activity
20162024
most citedLifted Disjoint Paths with Application in Multiple Object Tracking

84 citations · 261 across the 33 of their papers we have counts for

collaborators
Showing 2018Show all

7 papers · 1 filter

cs.CV2018

Security Event Recognition for Visual Surveillance

Michael Ying Yang, Wentong Liao, Chun Yang +2

With rapidly increasing deployment of surveillance cameras, the reliable methods for automatically analyzing the surveillance video and recognizing special events are demanded by d…

cs.LG2018

Markov Chain Neural Networks

Maren Awiszus, Bodo Rosenhahn

In this work we present a modified neural network model which is capable to simulate Markov Chains. We show how to express and train such a network, how to ensure given statistical…

cs.CV2018

Temporally Object-based Video Co-Segmentation

Michael Ying Yang, Matthias Reso, Jun Tang +2

In this paper, we propose an unsupervised video object co-segmentation framework based on the primary object proposals to extract the common foreground object(s) from a given video…

cs.CV2018

Slice Sampling Particle Belief Propagation

Oliver Mueller, Michael Ying Yang, Bodo Rosenhahn

Inference in continuous label Markov random fields is a challenging task. We use particle belief propagation (PBP) for solving the inference problem in continuous label space. Samp…

cs.CV2018

Video Event Recognition and Anomaly Detection by Combining Gaussian Process and Hierarchical Dirichlet Process Models

Michael Ying Yang, Wentong Liao, Yanpeng Cao +1

In this paper, we present an unsupervised learning framework for analyzing activities and interactions in surveillance videos. In our framework, three levels of video events are co…

cs.CV2018

Triplet-based Deep Similarity Learning for Person Re-Identification

Wentong Liao, Michael Ying Yang, Ni Zhan +1

In recent years, person re-identification (re-id) catches great attention in both computer vision community and industry. In this paper, we propose a new framework for person re-id…