其他分享
首页 > 其他分享> > 视频理解领域小样本学习调研报告

视频理解领域小样本学习调研报告

作者:互联网

视频理解领域小样本学习调研报告

标签(空格分隔): 学习笔记


文章目录

0 前言

1. 分类

Action Genome(li Feifei2019)提出的分类:

ProtoGAN提出的分类

2. 常用数据集总结

数据集动作类别数总视频数train:val:test 或train:testSOTA
UCF1011011332051:5095.5%(by AMeFu-Net)
HMDB5151676626:2575.5% (by AMeFu-Net)
Olympic-Sports167838:886.3%(by ProtoGAN)
miniMIT200200*550120:40:4056.7%(by ARN)
小样本版Kinetics100100*10064:12:2486.8%(by AMeFu-Net)
小样本版Something-Something V2100100*10064:12:2452.3%(by OTAM)

结论

3. 开源代码

TRX

Few-shot-action-recognition

4. 论文简述

4.1 ProtoGAN: Towards Few Shot Learning for Action Recognition

4.2 A Generative Approach to Zero-Shot and Few-Shot Action Recognition

4.3 TARN: Temporal Attentive Relation Network for Few-Shot and Zero-Shot Action Recognition

4.4 CMN: Compound memory networks for few-shot video classification.

4.5 OTAM: Few-shot video classification via temporal alignment

4.6 ARN: Few-shot Action Recognition with Permutation-invariant Attention

4.7 AMeFu-Net:Depth Guided Adaptive Meta-Fusion Network for Few-shot Video Recognition

标签:视频,Shot,样本,Few,Action,shot,Recognition,调研
来源: https://blog.csdn.net/qq_39213580/article/details/115057697