AI Paper Atlas

Research map / Video / Action recognition

Summarizing First-Person Videos from Third Persons' Points of View

HSUAN-I HO, Wei-Chen Chiu, Yu-Chiang Frank Wang

ECCV 2018 · Video › Action recognition · approach: Temporal action segmentation

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 unlabeled first-person videos (semi-supervised) (ablation)Ours non-sequential · SumMeF-measure: 35.272 -> 38.649Improved
add unlabeled first-person videos (semi-supervised) (ablation)Ours non-sequential · FPVSumF-measure: 37.098 -> 38.409Improved
add unlabeled first-person videos (semi-supervised) (ablation)Ours sequential · SumMeF-measure: 35.980 -> 41.991Improved
add unlabeled first-person videos (semi-supervised) (ablation)Ours sequential · FPVSumF-measure: 37.366 -> 38.572Improved
use recurrent highlight detector instead of 2-layer fully connectedOurs · SumMeF-measure: 38.649 -> 41.991Improved
use recurrent highlight detector instead of 2-layer fully connectedOurs · FPVSumF-measure: 38.409 -> 38.572Improved
add private encoders to shared encoder (ablation)Ours non-sequential · SumMeF-measure: 29.754 -> 38.649Improved
add private encoders to shared encoder (ablation)Ours non-sequential · FPVSumF-measure: 31.020 -> 38.409Improved
add pseudo triplet loss on unlabeled videos (ablation)Ours non-sequential · SumMeF-measure: 34.252 -> 38.649Improved
add pseudo triplet loss on unlabeled videos (ablation)Ours non-sequential · FPVSumF-measure: 35.485 -> 38.409Improved
use classification scoring loss instead of ranking loss (ablation)Ours non-sequential · SumMeF-measure: 28.435 -> 38.649Improved
use classification scoring loss instead of MSE loss (ablation)Ours non-sequential · FPVSumF-measure: 36.046 -> 38.409Improved

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