AI Paper Atlas

Research map / Video / Video segmentation and tracking

Video Geo-Localization Employing Geo-Temporal Feature Learning and GPS Trajectory Smoothing

Krishna Regmi, Mubarak Shah

ICCV 2021 · Video › Video segmentation and tracking · approach: Spatio-temporal predictive modeling · 18 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 clip triplet loss to frame triplet loss (ablation)GTFL · BDD-GSV video geo-localization (SF)localization error (m): 704.16 -> 524.81Improved
add GPS loss to frame and clip triplet losses (ablation)GTFL · BDD-GSV video geo-localization (SF)localization error (m): 524.81 -> 300.47Improved
add clip triplet loss to frame triplet loss (ablation)GTFL · BDD-GSV video geo-localization (NY)localization error (m): 978.51 -> 836.13Improved
add GPS loss to frame and clip triplet losses (ablation)GTFL · BDD-GSV video geo-localization (Berkeley)localization error (m): 819.54 -> 424.79Improved
add trajectory smoothing networkGTFL · BDD-GSV video geo-localization (SF)localization error (m): 300.47 -> 128.94Improved
add trajectory smoothing networkGTFL · BDD-GSV video geo-localization (NY)localization error (m): 493.43 -> 285.41Improved
add smoothing network2D CNNf · BDD-GSV video geo-localization (SF)localization error (m): 2091.66 -> 1710.54Improved
fine-tune 2D CNN on the dataset2D CNN · BDD-GSV video geo-localization (SF)localization error (m): 2516 -> 2091.66Improved
replace 2D CNNf frame-wise features with transformer geo-temporal features2D CNNf · BDD-GSV video geo-localization (SF)localization error (m): 2091.66 -> 300.47Improved
use 3D CNN trained from scratch instead of fine-tuned 2D CNN2D CNNf · BDD-GSV video geo-localization (SF)localization error (m): 2091.66 -> 4247.09Hurt
use 2 attention heads and 1 layer instead of 4 heads and 2 layers in smoothing network (ablation)smoothing network · BDD-GSV video geo-localization (SF)localization error (m): 128.94 -> 158.07Hurt
use 4 layers instead of 2 in smoothing network (4 heads) (ablation)smoothing network · BDD-GSV video geo-localization (SF)localization error (m): 128.94 -> 129.46No clear effect

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