AI Paper Atlas

Research map / Video / Action recognition

CFAD: Coarse-to-Fine Action Detector for Spatiotemporal Action Localization

Yuxi Li, Weiyao Lin, John See, Ning Xu Shugong Xu, Ke Yan, Cong Yang

ECCV 2020 · Video › Action recognition · approach: Weakly supervised temporal action localization · 26 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 location refinement module (sigma=0.8) (ablation)CFAD coarse tubes · UCF101-24, k=2v-mAP (%): 46.0 -> 60.3Improved
add location refinement module (sigma=0.8) (ablation)CFAD coarse tubes · UCF101-24, k=4v-mAP (%): 51.6 -> 62.7Improved
add location refinement module (sigma=0.8) (ablation)CFAD coarse tubes · JHMDB-21, k=2v-mAP (%): 80.9 -> 83.7Improved
enlarge refinement search area sigma from 0.4 to 0.8 (ablation)CFAD · UCF101-24, k=4v-mAP (%): 58.8 -> 62.7Improved
enlarge search area beyond sigma=0.8 (ablation)CFAD · UCF101-24v-mAP (%): less than +0.2%No clear effect
raise polynomial order from 4 to 5 (ablation)CFAD · UCF101-24v-mAP (%): 62.7 -> 61.6Hurt
raise polynomial order from 2 to 4 (ablation)CFAD · UCF101-24v-mAP (%): 60.3 -> 62.7Improved
add temporal residual (Diff Block) branch (ablation)CFAD coarse module · UCF101-24wrong classification errors: reduced by 42%Improved
add temporal residual (Diff Block) branch (ablation)CFAD coarse module · JHMDB-21wrong classification errors: reduced by 14%Improved
add refinement (ablation)CFAD · UCF101-24v-MABO: at most +4.7%Improved
use dynamic key timestamp selection instead of random or uniform (ablation)CFAD · UCF101-24v-mAP at similar time costImproved
add optical flow input to RGBCFAD · UCF101-24 delta=0.5v-mAP (%): 62.7 -> 64.6Improved

Later papers that compared with this method

1 later accepted paper reports CFAD as a baseline in their results tables; 0 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