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

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Xu, Zhu, Lei, Ting, Li, Zhimin, Wang, Guan, Chen, Qingchao, Peng, Yuxin, liu, Yang
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913978763968512
author Xu, Zhu
Lei, Ting
Li, Zhimin
Wang, Guan
Chen, Qingchao
Peng, Yuxin
liu, Yang
author_facet Xu, Zhu
Lei, Ting
Li, Zhimin
Wang, Guan
Chen, Qingchao
Peng, Yuxin
liu, Yang
contents Dynamic Scene Graph Generation (DSGG) aims to create a scene graph for each video frame by detecting objects and predicting their relationships. Weakly Supervised DSGG (WS-DSGG) reduces annotation workload by using an unlocalized scene graph from a single frame per video for training. Existing WS-DSGG methods depend on an off-the-shelf external object detector to generate pseudo labels for subsequent DSGG training. However, detectors trained on static, object-centric images struggle in dynamic, relation-aware scenarios required for DSGG, leading to inaccurate localization and low-confidence proposals. To address the challenges posed by external object detectors in WS-DSGG, we propose a Temporal-enhanced Relation-aware Knowledge Transferring (TRKT) method, which leverages knowledge to enhance detection in relation-aware dynamic scenarios. TRKT is built on two key components:(1)Relation-aware knowledge mining: we first employ object and relation class decoders that generate category-specific attention maps to highlight both object regions and interactive areas. Then we propose an Inter-frame Attention Augmentation strategy that exploits optical flow for neighboring frames to enhance the attention maps, making them motion-aware and robust to motion blur. This step yields relation- and motion-aware knowledge mining for WS-DSGG. (2) we introduce a Dual-stream Fusion Module that integrates category-specific attention maps into external detections to refine object localization and boost confidence scores for object proposals. Extensive experiments demonstrate that TRKT achieves state-of-the-art performance on Action Genome dataset. Our code is avaliable at https://github.com/XZPKU/TRKT.git.
format Preprint
id arxiv_https___arxiv_org_abs_2508_04943
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle TRKT: Weakly Supervised Dynamic Scene Graph Generation with Temporal-enhanced Relation-aware Knowledge Transferring
Xu, Zhu
Lei, Ting
Li, Zhimin
Wang, Guan
Chen, Qingchao
Peng, Yuxin
liu, Yang
Computer Vision and Pattern Recognition
Artificial Intelligence
Dynamic Scene Graph Generation (DSGG) aims to create a scene graph for each video frame by detecting objects and predicting their relationships. Weakly Supervised DSGG (WS-DSGG) reduces annotation workload by using an unlocalized scene graph from a single frame per video for training. Existing WS-DSGG methods depend on an off-the-shelf external object detector to generate pseudo labels for subsequent DSGG training. However, detectors trained on static, object-centric images struggle in dynamic, relation-aware scenarios required for DSGG, leading to inaccurate localization and low-confidence proposals. To address the challenges posed by external object detectors in WS-DSGG, we propose a Temporal-enhanced Relation-aware Knowledge Transferring (TRKT) method, which leverages knowledge to enhance detection in relation-aware dynamic scenarios. TRKT is built on two key components:(1)Relation-aware knowledge mining: we first employ object and relation class decoders that generate category-specific attention maps to highlight both object regions and interactive areas. Then we propose an Inter-frame Attention Augmentation strategy that exploits optical flow for neighboring frames to enhance the attention maps, making them motion-aware and robust to motion blur. This step yields relation- and motion-aware knowledge mining for WS-DSGG. (2) we introduce a Dual-stream Fusion Module that integrates category-specific attention maps into external detections to refine object localization and boost confidence scores for object proposals. Extensive experiments demonstrate that TRKT achieves state-of-the-art performance on Action Genome dataset. Our code is avaliable at https://github.com/XZPKU/TRKT.git.
title TRKT: Weakly Supervised Dynamic Scene Graph Generation with Temporal-enhanced Relation-aware Knowledge Transferring
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2508.04943