AI Paper Atlas

Research map / Video / Video segmentation and tracking

TRACK: A New Method from a Re-examination of Deep Architectures for Head Motion Prediction in 360-degree Videos

Miguel Fabián Romero Rondón, Lucile Sassatelli, Ramón Aparicio-Pardo, Fŕed́eric Precioso

TPAMI 2021 · Video › Video segmentation and tracking · approach: Physics-inspired motion prediction · 62 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
replace PAMI18 predictor with a trivial no-motion baselinehead motion prediction · PAMI18 dataset, H~30ms (1 frame)Mean Overlap: 0.753 -> 0.968Improved
replace ChinaCom18 with the trivial-static baselinehead motion prediction · ChinaCom18 dataset, H=1saccuracy: 72.54% -> 96.15%Improved
replace NOSSDAV17-Orient. with the trivial-static baselinehead motion prediction · NOSSDAV17 dataset, H=1saccuracy: 86.35% -> 95.79%Improved
use seq2seq LSTM on positions instead of trivial-staticdeep-position-only baseline · PAMI18 dataset, H~30ms (1 frame)Mean Overlap: 0.968 -> 0.977Improved
use seq2seq LSTM on positions instead of trivial-staticdeep-position-only baseline · ChinaCom18 dataset, H=1saccuracy: 96.15% -> 96.90%Improved
add video content (TRACK) to position-only baseline at short horizonTRACK · NOSSDAV17 dataset, H=1saccuracy: 96.30% -> 95.48%Hurt
add seq2seq framework, 3D Euclidean MSE loss and displacement prediction to CVPR18 and MM18 (improved versions) (ablation)CVPR18 and MM18 with ground-truth saliency · MMSys18 subset, H up to 5sorthodromic distanceImproved
use a dedicated recurrent unit for positions before fusing with visual features (CVPR18 style) instead of one RNN doing both (MM18 style) (ablation)head motion predictor with ground-truth saliency · MMSys18 subset, H up to 5sorthodromic distanceImproved
replace ground-truth saliency with content-based saliency (ablation)CVPR18-improved · MMSys18 subset, H up to 5sorthodromic distanceHurt
add a dedicated content RNN for saliency before fusion (TRACK) (ablation)CVPR18-improved with content-based saliency · MMSys18 subset, H up to 5sorthodromic distanceImproved

Later papers that compared with this method

1 later accepted paper reports Track as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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