AI Paper Atlas

Research map / Video / Video segmentation and tracking

GraphVid: It Only Takes a Few Nodes to Understand a Video

Eitan Kosman, Dotan Di Castro

ECCV 2022 · Video › Video segmentation and tracking · approach: Stochastic video prediction · 3 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 relational edges (RGCN) instead of GCN (ablation)GCN on video-graph · Kinetics-400 val (800 superpixels)top-1 accuracy: 50.1 -> 66.2Improved
use relational edges (RGCN) instead of GAT (ablation)GAT on video-graph · Kinetics-400 val (800 superpixels)top-1 accuracy: 54.7 -> 66.2Improved
use RGCN instead of GAT for compute (ablation)GAT on video-graph · Kinetics-400 val (800 superpixels)FLOPs (x10^9): 56 -> 42Improved
add the full set of four augmentations (ablation)RGCN-800 · Kinetics-400 valtop-1 accuracy: 66.2 -> 76.4Improved
add the full set of four augmentations (ablation)RGCN-800 · CharadesmAP: 37.4 -> 43.1Improved
increase superpixels from 800 to 2000RGCN · Kinetics-400 valtop-1 accuracy: 76.4 -> 80.0Improved
pretrain on Kinetics-400 before Charades fine-tuningRGCN-2000 · CharadesmAP: 45.3 -> 49.4Improved
add additive Gaussian edge noise (sigma 0.4) (ablation)RGCN-800 · Kinetics-400 valtop-1 accuracy: 74.5Improved
add additive Gaussian node noise (sigma 0.2) (ablation)RGCN-800 · Kinetics-400 valtop-1 accuracy: 73Improved
add random removal of spatial edges (ablation)RGCN-800 · Kinetics-400 valtop-1 accuracy: 66Hurt
add random removal of superpixels (keep 0.8) (ablation)RGCN-800 · Kinetics-400 valtop-1 accuracy: 70Improved
increase number of superpixels per frame (ablation)GCN/GAT/RGCN · Kinetics-400 valtop-1 accuracy: saturates for S >= 650Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.

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