We prove that stochastic gradient descent efficiently converges to the global optimizer of the maximum likelihood objective of an unknown linear time-invariant dynamicalsystem from a sequence of noisy observations ge...
详细信息
We prove that stochastic gradient descent efficiently converges to the global optimizer of the maximum likelihood objective of an unknown linear time-invariant dynamicalsystem from a sequence of noisy observations generated by the system. Even though the objective function is non-convex, we provide polynomial running time and sample complexity bounds under strong but natural assumptions. linearsystems identification has been studied for many decades, yet, to the best of our knowledge, these are the first polynomial guarantees for the problem we consider.
In this paper, we address the problem of recognizing human actions with motion dynamics alone. For this purpose, we propose to use silhouette sequences to represent the human actions by discarding the appearance infor...
详细信息
ISBN:
(纸本)9781479923427
In this paper, we address the problem of recognizing human actions with motion dynamics alone. For this purpose, we propose to use silhouette sequences to represent the human actions by discarding the appearance information, and then model the sequences with linear dynamical systems (LDSs). Recognition is achieved by directly comparing the distance between LDSs, rather than resorting to complex Bayesian learning and inference. In particular, we introduce an efficient optimization method to learn robust LDSs, and develop a shift invariant distance metric to measure the similarity on the LDSs space. We evaluate our approach on the human action data set and achieve comparable results.
In this paper, we try to develop a general framework of 3D shape reconstruction strategy with extremely rare point cloud extracted for fish ethology research. Particle filter is first taken to focus on fish trajectory...
详细信息
ISBN:
(纸本)9781509015276
In this paper, we try to develop a general framework of 3D shape reconstruction strategy with extremely rare point cloud extracted for fish ethology research. Particle filter is first taken to focus on fish trajectory tracking from monocular video sequence. The Speeded Up Robust Features (SURF) technique will be adopted to match the same tracking fish across the overlapping view fields with more stable and accurate features. Non-rigid 3D shape reconstruction will be finally developed with the help of expectation maximization (EM) model and linear dynamical system (LDS). It is shown from our simulation experiment that the developed scheme of this paper achieves consistent performance improvements over non-rigid 3D shape reconstruction for fish ethology research.
In this paper, we proposed new framework for human action representation, which leverages the strengths of convolutional neural networks (CNNs) and the linear dynamical system (LDS) to represent both spatial and tempo...
详细信息
ISBN:
(纸本)9781509041183
In this paper, we proposed new framework for human action representation, which leverages the strengths of convolutional neural networks (CNNs) and the linear dynamical system (LDS) to represent both spatial and temporal structures of actions in videos. We make two principal contributions: first, we incorporate image-trained CNNs to detect action clip concepts, which takes advantage of different levels of information by combining the two layers in CNNs trained from images;Second, we further propose adopting a linear dynamical system (LDS) to model the relationships between these clip concepts, which captures temporal structures of actions. We have applied the proposed method on two challenging realistic benchmark datasets, and our method achieves high performance up to 86.16% on the YouTube and 82.76% UCF50 datasets, which largely outperforms most of the state-of-the-art algorithms with more sophisticated techniques.
暂无评论