arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1803.06962cs.CV
收藏

无障碍:动作分类中的特征提取

Featureless: Bypassing feature extraction in action categorization

Intelligent Sensory Information SystemsUniversity of Amsterdam(阿姆斯特丹大学智能感知信息系统);Computer Vision LabDelft University of Technology(代尔夫特理工大学计算机视觉实验室)

Silvia L. Pintea, Pascal S. Mettes, Jan C. van Gemert, Arnold W. M. Smeulders

摘要:

该方法引入了一种有效的学习动作类别的方式,而不需要特征估计。该方法从低级值开始,与成功的CNN方法类似。然而,我们学习从原始视频数据中预测特定的视频表示,而不是提取一般的图像特征。这种方法的好处是,在相同的计算费用,它可以预测二维视频表示以及三维的基础上运动。所提出的模型依赖于判别Waldboost,我们提高到多类制定学习视频表示的目的。在UCF 11动作识别数据集上测试了该方法的适用性和时间效率。

英文摘要:

This method introduces an efficient manner of learning action categories without the need of feature estimation. The approach starts from low-level values, in a similar style to the successful CNN methods. However, rather than extracting general image features, we learn to predict specific video representations from raw video data. The benefit of such an approach is that at the same computational expense it can predict 2 D video representations as well as 3 D ones, based on motion. The proposed model relies on discriminative Waldboost, which we enhance to a multiclass formulation for the purpose of learning video representations. The suitability of the proposed approach as well as its time efficiency are tested on the UCF11 action recognition dataset.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑