AI Paper Atlas

Research map / Video / Video segmentation and tracking

A Deep Ranking Model for Spatio-Temporal Highlight Detection From a 360◦ Video

Youngjae Yu, Sangho Lee, Joonil Na, Jaeyun Kang, Gunhee Kim

AAAI 2018 · Video › Video segmentation and tracking · approach: Self-supervised video representation learning · 47 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 smooth-motion stitching to CVS-C3D (ablation)CVS-C3D · Pano2VidFrame cosine similarity: 0.656 -> 0.774Improved
Add smooth-motion stitching to CVS-C3D (ablation)CVS-C3D · Pano2VidFrame overlap: 0.554 -> 0.646Improved
Add smooth-motion stitching to CVS-Inception (ablation)CVS-Inception · Pano2VidFrame cosine similarity: 0.642 -> 0.768Improved
Add smooth-motion stitching to CVS-Inception (ablation)CVS-Inception · Pano2VidFrame overlap: 0.545 -> 0.666Improved
Add smooth-motion stitching to CVS-Fusion (ablation)CVS-Fusion · Pano2VidFrame cosine similarity: 0.701 -> 0.800Improved
Add smooth-motion stitching to CVS-Fusion (ablation)CVS-Fusion · Pano2VidFrame overlap: 0.590 -> 0.677Improved
Fuse C3D and Inception-v3 features rather than using C3D alone (ablation)CVS · Pano2VidFrame cosine similarity: 0.656 -> 0.701Improved
Fuse C3D and Inception-v3 features rather than using Inception-v3 alone (ablation)CVS · Pano2VidFrame overlap: 0.545 -> 0.590Improved
Use triplet ranking loss instead of pairwise ranking loss (ablation)CVS-Fusion · WeddingmAP: 14.34 -> 17.96; 3.62Improved
Use triplet ranking loss instead of pairwise ranking loss (ablation)CVS-Fusion · MVmAP: 12.56 -> 14.92; 2.36Improved
Use triplet ranking loss rather than pairwise ranking models (ablation)CVS-Fusion · WeddingmAP: +5.98 vs RankNet; +4.73 vs TS-DCNNImproved
Use triplet ranking loss rather than pairwise ranking models (ablation)CVS-Fusion · MVmAP: +3.27 vs RankNet; +2.64 vs TS-DCNNImproved

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