AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

Seq-SG2SL: Inferring Semantic Layout From Scene Graph Through Sequence to Sequence Learning

Boren Li, Boyu Zhuang, Mingyang Li, Jian Gu

ICCV 2019 · Graph learning › Knowledge and temporal graphs · approach: Scene graph generation · 11 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 sequential seq-to-seq formulation instead of graph convolution baselinelayout prediction · Visual Genome trainmean-SLEU (IoU 0.5): 0.0217 -> 0.4174Improved
use sequential seq-to-seq formulation instead of graph convolution baselinelayout prediction · Visual Genome testmean-SLEU (IoU 0.5): 0.0205 -> 0.0344Improved
use sequential seq-to-seq formulation instead of graph convolution baselinelayout prediction · Visual Genome testmean-SLEU (IoU 0.0): 1.0000 -> 0.9998No clear effect
add relative position encoding for the object box (ablation)Seq-SG2SL · Visual Genome trainmean-SLEU (IoU 0.5): 0.2698 -> 0.4174Improved
add relative position encoding for the object box (ablation)Seq-SG2SL · Visual Genome testmean-SLEU (IoU 0.5): 0.0334 -> 0.0344Improved
use Transformer instead of LSTM (ablation)Seq-SG2SL · Visual Genome trainmean-SLEU (IoU 0.5): 0.3822 -> 0.4174Improved
use Transformer instead of LSTM (ablation)Seq-SG2SL · Visual Genome testmean-SLEU (IoU 0.5): 0.0222 -> 0.0344Improved
LSTM seq-to-seq vs graph-convolution baseline (ablation)Seq-SG2SL framework · Visual Genome trainmean-SLEU (IoU 0.5): 0.0217 -> 0.3822Improved
use beam search top-1 instead of greedy decoding (ablation)Seq-SG2SL · Visual Genome trainmean-SLEU (IoU 0.5): 0.3958 -> 0.4174Improved
use beam search top-1 instead of greedy decoding (ablation)Seq-SG2SL · Visual Genome testmean-SLEU (IoU 0.5): 0.0335 -> 0.0344No clear effect
use beam top-2 instead of top-1 candidate (ablation)Seq-SG2SL · Visual Genome trainmean-SLEU (IoU 0.5): 0.4174 -> 0.3531Hurt

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