# Human Action Adverb Recognition: ADHA Dataset and A Three-Stream Hybrid Model

arXiv: https://arxiv.org/abs/1802.01144 · HTML: https://mlsanity.com/paper/1802.01144/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Feb 2018.

## Built on by (most cited first, 4 of 4)

- [AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time](https://mlsanity.com/paper/2211.03375/) (2022)
- [Learning Action Changes by Measuring Verb-Adverb Textual Relationships](https://mlsanity.com/paper/2303.15086/) (2023)
- [How Do You Do It? Fine-Grained Action Understanding with Pseudo-Adverbs](https://mlsanity.com/paper/2203.12344/) (2022)
- [Reasoning over the Behaviour of Objects in Video-Clips for Adverb-Type Recognition](https://mlsanity.com/paper/2307.04132/) (2023)

## Abstract (arXiv)

We introduce the first benchmark for a new problem --- recognizing human action adverbs (HAA): "Adverbs Describing Human Actions" (ADHA). This is the first step for computer vision to change over from pattern recognition to real AI. We demonstrate some key features of ADHA: a semantically complete set of adverbs describing human actions, a set of common, describable human actions, and an exhaustive labeling of simultaneously emerging actions in each video. We commit an in-depth analysis on the implementation of current effective models in action recognition and image captioning on adverb recognition, and the results show that such methods are unsatisfactory. Moreover, we propose a novel three-stream hybrid model to deal the HAA problem, which achieves a better result.