AI Paper Atlas

Research map / Video / Video segmentation and tracking

Representation Learning on Visual-Symbolic Graphs for Video Understanding

Effrosyni Mavroudi, Benjamín Béjar Haro, René Vidal

ECCV 2020 · Video › Video segmentation and tracking · approach: Stochastic video prediction · 38 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 the visual context module to actor features (ablation)ST-MPNN · CharadesmAP (%): 10.7 -> 13.7Improved
add the semantic context module to the visual module (ablation)ST-MPNN · CharadesmAP (%): 13.7 -> 15.3Improved
add long-term temporal modeling (ablation)ST-MPNN · CharadesmAP (%): 15.3 -> 18.6Improved
add the global model (ablation)ST-MPNN · CharadesmAP (%): 18.6 -> 23.4Improved
add semantic context module only (no visual) (ablation)ST-MPNN · CharadesmAP (%): 10.7 -> 11.7Improved
add the symbolic graph to the visual graph (ablation)ST-MPNN · CAD-120 sub-activityF1-score (%): 89.6 -> 90.4Improved
add the symbolic graph to the visual graph (ablation)ST-MPNN · CAD-120 affordanceF1-score (%): 88.6 -> 89.2Improved
use attention instead of fixed adjacency matrix (ablation)ST-MPNN · CAD-120F1-score (%)Improved
update nodes with both neighbor nodes and incoming edge attributes (ablation)ST-MPNN · CAD-120F1-score (%)Improved
increase number of ST-MPNN layers beyond 4-5 (ablation)ST-MPNN · CAD-120F1-score (%)No clear effect
replace MHA with visual context module in GVDGVD · ActivityNet Entities valF1_loc: 24.1 -> 25.2Improved
add semantic context module to GVD (MHA)GVD · ActivityNet Entities testCIDEr: 45.5 -> 47.7Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 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