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 …

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 …

Motion segmentation is an essential task in artificial intelligence and computer vision.
However, scene motion in real-world intelligent systems usually integrates multiple types of …

The extension of conventional clustering to hypergraph clustering, which involves higher
order similarities instead of pairwise similarities, is increasingly gaining attention in …

We propose a new trajectory clustering method using submodular optimization for better
motion segmentation in videos. A small number of representative trajectories are first …

Recently, Minimum Cost Multicut Formulations have been proposed and proven to be
successful in both motion trajectory segmentation and multi-target tracking scenarios. Both …

This paper proposes a shrinkage-based framework for unsupervised trajectory clustering.
Facing to the challenges of trajectory clustering, eg, large variations within a cluster and …

A hybrid social influence model (HSIM) has been proposed which is a novel and automatic
method for pedestrian motion segmentation. One of the major attractions of the HSIM is its …

In this paper, we propose a framework of maximizing quadratic submodular energy with a
knapsack constraint approximately, to solve certain computer vision problems. The …

We propose density independent hydrodynamics model (DIHM) which is a novel and
automatic method for coherency detection in crowded scenes. One of the major advantages …