DeepAI AI Chat
Log In Sign Up

Untrimmed Video Classification for Activity Detection: submission to ActivityNet Challenge

by   Gurkirt Singh, et al.
Oxford Brookes University

Current state-of-the-art human activity recognition is focused on the classification of temporally trimmed videos in which only one action occurs per frame. We propose a simple, yet effective, method for the temporal detection of activities in temporally untrimmed videos with the help of untrimmed classification. Firstly, our model predicts the top k labels for each untrimmed video by analysing global video-level features. Secondly, frame-level binary classification is combined with dynamic programming to generate the temporally trimmed activity proposals. Finally, each proposal is assigned a label based on the global label, and scored with the score of the temporal activity proposal and the global score. Ultimately, we show that untrimmed video classification models can be used as stepping stone for temporal detection.


page 1

page 2

page 3

page 4


Spatio-temporal Human Action Localisation and Instance Segmentation in Temporally Untrimmed Videos

Current state-of-the-art human action recognition is focused on the clas...

Temporal Activity Detection in Untrimmed Videos with Recurrent Neural Networks

This thesis explore different approaches using Convolutional and Recurre...

Spatio-Temporal Action Detection with Cascade Proposal and Location Anticipation

In this work, we address the problem of spatio-temporal action detection...

Is there progress in activity progress prediction?

Activity progress prediction aims to estimate what percentage of an acti...

Deep Adaptive Temporal Pooling for Activity Recognition

Deep neural networks have recently achieved competitive accuracy for hum...

Activity Graph Transformer for Temporal Action Localization

We introduce Activity Graph Transformer, an end-to-end learnable model f...

Similarity R-C3D for Few-shot Temporal Activity Detection

Many activities of interest are rare events, with only a few labeled exa...