Paper Atlas

Research map / Video / Action recognition

Efficient Action Counting with Dynamic Queries

Xiaoxuan Ma, Zishi Li, Qiuyan Shang, Wentao Zhu, Hai Ci, Yu Qiao, Yizhou Wang

IJCV 2026 · Video › Action recognition · approach: Disentangled action recognition · 6 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 Dynamic Action Query (initialise decoder queries from selected encoder features) (ablation)action counting model · RepCountA test (TSN backbone)MAE: 0.3542 -> 0.2809Improved
add Dynamic Action Query (ablation)action counting model · RepCountA test (TSN backbone)OBO: 0.4172 -> 0.4570Improved
add Inter-query Contrastive Learning (ablation)action counting model · RepCountA test (TSN backbone)MAE: 0.4035 -> 0.2809Improved
add Inter-query Contrastive Learning (ablation)action counting model · RepCountA test (TSN backbone)OBO: 0.4040 -> 0.4570Improved
add DAQ to short-period actions (ablation)action counting model · RepCountA test (TSN backbone)OBO (short): 0.2093 -> 0.1628Hurt
switch backbone from TSN to ViTaction counting model · RepCountA testOBO: 0.4570 -> 0.5430Improved
switch backbone from I3D to ViTaction counting model · RepCountA testMAE: 0.3305 -> 0.2622Improved
use query-based linear-complexity model instead of TransRAC at T=64action counting model · RepCountA inferenceinference time (s): 2.43 -> 0.15Improved
increase input length from 64 to 512 framesaction counting model · RepCountA inferenceinference time (s): 0.15 -> 0.78Improved
raise confidence threshold above 0.5 (ablation)action counting model · RepCountA testOBOHurt
use ViT-backed query model instead of TransRAC on unseen UCFRepaction counting model · UCFRep test (trained on RepCountA)OBO: 0.3143 -> 0.4184Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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