CDTR: Semantic Alignment for Video Moment Retrieval Using Concept Decomposition Transformer
Proceedings of the AAAI Conference on Artificial Intelligence · 11.04.2025 · 39 (6) · 6684-6692
DOI: 10.1609/aaai.v39i6.32717 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 11.04.2025. Verfasst von Ran Ran und 6 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref).
Abstract (Originalsprache)
Video Moment Retrieval (VMR) involves locating specific moments within a video based on natural language queries. However, existing VMR methods that employ various strategies for cross-modal alignment still face challenges such as limited understanding of fine-grained semantics, semantic overlap, and sparse constraints. To address these limitations, we propose a novel Concept Decomposition Transformer (CDTR) model for VMR. CDTR introduces a semantic concept decomposition module that disentangles video moments and sentence queries into concept representations, reflecting the relevance between various concepts and capturing fine-grained semantics which is crucial for cross-modal matching. These decomposed concept representations are then used as pseudo-labels, determined as positive or negative samples by adaptive concept-specific thresholds. Subsequently, fine-grained concept alignment is performed in video intra-modal and textual-visual cross-modal, aligning different conceptual components within features, enhancing the model's ability to distinguish fine-grained semantics, and alleviating issues related to semantic overlap and sparse constraints. Comprehensive experiments demonstrate the effectiveness of the CDTR, outperforming state-of-the-art methods on three widely used datasets: QVHighlights, Charades-STA, and TACoS.
Zitieren
APA
Ran, R., Wei, J., Cai, X., Guan, X., Zou, J., Yang, Y., & Shen, H. T. (2025). CDTR: Semantic Alignment for Video Moment Retrieval Using Concept Decomposition Transformer. Proceedings of the AAAI Conference on Artificial Intelligence, 39(6), 6684-6692. https://doi.org/10.1609/aaai.v39i6.32717
Vancouver
Ran R, Wei J, Cai X, Guan X, Zou J, Yang Y, et al. CDTR: Semantic Alignment for Video Moment Retrieval Using Concept Decomposition Transformer. Proceedings of the AAAI Conference on Artificial Intelligence. 2025;39(6):6684-6692. doi:10.1609/aaai.v39i6.32717
BibTeX
@article{Ran2025,
author = {Ran, Ran and Wei, Jiwei and Cai, Xiangyi and Guan, Xiang and Zou, Jie and Yang, Yang and Shen, Heng Tao},
title = {CDTR: Semantic Alignment for Video Moment Retrieval Using Concept Decomposition Transformer},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2025},
volume = {39},
number = {6},
pages = {6684--6692},
doi = {10.1609/aaai.v39i6.32717}
}
EUVIMED