Segmentation of moving objects by long term video analysis

P Ochs, J Malik, T Brox - IEEE transactions on pattern analysis …, 2013 - ieeexplore.ieee.org
Motion is a strong cue for unsupervised object-level grou**. In this paper, we demonstrate
that motion will be exploited most effectively, if it is regarded over larger time windows …

Object segmentation by long term analysis of point trajectories

T Brox, J Malik - European conference on computer vision, 2010 - Springer
Unsupervised learning requires a grou** step that defines which data belong together. A
natural way of grou** in images is the segmentation of objects or parts of objects. While …

Motion segmentation & multiple object tracking by correlation co-clustering

M Keuper, S Tang, B Andres, T Brox… - IEEE transactions on …, 2018 - ieeexplore.ieee.org
Models for computer vision are commonly defined either wrt low-level concepts such as
pixels that are to be grouped, or wrt high-level concepts such as semantic objects that are to …

Motion trajectory segmentation via minimum cost multicuts

M Keuper, B Andres, T Brox - Proceedings of the IEEE …, 2015 - openaccess.thecvf.com
For the segmentation of moving objects in videos, the analysis of long-term point trajectories
has been very popular recently. In this paper, we formulate the segmentation of a video …

Multi-target multi-camera tracking by tracklet-to-target assignment

Y He, X Wei, X Hong, W Shi… - IEEE Transactions on …, 2020 - ieeexplore.ieee.org
This paper focuses on the Multi-Target Multi-Camera Tracking task (MTMCT), which aims at
tracking multiple targets within a multi-camera network. As the trajectory of each target is …

A multi-cut formulation for joint segmentation and tracking of multiple objects

M Keuper, S Tang, Y Zhongjie, B Andres, T Brox… - ar** cues from two levels of tracking
granularities, detection tracklets and point trajectories, for segmenting objects in crowded …

Learning spatial and temporal extents of human actions for action detection

Z Zhou, F Shi, W Wu - IEEE Transactions on multimedia, 2015 - ieeexplore.ieee.org
For the problem of action detection, most existing methods require that relevant portions of
the action of interest in training videos have been manually annotated with bounding boxes …

Motion-based object segmentation based on dense rgb-d scene flow

L Shao, P Shah, V Dwaracherla… - IEEE Robotics and …, 2018 - ieeexplore.ieee.org
Given two consecutive RGB-D images, we propose a model that estimates a dense three-
dimensional (3D) motion field, also known as scene flow. We take advantage of the fact that …