Revisiting Few-shot Activity Detection with Class Similarity Control

03/31/2020
by   Huijuan Xu, et al.
28

Many interesting events in the real world are rare making preannotated machine learning ready videos a rarity in consequence. Thus, temporal activity detection models that are able to learn from a few examples are desirable. In this paper, we present a conceptually simple and general yet novel framework for few-shot temporal activity detection based on proposal regression which detects the start and end time of the activities in untrimmed videos. Our model is end-to-end trainable, takes into account the frame rate differences between few-shot activities and untrimmed test videos, and can benefit from additional few-shot examples. We experiment on three large scale benchmarks for temporal activity detection (ActivityNet1.2, ActivityNet1.3 and THUMOS14 datasets) in a few-shot setting. We also study the effect on performance of different amount of overlap with activities used to pretrain the video classification backbone and propose corrective measures for future works in this domain. Our code will be made available.

READ FULL TEXT
research
12/25/2018

Similarity R-C3D for Few-shot Temporal Activity Detection

Many activities of interest are rare events, with only a few labeled exa...
research
03/12/2020

ZSTAD: Zero-Shot Temporal Activity Detection

An integral part of video analysis and surveillance is temporal activity...
research
07/21/2018

S3D: Single Shot multi-Span Detector via Fully 3D Convolutional Networks

In this paper, we present a novel Single Shot multi-Span Detector for te...
research
08/10/2023

Is there progress in activity progress prediction?

Activity progress prediction aims to estimate what percentage of an acti...
research
03/08/2017

A Pursuit of Temporal Accuracy in General Activity Detection

Detecting activities in untrimmed videos is an important but challenging...
research
10/28/2020

Toyota Smarthome Untrimmed: Real-World Untrimmed Videos for Activity Detection

This work aims at building a large scale dataset with daily-living activ...
research
08/08/2020

A Unified Framework for Shot Type Classification Based on Subject Centric Lens

Shots are key narrative elements of various videos, e.g. movies, TV seri...

Please sign up or login with your details

Forgot password? Click here to reset