Bias-Conflict Sample Synthesis and Adversarial Removal Debias Strategy for Temporal Sentence Grounding in Video
Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (5) · 4533-4541
DOI: 10.1609/aaai.v38i5.28252 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Zhaobo Qi und 5 weiteren Autor:innen. Die Arbeit wurde bisher 23-mal zitiert (Crossref).
Abstract (Originalsprache)
Temporal Sentence Grounding in Video (TSGV) is troubled by dataset bias issue, which is caused by the uneven temporal distribution of the target moments for samples with similar semantic components in input videos or query texts. Existing methods resort to utilizing prior knowledge about bias to artificially break this uneven distribution, which only removes a limited amount of significant language biases. In this work, we propose the bias-conflict sample synthesis and adversarial removal debias strategy (BSSARD), which dynamically generates bias-conflict samples by explicitly leveraging potentially spurious correlations between single-modality features and the temporal position of the target moments. Through adversarial training, its bias generators continuously introduce biases and generate bias-conflict samples to deceive its grounding model. Meanwhile, the grounding model continuously eliminates the introduced biases, which requires it to model multi-modality alignment information. BSSARD will cover most kinds of coupling relationships and disrupt language and visual biases simultaneously. Extensive experiments on Charades-CD and ActivityNet-CD demonstrate the promising debiasing capability of BSSARD. Source codes are available at https://github.com/qzhb/BSSARD.
Zitieren
APA
Qi, Z., Yuan, Y., Ruan, X., Wang, S., Zhang, W., & Huang, Q. (2024). Bias-Conflict Sample Synthesis and Adversarial Removal Debias Strategy for Temporal Sentence Grounding in Video. Proceedings of the AAAI Conference on Artificial Intelligence, 38(5), 4533-4541. https://doi.org/10.1609/aaai.v38i5.28252
Vancouver
Qi Z, Yuan Y, Ruan X, Wang S, Zhang W, Huang Q. Bias-Conflict Sample Synthesis and Adversarial Removal Debias Strategy for Temporal Sentence Grounding in Video. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(5):4533-4541. doi:10.1609/aaai.v38i5.28252
BibTeX
@article{Qi2024,
author = {Qi, Zhaobo and Yuan, Yibo and Ruan, Xiaowen and Wang, Shuhui and Zhang, Weigang and Huang, Qingming},
title = {Bias-Conflict Sample Synthesis and Adversarial Removal Debias Strategy for Temporal Sentence Grounding in Video},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2024},
volume = {38},
number = {5},
pages = {4533--4541},
doi = {10.1609/aaai.v38i5.28252}
}
EUVIMED