AI Paper Atlas

Research map / Video / Action recognition

CAG-QIL: Context-Aware Actionness Grouping via Q Imitation Learning for Online Temporal Action Localization

Hyolim Kang, Kyungmin Kim, Yumin Ko, Seon Joo Kim

ICCV 2021 · Video › Action recognition · approach: Weakly supervised temporal action localization · 16 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 class probability p to the agent state (ablation)CAG-QIL · THUMOS14 On-TAL tIoU 0.5mAP: 27.2 -> 29.8Improved
add class probability p to the agent state (ablation)CAG-QIL · THUMOS14 On-TAL tIoU 0.3mAP: 43.0 -> 44.7Improved
add class probability p to the agent state (ablation)CAG-QIL · THUMOS14 On-TAL tIoU 0.7mAP: 12.4 -> 14.5Improved
train the agent with Q imitation learning instead of hand-crafted reward RL (ablation)CAG · THUMOS14 On-TAL tIoU 0.5mAP: 22.2 -> 29.8Improved
train the agent with Q imitation learning instead of behavior cloning (ablation)CAG · THUMOS14 On-TAL tIoU 0.5mAP: 3.3 -> 29.8Improved
train with QIL instead of RL (ablation)CAG · ActivityNet1.3 val tIoU 0.5mAP: 21.4 -> 30.5Improved
train with QIL instead of BC (ablation)CAG · ActivityNet1.3 val tIoU 0.5mAP: 9.5 -> 30.5Improved
add the CAG-QIL context-aware agent on top of OAD groupingOAD-Grouping · THUMOS14 On-TAL tIoU 0.5mAP: 22.0 -> 29.8Improved
add the CAG-QIL context-aware agent on top of OAD groupingOAD-Grouping · ActivityNet1.3 val tIoU 0.75mAP: 15.7 -> 18.5Improved
train the agent with hand-crafted frame-wise reward RLOAD-Grouping · THUMOS14 On-TAL (4 trials)mAP difference to baseline: 0.4 (SD 1.5) at tIoU 0.3, -0.1 (SD 0.8) at 0.5No clear effect
train the agent with behavior cloningOAD-Grouping · THUMOS14 On-TAL (4 trials)mAP difference to baseline: -25.2 at tIoU 0.3, -17.2 at 0.5Hurt
use CAG-QIL instead of hindsight per-class thresholdOAD-Grouping · THUMOS14 On-TAL tIoU 0.5mAP: 24.5 -> 29.8Improved

Later papers that compared with this method

3 later accepted papers report CAG-QIL as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.

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