# A Multi-viewpoint Outdoor Dataset for Human Action Recognition

arXiv: https://arxiv.org/abs/2110.04119 · HTML: https://mlsanity.com/paper/2110.04119/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 41 references that are in the map.
- First posted on arXiv 7 Oct 2021.

## Builds on (most cited first, 11 of 11)

- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [The Kinetics Human Action Video Dataset](https://mlsanity.com/paper/1705.06950/) (2017)
- [Convolutional Two-Stream Network Fusion for Video Action Recognition](https://mlsanity.com/paper/1604.06573/) (2016)
- [YouTube-8M: A Large-Scale Video Classification Benchmark](https://mlsanity.com/paper/1609.08675/) (2016)
- [CityPersons: A Diverse Dataset for Pedestrian Detection](https://mlsanity.com/paper/1702.05693/) (2017)
- [Return of the Devil in the Details: Delving Deep into Convolutional Nets](https://mlsanity.com/paper/1405.3531/) (2014)
- [P-CNN: Pose-based CNN Features for Action Recognition](https://mlsanity.com/paper/1506.03607/) (2015)
- [Finding Action Tubes](https://mlsanity.com/paper/1411.6031/) (2014)
- [Okutama-Action: An Aerial View Video Dataset for Concurrent Human Action Detection](https://mlsanity.com/paper/1706.03038/) (2017)
- [Review of Action Recognition and Detection Methods](https://mlsanity.com/paper/1610.06906/) (2016)
- [Non-Linear Temporal Subspace Representations for Activity Recognition](https://mlsanity.com/paper/1803.11064/) (2018)

## Built on by (most cited first, 11 of 11)

- [BEAT: A Large-Scale Semantic and Emotional Multi-Modal Dataset for Conversational Gestures Synthesis](https://mlsanity.com/paper/2203.05297/) (2022)
- [UAVs Meet LLMs: Overviews and Perspectives Toward Agentic Low-Altitude Mobility](https://mlsanity.com/paper/2501.02341/) (2025)
- [The State of Aerial Surveillance: A Survey](https://mlsanity.com/paper/2201.03080/) (2022)
- [A Large-scale Study of Spatiotemporal Representation Learning with a New Benchmark on Action Recognition](https://mlsanity.com/paper/2303.13505/) (2023)
- [AZTR: Aerial Video Action Recognition with Auto Zoom and Temporal Reasoning](https://mlsanity.com/paper/2303.01589/) (2023)
- [PMI Sampler: Patch Similarity Guided Frame Selection for Aerial Action Recognition](https://mlsanity.com/paper/2304.06866/) (2023)
- [MITFAS: Mutual Information based Temporal Feature Alignment and Sampling for Aerial Video Action Recognition](https://mlsanity.com/paper/2303.02575/) (2023)
- [DroneAttention: Sparse Weighted Temporal Attention for Drone-Camera Based Activity Recognition](https://mlsanity.com/paper/2212.03384/) (2022)
- [Enhancing Human Action Recognition and Violence Detection Through Deep Learning Audiovisual Fusion](https://mlsanity.com/paper/2408.02033/) (2024)
- [Beyond the Horizon: Decoupling Multi-View UAV Action Recognition via Partial Order Transfer](https://mlsanity.com/paper/2504.20530/) (2025)
- [SWTF: Sparse Weighted Temporal Fusion for Drone-Based Activity Recognition](https://mlsanity.com/paper/2211.05531/) (2022)

## Abstract (arXiv)

Advancements in deep neural networks have contributed to near perfect results for many computer vision problems such as object recognition, face recognition and pose estimation. However, human action recognition is still far from human-level performance. Owing to the articulated nature of the human body, it is challenging to detect an action from multiple viewpoints, particularly from an aerial viewpoint. This is further compounded by a scarcity of datasets that cover multiple viewpoints of actions. To fill this gap and enable research in wider application areas, we present a multi-viewpoint outdoor action recognition dataset collected from YouTube and our own drone. The dataset consists of 20 dynamic human action classes, 2324 video clips and 503086 frames. All videos are cropped and resized to 720x720 without distorting the original aspect ratio of the human subjects in videos. This dataset should be useful to many research areas including action recognition, surveillance and situational awareness. We evaluated the dataset with a two-stream CNN architecture coupled with a recently proposed temporal pooling scheme called kernelized rank pooling that produces nonlinear feature subspace representations. The overall baseline action recognition accuracy is 74.0%.