Foundation Model and Temporal Priors-guided Transductive Few-shot Action Recognition
Bach Vu, Hoang Nguyen, Quang Minh Nguyen, Duong Le, Hieu Pham, Phi Le Nguyen, Lam M. Nguyen
Abstract
Dynamic Time Warping (DTW) is a widely used metric for time series matching. However, when applied to few-shot action recognition (FSAR), DTW often encounters the "identical matching" issue, where multiple frames from one video are matched to a single frame from another. To address this, we introduce FTP-FSAR, a novel metric-based FSAR approach designed to mitigate this challenge. FTP-FSAR proposes an innovative alignment metric that incorporates temporal priors, guiding the matching process by encouraging the alignment of frames with similar temporal progression, thus improving the accuracy of frame matching. Additionally, FTP-FSAR integrates a dual framework, combining a foundation model with transductive learning to optimize feature extraction. Extensive experiments across multiple datasets demonstrate that FTP-FSAR outperforms existing methods, achieving the best results in 3 out of 4 benchmarks across 1-shot, 3-shot, and 5-shot settings, with performance improvements of up to 4.5%.
BibTeX
@inproceedings{icassp2025_foundationmodela,
title = {Foundation Model and Temporal Priors-guided Transductive Few-shot Action Recognition},
author = {Bach Vu and Hoang Nguyen and Quang Minh Nguyen and Duong Le and Hieu Pham and Phi Le Nguyen and Lam M. Nguyen},
booktitle = {ICASSP 2025},
year = {2025}
}