# Visual Attribute-augmented Three-dimensional Convolutional Neural Network for Enhanced Human Action Recognition

Source: [Visual Attribute-augmented Three-dimensional Convolutional Neural Network for Enhanced Human Action Recognition](<https://www.sota2.com/research/paper/68fa644c1e209131cea03d2e>)

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

Data updated: 2025-10-28T13:56:35.711Z

Authors: Yunfeng Wang, Wengang Zhou, Qilin Zhang, Houqiang Li

Published: 2018-05-08T07:09:12.000Z

## Abstract

Visual attributes in individual video frames, such as the presence of characteristic objects and scenes, offer substantial information for action recognition in videos. With individual 2D video frame as input, visual attributes extraction could be achieved effectively and efficiently with more sophisticated convolutional neural network than current 3D CNNs with spatio-temporal filters, thanks to fewer parameters in 2D CNNs. In this paper, the integration of visual attributes (including detection, encoding and classification) into multi-stream 3D CNN is proposed for action recognition in trimmed videos, with the proposed visual Attribute-augmented 3D CNN (A3D) framework. The visual attribute pipeline includes an object detection network, an attributes encoding network and a classification network. Our proposed A3D framework achieves state-of-the-art performance on both the HMDB51 and the UCF101 datasets.

## 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/1805.02860>)

[PDF](<https://arxiv.org/pdf/1805.02860.pdf>)
