AI Paper Atlas

Research map / Video / Video segmentation and tracking

TRKT: Weakly Supervised Dynamic Scene Graph Generation with Temporal-enhanced Relation-aware Knowledge Transferring

Zhu Xu, Ting Lei, Zhimin Li, Guan Wang, Qingchao Chen, Yuxin Peng, Yang Liu

ICCV 2025 · Video › Video segmentation and tracking · approach: Layered video decomposition and dynamics · 8 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 Inter-frame Attention Augmentation (optical-flow temporal cues) on top of CBM+LRM (ablation)TRKT · Action Genome object detectionAP (maxDets=1): 14.1 -> 23.0Improved
add IAA to attention-map-only detections (ablation)Internal detections · Action Genome object detectionAP (maxDets=1): 2.8 -> 5.3Improved
combine attention-map detections with external detections (ablation)PLA · Action Genome WS-DSGG (With Constraint)R@10: 14.32 -> 16.52Improved
use attention-map detections alone instead of external detector (ablation)PLA · Action Genome object detectionAP (maxDets=1): 11.4 -> 2.8Hurt
add Confidence Boosting Module (ablation)PLA · Action Genome object detectionAP (maxDets=1): 11.4 -> 12.6Improved
add Localization Refinement Module (ablation)PLA · Action Genome object detectionAP (maxDets=1): 11.4 -> 13.4Improved
combine CBM and LRM (ablation)PLA · Action Genome object detectionAP (maxDets=1): 11.4 -> 14.1Improved
add object tokens to class decoder (ablation)PLA · Action Genome object detectionAP (maxDets=1): 11.4 -> 21.6Improved
add relation tokens to object tokens (ablation)TRKT · Action Genome object detectionAP (maxDets=1): 21.6 -> 23.0Improved
add relation tokens to object tokens (ablation)TRKT · Action Genome object detectionAR (maxDets=1): 31.8 -> 28.8Hurt
replace PLA with TRKT detections for pseudo labelsWS-DSGG · Action Genome (No Constraints)R@10: 15.87 -> 18.76Improved
apply TRKT on UCML for tracklet-level WS-DSGGUCML · VidVRDmAP: 17.17% -> 17.93%Improved

Later papers that compared with this method

1 later accepted paper reports TRKT as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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