AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

Graph Representation for Order-Aware Visual Transformation

Yue Qiu, Yanjun Sun, Fumiya Matsuzawa, Kenji Iwata, Hirokatsu Kataoka

CVPR 2023 · Graph learning › Knowledge and temporal graphs · approach: Graph reasoning for visual recognition · 2 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
Represent change contents as graph nodes and temporal orders as directed edges, explicitly associating changesVTGen · OVT testper-scene accuracy: 42.1 -> 57.8Improved
Represent change contents as graph nodes and temporal orders as directed edges, explicitly associating changesVTGen · CLEVR-Multi-ChangeSPICE: 71.7 -> 81.3Improved
Use graph matching loss instead of cross-entropy loss (ablation)VTGen transformer decoder, 1 layer and 4 heads · OVT testper-change accuracy (with order): 49.6 -> 52.4Improved
Use a transformer decoder instead of a GCN decoder (ablation)VTGen with graph matching loss and 1 decoder layer · OVT testper-change accuracy (with order): 49.0 -> 50.8Improved
Use one decoder layer instead of two (ablation)VTGen transformer with graph matching loss and 2 heads · OVT testper-change accuracy (with order): 36.6 -> 50.8Improved
Use one decoder layer instead of two (ablation)VTGen transformer with graph matching loss and 4 heads · OVT testper-change accuracy (with order): 41.1 -> 52.4Improved
Use four attention heads instead of two (ablation)VTGen transformer with graph matching loss and 1 layer · OVT testper-change accuracy (with order): 50.8 -> 52.4Improved
Use four attention heads instead of two (ablation)VTGen transformer with cross-entropy loss and 1 layer · OVT testper-change accuracy (with order): 50.2 -> 49.6Hurt
Use graph matching loss instead of cross-entropy loss (ablation)VTGen transformer decoder, 1 layer and 2 heads · OVT testper-change accuracy (with order): 50.2 -> 50.8Improved
Use a two-layer GCN instead of a one-layer GCN (ablation)VTGen with cross-entropy loss · OVT testper-change accuracy (with order): 47.2 -> 42.6Hurt
Use a two-layer GCN instead of a one-layer GCN (ablation)VTGen with graph matching loss · OVT testper-change accuracy (with order): 49.0 -> 45.2Hurt

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