English

A Proposal-Based Solution to Spatio-Temporal Action Detection in Untrimmed Videos

Computer Vision and Pattern Recognition 2018-11-26 v2

Abstract

Existing approaches for spatio-temporal action detection in videos are limited by the spatial extent and temporal duration of the actions. In this paper, we present a modular system for spatio-temporal action detection in untrimmed security videos. We propose a two stage approach. The first stage generates dense spatio-temporal proposals using hierarchical clustering and temporal jittering techniques on frame-wise object detections. The second stage is a Temporal Refinement I3D (TRI-3D) network that performs action classification and temporal refinement on the generated proposals. The object detection-based proposal generation step helps in detecting actions occurring in a small spatial region of a video frame, while temporal jittering and refinement helps in detecting actions of variable lengths. Experimental results on the spatio-temporal action detection dataset - DIVA - show the effectiveness of our system. For comparison, the performance of our system is also evaluated on the THUMOS14 temporal action detection dataset.

Keywords

Cite

@article{arxiv.1811.08496,
  title  = {A Proposal-Based Solution to Spatio-Temporal Action Detection in Untrimmed Videos},
  author = {Joshua Gleason and Rajeev Ranjan and Steven Schwarcz and Carlos D. Castillo and Jun-Chen Cheng and Rama Chellappa},
  journal= {arXiv preprint arXiv:1811.08496},
  year   = {2018}
}

Comments

To appear in IEEE Winter Conference on Applications of Computer Vision (WACV) 2019

R2 v1 2026-06-23T05:22:47.083Z