# Multi-dataset Training of Transformers for Robust Action Recognition

arXiv: https://arxiv.org/abs/2209.12362 · HTML: https://mlsanity.com/paper/2209.12362/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 45 of its 85 references that are in the map.
- First posted on arXiv 26 Sep 2022.

## Builds on (most cited first, 30 of 45)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [The Kinetics Human Action Video Dataset](https://mlsanity.com/paper/1705.06950/) (2017)
- [SlowFast Networks for Video Recognition](https://mlsanity.com/paper/1812.03982/) (2018)
- [Barlow Twins: Self-Supervised Learning via Redundancy Reduction](https://mlsanity.com/paper/2103.03230/) (2021)
- [Is Space-Time Attention All You Need for Video Understanding?](https://mlsanity.com/paper/2102.05095/) (2021)
- [ViViT: A Video Vision Transformer](https://mlsanity.com/paper/2103.15691/) (2021)
- [Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics](https://mlsanity.com/paper/1705.07115/) (2017)
- [Adversarial Discriminative Domain Adaptation](https://mlsanity.com/paper/1702.05464/) (2017)
- [A Closer Look at Spatiotemporal Convolutions for Action Recognition](https://mlsanity.com/paper/1711.11248/) (2017)
- [The "something something" video database for learning and evaluating visual common sense](https://mlsanity.com/paper/1706.04261/) (2017)
- [Video Swin Transformer](https://mlsanity.com/paper/2106.13230/) (2021)
- [VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning](https://mlsanity.com/paper/2105.04906/) (2021)
- [Scaling Vision Transformers](https://mlsanity.com/paper/2106.04560/) (2021)
- [HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips](https://mlsanity.com/paper/1906.03327/) (2019)
- [Multiscale Vision Transformers](https://mlsanity.com/paper/2104.11227/) (2021)
- [TSM: Temporal Shift Module for Efficient Video Understanding](https://mlsanity.com/paper/1811.08383/) (2018)
- [Domain Generalization: A Survey](https://mlsanity.com/paper/2103.02503/) (2021)
- [X3D: Expanding Architectures for Efficient Video Recognition](https://mlsanity.com/paper/2004.04730/) (2020)
- [MViTv2: Improved Multiscale Vision Transformers for Classification and Detection](https://mlsanity.com/paper/2112.01526/) (2021)
- [VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text](https://mlsanity.com/paper/2104.11178/) (2021)
- [A Short Note on the Kinetics-700 Human Action Dataset](https://mlsanity.com/paper/1907.06987/) (2019)
- [Moments in Time Dataset: one million videos for event understanding](https://mlsanity.com/paper/1801.03150/) (2018)
- [Temporal Pyramid Network for Action Recognition](https://mlsanity.com/paper/2004.03548/) (2020)
- [Multiview Transformers for Video Recognition](https://mlsanity.com/paper/2201.04288/) (2022)
- [MoViNets: Mobile Video Networks for Efficient Video Recognition](https://mlsanity.com/paper/2103.11511/) (2021)

## Built on by (most cited first, 10 of 10)

- [UniTraj: A Unified Framework for Scalable Vehicle Trajectory Prediction](https://mlsanity.com/paper/2403.15098/) (2024)
- [Multi-Dataset Co-Training with Sharpness-Aware Optimization for Audio Anti-spoofing](https://mlsanity.com/paper/2305.19953/) (2023)
- [ActionHub: A Large-scale Action Video Description Dataset for Zero-shot Action Recognition](https://mlsanity.com/paper/2401.11654/) (2024)
- [Scaling Multi-Camera 3D Object Detection through Weak-to-Strong Eliciting](https://mlsanity.com/paper/2404.06700/) (2024)
- [Advancing Human Action Recognition with Foundation Models trained on Unlabeled Public Videos](https://mlsanity.com/paper/2402.08875/) (2024)
- [CHASE: Learning Convex Hull Adaptive Shift for Skeleton-based Multi-Entity Action Recognition](https://mlsanity.com/paper/2410.07153/) (2024)
- [TMT-VIS: Taxonomy-aware Multi-dataset Joint Training for Video Instance Segmentation](https://mlsanity.com/paper/2312.06630/) (2023)
- [Spatial-Temporal Alignment Network for Action Recognition](https://mlsanity.com/paper/2308.09897/) (2023)
- [AMA-SAM: Adversarial Multi-Domain Alignment of Segment Anything Model for High-Fidelity Histology Nuclei Segmentation](https://mlsanity.com/paper/2503.21695/) (2025)
- [Separating Shared and Domain-Specific LoRAs for Multi-Domain Learning](https://mlsanity.com/paper/2508.02978/) (2025)

## Abstract (arXiv)

We study the task of robust feature representations, aiming to generalize well on multiple datasets for action recognition. We build our method on Transformers for its efficacy. Although we have witnessed great progress for video action recognition in the past decade, it remains challenging yet valuable how to train a single model that can perform well across multiple datasets. Here, we propose a novel multi-dataset training paradigm, MultiTrain, with the design of two new loss terms, namely informative loss and projection loss, aiming to learn robust representations for action recognition. In particular, the informative loss maximizes the expressiveness of the feature embedding while the projection loss for each dataset mines the intrinsic relations between classes across datasets. We verify the effectiveness of our method on five challenging datasets, Kinetics-400, Kinetics-700, Moments-in-Time, Activitynet and Something-something-v2 datasets. Extensive experimental results show that our method can consistently improve state-of-the-art performance. Code and models are released.