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

Source: [DirecFormer: A Directed Attention in Transformer Approach to Robust Action Recognition](<https://www.sota2.com/research/paper/68fa6c141e209131cea31fed>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-04T03:40:49.187Z

Authors: Thanh-Dat Truong, Quoc-Huy Bui, Chi Nhan Duong, Han-Seok Seo, Son Lam Phung, Xin Li, Khoa Luu

Published: 2022-03-19T03:41:48.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Action Recognition on Something-Something V2](<https://www.sota2.com/research/sota/action-recognition-on-something-something-v2.md>): Action Recognition; Something-Something v2; Top-1 Accuracy: 64.94.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2203.10233>)

[PDF](<https://arxiv.org/pdf/2203.10233.pdf>)

[Implementation](<https://github.com/uark-cviu/DirecFormer>)
