# Weakly-Supervised Multi-Person Action Recognition in 360circ Videos

arXiv: https://arxiv.org/abs/2002.03266 · HTML: https://mlsanity.com/paper/2002.03266/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Feb 2020.

## Built on by (most cited first, 4 of 4)

- [Applications of Deep Learning for Top-View Omnidirectional Imaging: A Survey](https://mlsanity.com/paper/2304.08193/) (2023)
- [ACT360: An Efficient 360-Degree Action Detection and Summarization Framework for Mission-Critical Training and Debriefing](https://mlsanity.com/paper/2503.12852/) (2025)
- [Discovering Multi-Label Actor-Action Association in a Weakly Supervised Setting](https://mlsanity.com/paper/2101.08567/) (2021)
- [GazeOnce360: Fisheye-Based 360deg Multi-Person Gaze Estimation with Global-Local Feature Fusion](https://mlsanity.com/paper/2603.17161/) (2026)

## Abstract (arXiv)

The recent development of commodity 360circ cameras have enabled a single video to capture an entire scene, which endows promising potentials in surveillance scenarios. However, research in omnidirectional video analysis has lagged behind the hardware advances. In this work, we address the important problem of action recognition in top-view 360circ videos. Due to the wide filed-of-view, 360circ videos usually capture multiple people performing actions at the same time. Furthermore, the appearance of people are deformed. The proposed framework first transforms omnidirectional videos into panoramic videos, then it extracts spatial-temporal features using region-based 3D CNNs for action recognition. We propose a weakly-supervised method based on multi-instance multi-label learning, which trains the model to recognize and localize multiple actions in a video using only video-level action labels as supervision. We perform experiments to quantitatively validate the efficacy of the proposed method and qualitatively demonstrate action localization results. To enable research in this direction, we introduce 360Action, the first omnidirectional video dataset for multi-person action recognition.