Few-Shot Video Classification via Temporal Alignment

06/27/2019
by   Kaidi Cao, et al.
5

There is a growing interest in learning a model which could recognize novel classes with only a few labeled examples. In this paper, we propose Temporal Alignment Module (TAM), a novel few-shot learning framework that can learn to classify a previous unseen video. While most previous works neglect long-term temporal ordering information, our proposed model explicitly leverages the temporal ordering information in video data through temporal alignment. This leads to strong data-efficiency for few-shot learning. In concrete, TAM calculates the distance value of query video with respect to novel class proxies by averaging the per frame distances along its alignment path. We introduce continuous relaxation to TAM so the model can be learned in an end-to-end fashion to directly optimize the few-shot learning objective. We evaluate TAM on two challenging real-world datasets, Kinetics and Something-Something-V2, and show that our model leads to significant improvement of few-shot video classification over a wide range of competitive baselines.

READ FULL TEXT

page 1

page 3

page 7

research
05/11/2021

Learning Implicit Temporal Alignment for Few-shot Video Classification

Few-shot video classification aims to learn new video categories with on...
research
07/26/2021

Temporal Alignment Prediction for Few-Shot Video Classification

The goal of few-shot video classification is to learn a classification m...
research
10/13/2020

Few-shot Action Recognition with Implicit Temporal Alignment and Pair Similarity Optimization

Few-shot learning aims to recognize instances from novel classes with fe...
research
07/09/2020

Generalized Many-Way Few-Shot Video Classification

Few-shot learning methods operate in low data regimes. The aim is to lea...
research
09/04/2015

Learning Temporal Alignment Uncertainty for Efficient Event Detection

In this paper we tackle the problem of efficient video event detection. ...
research
03/11/2019

Alignment Based Matching Networks for One-Shot Classification and Open-Set Recognition

Deep learning for object classification relies heavily on convolutional ...
research
03/03/2020

Rethinking Zero-shot Video Classification: End-to-end Training for Realistic Applications

Trained on large datasets, deep learning (DL) can accurately classify vi...

Please sign up or login with your details

Forgot password? Click here to reset