# IntegralAction: Pose-driven Feature Integration for Robust Human Action Recognition in Videos

arXiv: https://arxiv.org/abs/2007.06317 · HTML: https://mlsanity.com/paper/2007.06317/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Jul 2020.

## Built on by (most cited first, 12 of 12)

- [Relational Context Learning for Human-Object Interaction Detection](https://mlsanity.com/paper/2304.04997/) (2023)
- [Learning Self-Similarity in Space and Time as Generalized Motion for Video Action Recognition](https://mlsanity.com/paper/2102.07092/) (2021)
- [EZ-HOI: VLM Adaptation via Guided Prompt Learning for Zero-Shot HOI Detection](https://mlsanity.com/paper/2410.23904/) (2024)
- [Unified Keypoint-based Action Recognition Framework via Structured Keypoint Pooling](https://mlsanity.com/paper/2303.15270/) (2023)
- [Multimodal Cross-Domain Few-Shot Learning for Egocentric Action Recognition](https://mlsanity.com/paper/2405.19917/) (2024)
- [NTU-X: An Enhanced Large-scale Dataset for Improving Pose-based Recognition of Subtle Human Actions](https://mlsanity.com/paper/2101.11529/) (2021)
- [Human Part-wise 3D Motion Context Learning for Sign Language Recognition](https://mlsanity.com/paper/2308.09305/) (2023)
- [Extreme Image Transformations Affect Humans and Machines Differently](https://mlsanity.com/paper/2212.13967/) (2022)
- [Bottom-up approaches for multi-person pose estimation and it's applications: A brief review](https://mlsanity.com/paper/2112.11834/) (2021)
- [EPAM-Net: An Efficient Pose-driven Attention-guided Multimodal Network for Video Action Recognition](https://mlsanity.com/paper/2408.05421/) (2024)
- [Zero-shot HOI Detection with MLLM-based Detector-agnostic Interaction Recognition](https://mlsanity.com/paper/2602.15124/) (2026)
- [Identifying Ethical Biases in Action Recognition Models](https://mlsanity.com/paper/2604.17971/) (2026)

## Abstract (arXiv)

Most current action recognition methods heavily rely on appearance information by taking an RGB sequence of entire image regions as input. While being effective in exploiting contextual information around humans, e.g., human appearance and scene category, they are easily fooled by out-of-context action videos where the contexts do not exactly match with target actions. In contrast, pose-based methods, which take a sequence of human skeletons only as input, suffer from inaccurate pose estimation or ambiguity of human pose per se. Integrating these two approaches has turned out to be non-trivial; training a model with both appearance and pose ends up with a strong bias towards appearance and does not generalize well to unseen videos. To address this problem, we propose to learn pose-driven feature integration that dynamically combines appearance and pose streams by observing pose features on the fly. The main idea is to let the pose stream decide how much and which appearance information is used in integration based on whether the given pose information is reliable or not. We show that the proposed IntegralAction achieves highly robust performance across in-context and out-of-context action video datasets. The codes are available in https://github.com/mks0601/IntegralAction_RELEASE.