# DirecFormer: A Directed Attention in Transformer Approach to Robust Action Recognition

arXiv: https://arxiv.org/abs/2203.10233 · HTML: https://mlsanity.com/paper/2203.10233/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- Builds on 56 of its 80 references that are in the map.
- First posted on arXiv 19 Mar 2022.

## Builds on (most cited first, 30 of 56)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [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)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [Non-local Neural Networks](https://mlsanity.com/paper/1711.07971/) (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)
- [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)
- [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)
- [Two-Stream Convolutional Networks for Action Recognition in Videos](https://mlsanity.com/paper/1406.2199/) (2014)
- [SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size](https://mlsanity.com/paper/1602.07360/) (2016)
- [Temporal Segment Networks: Towards Good Practices for Deep Action Recognition](https://mlsanity.com/paper/1608.00859/) (2016)
- [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)
- [X3D: Expanding Architectures for Efficient Video Recognition](https://mlsanity.com/paper/2004.04730/) (2020)
- [Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification](https://mlsanity.com/paper/1712.04851/) (2017)
- [Long-term Recurrent Convolutional Networks for Visual Recognition and Description](https://mlsanity.com/paper/1411.4389/) (2014)
- [Domain Generalization by Solving Jigsaw Puzzles](https://mlsanity.com/paper/1903.06864/) (2019)
- [AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions](https://mlsanity.com/paper/1705.08421/) (2017)
- [VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text](https://mlsanity.com/paper/2104.11178/) (2021)
- [Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks](https://mlsanity.com/paper/1711.10305/) (2017)
- [Convolutional Two-Stream Network Fusion for Video Action Recognition](https://mlsanity.com/paper/1604.06573/) (2016)
- [A Short Note about Kinetics-600](https://mlsanity.com/paper/1808.01340/) (2018)

## Built on by (most cited first, 30 of 31)

- [Micron-BERT: BERT-based Facial Micro-Expression Recognition](https://mlsanity.com/paper/2304.03195/) (2023)
- [Video Test-Time Adaptation for Action Recognition](https://mlsanity.com/paper/2211.15393/) (2022)
- [Insect-Foundation: A Foundation Model and Large-scale 1M Dataset for Visual Insect Understanding](https://mlsanity.com/paper/2311.15206/) (2023)
- [Vision Transformers for Action Recognition: A Survey](https://mlsanity.com/paper/2209.05700/) (2022)
- [Swift Parameter-free Attention Network for Efficient Super-Resolution](https://mlsanity.com/paper/2311.12770/) (2023)
- [HIG: Hierarchical Interlacement Graph Approach to Scene Graph Generation in Video Understanding](https://mlsanity.com/paper/2312.03050/) (2023)
- [Frequency Guidance Matters: Skeletal Action Recognition by Frequency-Aware Mixed Transformer](https://mlsanity.com/paper/2407.12322/) (2024)
- [A Large-scale Study of Spatiotemporal Representation Learning with a New Benchmark on Action Recognition](https://mlsanity.com/paper/2303.13505/) (2023)
- [Cross-view Action Recognition Understanding From Exocentric to Egocentric Perspective](https://mlsanity.com/paper/2305.15699/) (2023)
- [OTAdapt: Optimal Transport-based Approach For Unsupervised Domain Adaptation](https://mlsanity.com/paper/2205.10738/) (2022)
- [Self-supervised Domain Adaptation in Crowd Counting](https://mlsanity.com/paper/2206.03431/) (2022)
- [CYCLO: Cyclic Graph Transformer Approach to Multi-Object Relationship Modeling in Aerial Videos](https://mlsanity.com/paper/2406.01029/) (2024)
- [DIFFVSGG: Diffusion-Driven Online Video Scene Graph Generation](https://mlsanity.com/paper/2503.13957/) (2025)
- [Meet JEANIE: a Similarity Measure for 3D Skeleton Sequences via Temporal-Viewpoint Alignment](https://mlsanity.com/paper/2402.04599/) (2024)
- [Insect-Foundation: A Foundation Model and Large Multimodal Dataset for Vision-Language Insect Understanding](https://mlsanity.com/paper/2502.09906/) (2025)
- [Video-based Contrastive Learning on Decision Trees: from Action Recognition to Autism Diagnosis](https://mlsanity.com/paper/2304.10073/) (2023)
- [Directed-Tokens: A Robust Multi-Modality Alignment Approach to Large Language-Vision Models](https://mlsanity.com/paper/2508.14264/) (2025)
- [Vec2Face-v2: Unveil Human Faces from their Blackbox Features via Attention-based Network in Face Recognition](https://mlsanity.com/paper/2209.04920/) (2022)
- [VIPriors 3: Visual Inductive Priors for Data-Efficient Deep Learning Challenges](https://mlsanity.com/paper/2305.19688/) (2023)
- [Deep video representation learning: a survey](https://mlsanity.com/paper/2405.06574/) (2024)
- [Deep Single Image Camera Calibration by Heatmap Regression to Recover Fisheye Images Under Manhattan World Assumption](https://mlsanity.com/paper/2303.17166/) (2023)
- [MANGO: Multimodal Attention-based Normalizing Flow Approach to Fusion Learning](https://mlsanity.com/paper/2508.10133/) (2025)
- [Multi-view knowledge distillation transformer for human action recognition](https://mlsanity.com/paper/2303.14358/) (2023)
- [Free-Form Composition Networks for Egocentric Action Recognition](https://mlsanity.com/paper/2307.06527/) (2023)
- [Video-Based Autism Detection with Deep Learning](https://mlsanity.com/paper/2402.16774/) (2024)
- [Element-Wise Attention Layers: an option for optimization](https://mlsanity.com/paper/2302.05488/) (2023)
- [Deep Neural Networks in Video Human Action Recognition: A Review](https://mlsanity.com/paper/2305.15692/) (2023)
- [Multi-view Action Recognition via Directed Gromov-Wasserstein Discrepancy](https://mlsanity.com/paper/2405.01337/) (2024)
- [A Novel Dataset for Video-Based Neurodivergent Classification Leveraging Extra-Stimulatory Behavior](https://mlsanity.com/paper/2409.04598/) (2024)
- [Data-Efficient Challenges in Visual Inductive Priors: A Retrospective](https://mlsanity.com/paper/2506.08612/) (2025)

## Abstract (arXiv)

Human action recognition has recently become one of the popular research topics in the computer vision community. Various 3D-CNN based methods have been presented to tackle both the spatial and temporal dimensions in the task of video action recognition with competitive results. However, these methods have suffered some fundamental limitations such as lack of robustness and generalization, e.g., how does the temporal ordering of video frames affect the recognition results? This work presents a novel end-to-end Transformer-based Directed Attention (DirecFormer) framework for robust action recognition. The method takes a simple but novel perspective of Transformer-based approach to understand the right order of sequence actions. Therefore, the contributions of this work are three-fold. Firstly, we introduce the problem of ordered temporal learning issues to the action recognition problem. Secondly, a new Directed Attention mechanism is introduced to understand and provide attentions to human actions in the right order. Thirdly, we introduce the conditional dependency in action sequence modeling that includes orders and classes. The proposed approach consistently achieves the state-of-the-art (SOTA) results compared with the recent action recognition methods, on three standard large-scale benchmarks, i.e. Jester, Kinetics-400 and Something-Something-V2.