# MVAFormer: RGB-based Multi-View Spatio-Temporal Action Recognition with Transformer

arXiv: https://arxiv.org/abs/2511.02473 · HTML: https://mlsanity.com/paper/2511.02473/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 26 references that are in the map.
- First posted on arXiv 4 Nov 2025.

## Builds on (most cited first, 19 of 19)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [SlowFast Networks for Video Recognition](https://mlsanity.com/paper/1812.03982/) (2018)
- [VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training](https://mlsanity.com/paper/2203.12602/) (2022)
- [The "something something" video database for learning and evaluating visual common sense](https://mlsanity.com/paper/1706.04261/) (2017)
- [VideoBERT: A Joint Model for Video and Language Representation Learning](https://mlsanity.com/paper/1904.01766/) (2019)
- [NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis](https://mlsanity.com/paper/1604.02808/) (2016)
- [DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queries](https://mlsanity.com/paper/2110.06922/) (2021)
- [AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions](https://mlsanity.com/paper/1705.08421/) (2017)
- [Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2107.12213/) (2021)
- [Actor-Context-Actor Relation Network for Spatio-Temporal Action Localization](https://mlsanity.com/paper/2006.07976/) (2020)
- [A Comprehensive Study of Deep Video Action Recognition](https://mlsanity.com/paper/2012.06567/) (2020)
- [The AVA-Kinetics Localized Human Actions Video Dataset](https://mlsanity.com/paper/2005.00214/) (2020)
- [Multiview Detection with Feature Perspective Transformation](https://mlsanity.com/paper/2007.07247/) (2020)
- [Multi-view and Multi-modal Event Detection Utilizing Transformer-based Multi-sensor fusion](https://mlsanity.com/paper/2202.09124/) (2022)
- [Relation Modeling in Spatio-Temporal Action Localization](https://mlsanity.com/paper/2106.08061/) (2021)

## Built on by (most cited first, 1 of 1)

- [Beyond Motion Pattern: An Empirical Study of Physical Forces for Human Motion Understanding](https://mlsanity.com/paper/2512.20451/) (2025)

## Abstract (arXiv)

Multi-view action recognition aims to recognize human actions using multiple camera views and deals with occlusion caused by obstacles or crowds. In this task, cooperation among views, which generates a joint representation by combining multiple views, is vital. Previous studies have explored promising cooperation methods for improving performance. However, since their methods focus only on the task setting of recognizing a single action from an entire video, they are not applicable to the recently popular spatio-temporal action recognition~(STAR) setting, in which each person's action is recognized sequentially. To address this problem, this paper proposes a multi-view action recognition method for the STAR setting, called MVAFormer. In MVAFormer, we introduce a novel transformer-based cooperation module among views. In contrast to previous studies, which utilize embedding vectors with lost spatial information, our module utilizes the feature map for effective cooperation in the STAR setting, which preserves the spatial information. Furthermore, in our module, we divide the self-attention for the same and different views to model the relationship between multiple views effectively. The results of experiments using a newly collected dataset demonstrate that MVAFormer outperforms the comparison baselines by approximately 4.4 points on the F-measure.