Temporal Alignment Prediction for Few-Shot Video Classification
This addresses the challenge of video classification with limited labeled data, which is incremental as it builds on sequence similarity learning for improved performance.
The paper tackles the problem of learning discriminative feature representations for few-shot video classification by proposing Temporal Alignment Prediction (TAP), which predicts alignment scores between temporal positions in video pairs, and shows superiority over state-of-the-art methods on benchmarks like Kinetics and Something-Something V2.
The goal of few-shot video classification is to learn a classification model with good generalization ability when trained with only a few labeled videos. However, it is difficult to learn discriminative feature representations for videos in such a setting. In this paper, we propose Temporal Alignment Prediction (TAP) based on sequence similarity learning for few-shot video classification. In order to obtain the similarity of a pair of videos, we predict the alignment scores between all pairs of temporal positions in the two videos with the temporal alignment prediction function. Besides, the inputs to this function are also equipped with the context information in the temporal domain. We evaluate TAP on two video classification benchmarks including Kinetics and Something-Something V2. The experimental results verify the effectiveness of TAP and show its superiority over state-of-the-art methods.