Saved in:
Bibliographic Details
Main Authors: Porto, Yannick, Martins, Renato, Chalumeau, Thomas, Demonceaux, Cedric
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.22695
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • Viewpoint change invariance and action temporal consistency are critical aspects for the effective deployment of human action detection of untrimmed videos. Existing appearance-based video detection methods often struggle with limited viewpoint diversity during training, while motion-based detection approaches frequently fail to model fine-grained temporal relationships across consecutive motion windows. This paper introduces a novel two-stage action detection approach designed to improve both view-invariance and global temporal coherence properties. In the first stage, we extract motion features from augmented virtual viewpoints, solely used at training. Then, the second stage introduces a new view-invariant, multi-scale temporal encoder based on selective state-space sequence modelling to aggregate information across viewpoints and time scales. Experiments on PKU-MMD and BABEL benchmarks demonstrate that this approach significantly outperforms state-of-the-art methods in all considered splits. Code and trained models are available at: https://icb-vision-ai.github.io/HydraView-TAD