AI Paper Atlas

Research map / Video / Action recognition

C2F-TCN: A Framework for Semi- and Fully-Supervised Temporal Action Segmentation

Dipika Singhania, Rahul Rahaman, Angela Yao

TPAMI 2023 · Video › Action recognition · approach: Temporal action segmentation · 65 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 coarse-to-fine ensemble of decoder outputs (ablation)base model M · BreakfastF1@10: +5.1 F1@10, +3.1 EditImproved
add coarse-to-fine ensemble (ablation)ED-TCN · 50SaladsMoF: 62.7 -> 63.3 Edit; 66.5 -> 68.5 MoFImproved
add feature augmentation (FA-Train-Test) (ablation)C2F-TCN · 50SaladsMoF: 79.6 -> 84.5Improved
add feature augmentation (FA-Train-Test) (ablation)C2F-TCN · BreakfastMoF: 70.2 -> 76.6Improved
add feature augmentation (FA-Train-Test) (ablation)MS-TCN · BreakfastMoF: 67.6 -> 71.3Improved
add feature augmentation (ablation)MS-TCN · GTEAF1@25: F1@25 86.2 -> 85.7; F1@50 74.4 -> 74.1Mixed
add temporal pyramid pooling layer (ablation)C2F-TCN + FA · 50SaladsF1@50: 71.0 -> 72.8Improved
add loss at each decoder layer instead of ensemble (ablation)base model M · BreakfastEdit: Edit 60.1 -> 58.7; MoF 69.3 -> 70.6Hurt
use learned ensemble weights instead of fixed (ablation)C2F-TCN · BreakfastEdit: Edit 63.2 -> 61.4; MoF 70.2 -> 70.5Hurt
use fixed equal ensemble weights (ablation)base model M · BreakfastEdit: 60.1 -> 63.2Improved
add time-proximity condition to contrastive learning (ablation)unsupervised C2F-TCN · BreakfastMoF: 36.1 -> 50.0Improved
add video-level constraint to contrastive learning (ablation)unsupervised C2F-TCN · BreakfastMoF: 50.0 -> 66.1Improved

Later papers that compared with this method

2 later accepted papers report C2F-TCN as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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