SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2105.04823 · IJCAI · 2021

Learning Implicit Temporal Alignment for Few-shot Video Classification

Xuming He, Songyang Zhang, Jiale Zhou

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Few-shot video classification aims to learn new video categories with only a few labeled examples, alleviating the burden of costly annotation in realworld applications. However, it is particularly challenging to learn a class-invariant spatial-temporal representation in such a setting. To address this, we propose a novel matching-based few-shot learning strategy for video sequences in this work. Our main idea is to introduce an implicit temporal alignment for a video pair, capable of estimating the similarity between them in an accurate and robust manner. Moreover, we design an effective context encoding module to incorporate spatial and feature channel context, resulting in better modeling of intra-class variations. To train our model, we develop a multi-task loss for learning video matching, leading to video features with better generalization. Extensive experimental results on two challenging benchmarks, show that our method outperforms the prior arts with a sizable margin on Something-Something-V2 and competitive results on Kinetics.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2105.04823")
get_code_for_paper("2105.04823")
have("2105.04823")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2105.04823.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2105.04823.svg)](https://syntology.ai/paper/2105.04823)

Connect an agent — have() is free.