تقرير
Inductive and Transductive Few-Shot Video Classification via Appearance and Temporal Alignments
العنوان: | Inductive and Transductive Few-Shot Video Classification via Appearance and Temporal Alignments |
---|---|
المؤلفون: | Nguyen, Khoi D., Tran, Quoc-Huy, Nguyen, Khoi, Hua, Binh-Son, Nguyen, Rang |
سنة النشر: | 2022 |
المجموعة: | Computer Science |
مصطلحات موضوعية: | Computer Science - Computer Vision and Pattern Recognition |
الوصف: | We present a novel method for few-shot video classification, which performs appearance and temporal alignments. In particular, given a pair of query and support videos, we conduct appearance alignment via frame-level feature matching to achieve the appearance similarity score between the videos, while utilizing temporal order-preserving priors for obtaining the temporal similarity score between the videos. Moreover, we introduce a few-shot video classification framework that leverages the above appearance and temporal similarity scores across multiple steps, namely prototype-based training and testing as well as inductive and transductive prototype refinement. To the best of our knowledge, our work is the first to explore transductive few-shot video classification. Extensive experiments on both Kinetics and Something-Something V2 datasets show that both appearance and temporal alignments are crucial for datasets with temporal order sensitivity such as Something-Something V2. Our approach achieves similar or better results than previous methods on both datasets. Our code is available at https://github.com/VinAIResearch/fsvc-ata. Comment: Accepted to ECCV 2022 |
نوع الوثيقة: | Working Paper |
URL الوصول: | http://arxiv.org/abs/2207.10785 |
رقم الأكسشن: | edsarx.2207.10785 |
قاعدة البيانات: | arXiv |
الوصف غير متاح. |