LetItBe的博客

Abstract3D 卷积核，由于参数量多，容易overfitting；提出了一种正则化方法；the key idea of RMS is to randomly vary the magnitude of low-frequency components of the feature to regularize the model.Introduction解决overfitting问题有Perturbation base regularization methods on the input sp.

Abstractimage-based domain adaptation, domain shift in videos,Two large-scale DA datasets (UCF-HMDB_full, Kinetics-Gameplay)Introductionvideos can suffer from domain discrepancy along both the spatial and temporal directions.Claim的两个点:Conclusionth.

AbstractThe problem of Domain Shift in action videos.Introduction实际应用例子surveillance cameras are everywhere, be it city streets, market place, buildings or airports. A massive amount of video data that needs to be processed for autonomous understanding .

AbstractFine-grained action recognition datasets exhibit environmental bias, where multiple video sequences are captured from a limited number of environments. Multi-modal nature of video（视频的多模态性），提出的方法一个是multi-modal self-supervision，还有一个是adversarial tra.

定义行为识别似乎是图像分类任务到多个帧的扩展，然后聚合来自每帧的预测背景传统方法，视频输入=》特征提取=》特征融合=》特征分类=》分类结果深度学习方法，单流法，双流法，基于骨架特征提取，ROI提取表示传统方法DT（Dense Trajectories）算法,是利用光流场来获得视频序列中的轨迹，在沿着轨迹提取轨迹形状特征HOF，HOG，MHB特征，然后利用BoF(Bag of Features)方法对特征进行编码，最后基于编码结果训练SVM分类器。iDT算法，基于DT算法进行了以下几点的改进：