]Video object segmentation by hypergraph cut

Huang, Yuchi; Liu, Qingshan; Metaxas, Dimitris N.

doi:10.1109/cvpr.2009.5206795

Cited by 160 publications

(88 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Interactive object segmentation has recently shown significant progress [1,2,9,13,16]. These systems produce high quality segmentations driven by user input.…”

Section: Related Workmentioning

confidence: 99%

Efficient hierarchical graph-based video segmentation

Grundmann

Kwatra

Han

et al. 2010

2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition

596

764

View full text Add to dashboard Cite

We present an efficient and scalable technique for spatiotemporal segmentation of long video sequences using a hierarchical graph-based algorithm. We begin by oversegmenting a volumetric video graph into space-time regions grouped by appearance. We then construct a "region graph" over the obtained segmentation and iteratively repeat this process over multiple levels to create a tree of spatio-temporal segmentations. This hierarchical approach generates high quality segmentations, which are temporally coherent with stable region boundaries, and allows subsequent applications to choose from varying levels of granularity. We further improve segmentation quality by using dense optical flow to guide temporal connections in the initial graph. We also propose two novel approaches to improve the scalability of our technique: (a) a parallel outof-core algorithm that can process volumes much larger than an in-core algorithm, and (b) a clip-based processing algorithm that divides the video into overlapping clips in time, and segments them successively while enforcing consistency. We demonstrate hierarchical segmentations on video shots as long as 40 seconds, and even support a streaming mode for arbitrarily long videos, albeit without the ability to process them hierarchically.

show abstract

“…Interactive object segmentation has recently shown significant progress [1,2,9,13,16]. These systems produce high quality segmentations driven by user input.…”

Section: Related Workmentioning

confidence: 99%

Efficient hierarchical graph-based video segmentation

Grundmann

Kwatra

Han

et al. 2010

2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition

596

764

View full text Add to dashboard Cite

show abstract

“…Our framework can be extended to handle more feature channels, like space-time interest points [29] and can benefit from more complex video object segmentation methods like [15]. Future work includes exploring these techniques and more feature channels, together with their spatio-temporal relationships.…”

Section: Resultsmentioning

confidence: 99%

Object, Scene and Actions: Combining Multiple Features for Human Action Recognition

Ikizler-Cinbis

Sclaroff

2010

Lecture Notes in Computer Science

216

122

View full text Add to dashboard Cite

Abstract. In many cases, human actions can be identified not only by the singular observation of the human body in motion, but also properties of the surrounding scene and the related objects. In this paper, we look into this problem and propose an approach for human action recognition that integrates multiple feature channels from several entities such as objects, scenes and people. We formulate the problem in a multiple instance learning (MIL) framework, based on multiple feature channels. By using a discriminative approach, we join multiple feature channels embedded to the MIL space. Our experiments over the large YouTube dataset show that scene and object information can be used to complement person features for human action recognition.

show abstract

“…Further, [5] utilized hypergraphs for unsupervised video segmentation, in contrast to the supervised case the proposed approach deals with. Salient aspects of the proposed 3D tracing framework are scalability to hundreds of labels, modeling higher order interaction between segments, introduction of global contour cues using hyperedges, generic autoseeding for fully automatic tracing, and semi-supervised nature, amenable to user interaction if needed.…”

Section: Related Workmentioning

confidence: 99%

Scalable Tracing of Electron Micrographs by Fusing Top Down and Bottom Up Cues Using Hypergraph Diffusion

Jagadeesh

Shih

Manjunath

et al. 2012

Medical Image Computing and Computer-Assisted Intervention – MICCAI 2012

View full text Add to dashboard Cite

Abstract.A novel framework for robust 3D tracing in Electron Micrographs is presented. The proposed framework is built using ideas from hypergraph diffusion, and achieves two main objectives. Firstly, the approach scales to trace hundreds of targets without noticeable increase in runtime complexity. Secondly, the framework yields flexibility to fuse top down (global cues as hyperedges) and bottom up (local superpixels as nodes) information. Subsequently, a procedure for auto-seeding to initialize the tracing procedure is proposed. The paper concludes with experimental validation on a challenging large scale tracing problem for simultaneously tracing 95 structures, illustrating applicability of the proposed algorithm.

show abstract

]Video object segmentation by hypergraph cut

Cited by 160 publications

References 12 publications

Efficient hierarchical graph-based video segmentation

Efficient hierarchical graph-based video segmentation

Object, Scene and Actions: Combining Multiple Features for Human Action Recognition

Scalable Tracing of Electron Micrographs by Fusing Top Down and Bottom Up Cues Using Hypergraph Diffusion

Contact Info

Product

Resources

About