AI Paper Atlas

Research map / Video / Video segmentation and tracking

A Spherical Convolution Approach for Learning Long Term Viewport Prediction in 360 Immersive Video

Chenglei Wu, Ruixiao Zhang, Zhi Wang, Lifeng Sun

AAAI 2020 · Video › Video segmentation and tracking · approach: Layered video decomposition and dynamics · 50 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
use near-identity kernel instead of equatorial kernel (ablation)S2CNN feature extractor · PanoUCF101top-1 accuracy (%): 57.9 -> 65.7Improved
add one more SO3Conv layer (6 layers) (ablation)S2CNN feature extractor · PanoUCF101top-1 accuracy (%): 65.7 -> 76.5Improved
increase frame sampling rate F from 4 to 16 (ablation)S2CNN+ConvGRU · PanoUCF101top-1 accuracy (%): 70.3 -> 73.2Improved
remove preference and attention (History only) vs AttPref (ablation)AttPref viewport predictor · 360 viewport dataset (Wu et al. 2017)viewport accuracy (IOU): 16.2% reduction at wk=8 without themImproved
replace 360Sal saliency features with AttPrefviewport predictor · 360 viewport dataset (Wu et al. 2017)viewport accuracy (IOU): 32.3% improvement for wk=6Improved

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