AI Paper Atlas

Research map / Video / Video-language understanding

Revisiting Weakly-Supervised Video Scene Graph Generation via Pair Affinity Learning

MINSEOK KANG, Minhyeok Lee, Minjung Kim, Jungho Lee, Donghyeong Kim, Sungmin Woo, Inseok Jeon, Sangyoun Lee

ECCV 2026 · Video › Video-language understanding · approach: Dense video captioning · 1 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 pair affinity learning and scoring (PALS) (ablation)PLA + STTran · AG SGDet (With Constraint)R@10: 15.39 -> 19.79Improved
add pair affinity modulation (PAM) to PALS (ablation)PLA + STTran · AG SGDet (With Constraint)R@10: 19.79 -> 20.22Improved
add relation-aware matching (RAM) alone (ablation)PLA + STTran · AG SGDet (With Constraint)R@10: 15.39 -> 15.90Improved
add RAM on top of PALS (ablation)PLA + STTran · AG SGDet (With Constraint)R@10: 19.79 -> 22.14Improved
add PAM on top of RAM + PALS (ablation)PLA + STTran · AG SGDet (With Constraint)R@10: 22.14 -> 22.24Improved
add PALS to the No Constraint setting (ablation)PLA + STTran · AG SGDet (No Constraint)R@10: 15.83 -> 21.03Improved
use pair affinity score in inference-time ranking (ablation)PLA + Ours (STTran) · AG SGDetR@10: +5.16 in (W)R@10 and +6.95 in (N)R@10Improved
replace class-level matching with RAM (GroundingDINO) (ablation)PLA pseudo-labels · AG pseudo-label qualityprecision: 0.4016 -> 0.7255Improved
replace class-level matching with RAM (GroundingDINO) (ablation)PLA pseudo-labels · AG pseudo-label qualityrecall: 0.4423 -> 0.3995Hurt
use GLIP instead of GroundingDINO in RAM (ablation)PLA + Ours (STTran) · AG SGDet (With Constraint)R@50: 28.00 -> 26.65Hurt
lower RAM reliability threshold fallback: tau_r 0.3 vs 1.0 (class-level matching) (ablation)PLA + Ours (STTran) · AG SGDet (With Constraint)R@10: 20.25 -> 22.24Improved
raise grounding score threshold tau_gs from 0.2 to 0.9 (ablation)PLA + Ours (STTran) · AG SGDet (With Constraint)R@10: 22.24 -> 19.82Hurt

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