# Part-level Action Parsing via a Pose-guided Coarse-to-Fine Framework

Source: [Part-level Action Parsing via a Pose-guided Coarse-to-Fine Framework](<https://www.sota2.com/research/paper/68fa6d581e209131cea39556>)

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

Data updated: 2025-10-26T00:32:23.745Z

Authors: Xiaodong Chen, Xinchen Liu, Wu Liu, Kun Liu, Dong Wu, Yongdong Zhang, Tao Mei

Published: 2022-03-09T01:30:57.000Z

## Abstract

Action recognition from videos, i.e., classifying a video into one of the pre-defined action types, has been a popular topic in the communities of artificial intelligence, multimedia, and signal processing. However, existing methods usually consider an input video as a whole and learn models, e.g., Convolutional Neural Networks (CNNs), with coarse video-level class labels. These methods can only output an action class for the video, but cannot provide fine-grained and explainable cues to answer why the video shows a specific action. Therefore, researchers start to focus on a new task, Part-level Action Parsing (PAP), which aims to not only predict the video-level action but also recognize the frame-level fine-grained actions or interactions of body parts for each person in the video. To this end, we propose a coarse-to-fine framework for this challenging task. In particular, our framework first predicts the video-level class of the input video, then localizes the body parts and predicts the part-level action. Moreover, to balance the accuracy and computation in part-level action parsing, we propose to recognize the part-level actions by segment-level features. Furthermore, to overcome the ambiguity of body parts, we propose a pose-guided positional embedding method to accurately localize body parts. Through comprehensive experiments on a large-scale dataset, i.e., Kinetics-TPS, our framework achieves state-of-the-art performance and outperforms existing methods over a 31.10% ROC score.

## 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.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2203.04476>)

[PDF](<https://arxiv.org/pdf/2203.04476.pdf>)
