AI Paper Atlas

Research map / Video / Action recognition

Are you Struggling? Dataset and Baselines for Struggle Determination in Assembly Videos

Shijia Feng, Michael Wray, Brian Sullivan, Youngkyoon Jang, Casimir J. H. Ludwig, Iain Donald Gilchrist, Walterio W. Mayol-Cuevas

IJCV 2025 · Video › Action recognition · approach: Action anticipation and latent actions · 4 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
train as classification instead of regression (ablation)MViTv2 · Pipes-Struggle binaryaccuracy: 75.03 -> 76.68Improved
train as classification instead of regression (ablation)MViTv2 · Tower-Struggle four-wayaccuracy: 33.41 -> 57.42Improved
train on combined struggle subsets instead of Pipes alone (ablation)MViTv2 · Pipes-Struggle binaryaccuracy: 76.68 -> 79.83Improved
train on combined struggle subsets instead of Tent alone (ablation)MViTv2 · Tent-Struggle binaryaccuracy: 64.42 -> 69.48Improved
train on combined struggle subsets instead of Tower alone (ablation)MViTv2 · Tower-Struggle four-wayaccuracy: 57.42 -> 68.81Improved
zero-shot transfer from Pipes to Tent (ablation)MViTv2 · Tent-Struggle binaryaccuracy: 64.42 -> 49.22Hurt
evaluate with a single frame instead of 128 frames (ablation)SlowFast models · all three activitiesaccuracyHurt
shuffle frame order at test time (ablation)SlowFast models · all three activitiesaccuracyHurt
add ViT or gMLP temporal layer on SlowFast-R50SlowFast-R50 · Pipes-Struggle binaryaccuracy: 78.01 -> 77.80No clear effect
use SlowFast-R50 instead of TSN (2D to 3D ConvNet)TSN · Tower-Struggle binaryaccuracy: 82.59 -> 88.24Improved
use label distribution learning instead of classificationMViTv2 · Pipes-Struggle binaryaccuracy: 76.68 -> 78.88Improved
use label distribution learning instead of classificationMViTv2 · Tent-Struggle binaryaccuracy: 64.42 -> 64.58Mixed

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