AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

Context-Aware Scene Graph Generation With Seq2Seq Transformers

Yichao Lu, Himanshu Rai, Jason Chang, Boris Knyazev, Guangwei Yu, Shashank Shekhar, Graham W. Taylor, Maksims Volkovs

ICCV 2021 · Graph learning › Knowledge and temporal graphs · approach: Scene graph generation · 87 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 sequential decoder conditioned on predicted triplets (teacher forcing) (ablation)Seq2Seq encoder-only · VG SGDET (graph constraint)Recall@100: 31.9 -> 33.0Improved
add sequential decoder conditioned on predicted triplets (teacher forcing) (ablation)Seq2Seq encoder-only · VRD Relationship Detection (free k)Recall@100: 31.6 -> 34.4Improved
add sequential decoder conditioned on predicted triplets (teacher forcing) (ablation)Seq2Seq encoder-only · VRD Phrase Detection (free k)Recall@100: 39.9 -> 43.9Improved
add RL training with mean-recall reward on top of teacher forcing (ablation)Seq2Seq · VG SGDET (graph constraint)Recall@100: 33.0 -> 34.4Improved
add RL training with mean-recall reward on top of teacher forcing (ablation)Seq2Seq · VG SGDETmRecall@100: 10.8 -> 12.1Improved
add RL training with mean-recall reward on top of teacher forcing (ablation)Seq2Seq · VRD Relationship Detection (free k)Recall@100: 34.4 -> 35.9Improved
add RL training with mean-recall reward on top of teacher forcing (ablation)Seq2Seq · VRD Phrase Detection (free k)Recall@100: 43.9 -> 46.2Improved
use RL instead of scheduled sampling (ablation)Seq2Seq · VG SGDETmRecall@100: 11.0 -> 12.1Improved
use RL instead of scheduled sampling (ablation)Seq2Seq · VG SGDET (graph constraint)Recall@100: 34.1 -> 34.4Improved
use scheduled sampling instead of teacher forcing (ablation)Seq2Seq · VG SGDET (graph constraint)Recall@100: 33.0 -> 34.1Improved
increase prediction block size at inference (ablation)Seq2Seq · VGaccuracyHurt
vary alpha between recall and mRecall in reward (ablation)Seq2Seq - RL · VG SGDETRecall vs mRecall @100Mixed

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