Similarity R-C3D for Few-shot Temporal Activity Detection

by   Huijuan Xu, et al.
Boston University
berkeley college

Many activities of interest are rare events, with only a few labeled examples available. Therefore models for temporal activity detection which 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 which detects the start and end time of the few-shot input activities in an untrimmed video. Our model is end-to-end trainable and can benefit from more few-shot examples. At test time, each proposal is assigned the label of the few-shot activity class corresponding to the maximum similarity score. Our Similarity R-C3D method outperforms previous work on three large-scale benchmarks for temporal activity detection (THUMOS14, ActivityNet1.2, and ActivityNet1.3 datasets) in the few-shot setting. Our code will be made available.


page 1

page 3

page 7

page 8


Revisiting Few-shot Activity Detection with Class Similarity Control

Many interesting events in the real world are rare making preannotated m...

ZSTAD: Zero-Shot Temporal Activity Detection

An integral part of video analysis and surveillance is temporal activity...

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...

R-C3D: Region Convolutional 3D Network for Temporal Activity Detection

We address the problem of activity detection in continuous, untrimmed vi...

Untrimmed Video Classification for Activity Detection: submission to ActivityNet Challenge

Current state-of-the-art human activity recognition is focused on the cl...

FS-DETR: Few-Shot DEtection TRansformer with prompting and without re-training

This paper is on Few-Shot Object Detection (FSOD), where given a few tem...

Activity Detection with Latent Sub-event Hierarchy Learning

In this paper, we introduce a new convolutional layer named the Temporal...

Please sign up or login with your details

Forgot password? Click here to reset