Research map / Video / Video segmentation and tracking
Egocentric Meets Top-View
Shervin Ardeshir, Ali Borji
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 changed | Where | Measured | Effect |
|---|---|---|---|
| enforce consistent time delays via iterative joint optimization instead of independent cross-correlation maxima | Egocentric-top-view graph matching · Top-view video ranking | ranking accuracy: more than 1.3% and 3.1% | Improved |
| use matching-score based optimization instead of spectral optimization | Egocentric-top-view graph matching · Top-view video ranking | ranking accuracy | Improved |
| initialize time delays with median of cross-correlation suggestions instead of zeros (ablation) | Egocentric-top-view graph matching · Viewer assignment accuracy | assignment accuracy | Improved |
| add pairwise (edge) features to graph matching (ablation) | Egocentric-top-view graph matching · Viewer assignment accuracy | assignment accuracy | Improved |
| add GIST vs Top-FOV 2D unary features over 1D people-count feature | Egocentric-top-view graph matching · Viewer ranking | ranking accuracy | Improved |
| increase completeness ratio of egocentric set (ablation) | Egocentric-top-view graph matching · Viewer assignment accuracy | assignment accuracy | Improved |
| use longer video clips (ablation) | Egocentric-top-view graph matching · Viewer assignment accuracy | assignment accuracy | Improved |
Closest papers by meaning
- Ego2Top: Matching Viewers in Egocentric and Top-View Videos (ECCV 2016 · similarity 0.95)
- Integrating Egocentric Videos in Top-view Surveillance Videos: Joint Identification and Temporal Alignment (ECCV 2018 · similarity 0.93)
- EgoSim: An Egocentric Multi-view Simulator and Real Dataset for Body-worn Cameras during Motion and Activity (NeurIPS 2024 · similarity 0.87)
- EgoVid-5M: A Large-Scale Video-Action Dataset for Egocentric Videos Generation (NeurIPS 2025 · similarity 0.86)
- Action Scene Graphs for Long-Form Understanding of Egocentric Videos (CVPR 2024 · similarity 0.86)
- Instance Tracking in 3D Scenes from Egocentric Videos (CVPR 2024 · similarity 0.86)
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.
