TGBFormer: Transformer-GraphFormer Blender Network for Video Object Detection
Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (6) · 6559-6567
DOI: 10.1609/aaai.v39i6.32703 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Qiang Qi und 1 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref).
Abstract (Originalsprache)
Video object detection has made significant progress in recent years thanks to convolutional neural networks (CNNs) and vision transformers (ViTs). Typically, CNNs excel at capturing local features but struggle to model global representations. Conversely, ViTs are adept at capturing long-range global features but face challenges in representing local feature details. Off-the-shelf video object detection methods solely rely on CNNs or ViTs to conduct feature aggregation, which hampers their capability to simultaneously leverage global and local information, thereby resulting in limited detection performance. In this paper, we propose a Transformer-GraphFormer Blender Network (TGBFormer) for video object detection, with three key technical improvements to fully exploit the advantages of transformers and graph convolutional networks while compensating for their limitations. First, we develop a spatial-temporal transformer module to aggregate global contextual information, constituting global representations with long-range feature dependencies. Second, we introduce a spatial-temporal GraphFormer module that utilizes local spatial and temporal relationships to aggregate features, generating new local representations that are complementary to the transformer outputs. Third, we design a global-local feature blender module to adaptively couple transformer-based global representations and GraphFormer-based local representations. Extensive experiments demonstrate that our TGBFormer establishes new state-of-the-art results on the ImageNet VID dataset. Particularly, our TGBFormer achieves 86.5% mAP while running at around 41.0 FPS on a single Tesla A100 GPU.
Zitieren
APA
Qi, Q., & Wang, X. (2025). TGBFormer: Transformer-GraphFormer Blender Network for Video Object Detection. Proceedings of the AAAI Conference on Artificial Intelligence, 39(6), 6559-6567. https://doi.org/10.1609/aaai.v39i6.32703
Vancouver
Qi Q, Wang X. TGBFormer: Transformer-GraphFormer Blender Network for Video Object Detection. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(6):6559-6567. doi:10.1609/aaai.v39i6.32703
BibTeX
@article{Qi2025,
author = {Qi, Qiang and Wang, Xiao},
title = {TGBFormer: Transformer-GraphFormer Blender Network for Video Object Detection},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2025},
volume = {39},
number = {6},
pages = {6559--6567},
doi = {10.1609/aaai.v39i6.32703}
}
EUVIMED