Video Object Segmentation through Spatially Accurate and Temporally Dense Extraction of Primary Object Regions

By Dong Zhang, Omar Javed, Mubarak Shah. 2013 IEEE Conference on Computer Vision and Pattern Recognition, 2013

325 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/66442f43cefec9ed1c53cc4a349a7e3d9f3b8948

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Track and Segment: An Iterative Unsupervised Approach for Video Object Proposals (2016, result): “We [53] [58] [40] [7] Ours Average Pixel Error 4766 25289 5859 16074 2464.”
Fast Object Segmentation in Unconstrained Video (2013, methodology): “The works [14, 16, 27] are closely related to ours, as they tackle the very same task.”
Semantic object segmentation via detection in weakly labeled video (2015, methodology): “Objectness is defined as combination of the score produced by region detector and magnitude of boundary motions, as suggested by [8].”
Learning Unsupervised Video Object Segmentation Through Visual Attention (2019, background): “Early UVOS methods are typically based on handcrafted features and heuristics such as long-term point trajectory [54, 5, 17, 53, 9], motion boundary [56], objectness [43, 51, 89, 18, 59, 83, 40, 45], and saliency [13, 77, 76, 34, 27].”
Semi-automatic video object segmentation by advanced manipulation of segmentation hierarchies (2015, background): “Video object segmentation and tracking algorithms [15], [16], [17] take a binary mask representing the shape of the object at a given frame, and output the propagated mask to the subsequent frames.”
Click Carving: Segmenting Objects in Video with Point Clicks (2016, background): “…from wholly unsupervised bottom-up approaches [1], [2], [3], to propagation methods that exploit user input on the first frame [4], [5], [6], [7], [8], [9], [10], to human-in-the-loop methods where a user closely guides the system towards a good segmentation output [11], [12], [13], [14], [15].”
Eye tracking assisted extraction of attentionally important objects from videos (2015, methodology): “The proposed technique outperforms state-of-the-art video segmentation using eye tracking prior and obtains favorable object extraction over algorithms which do not utilize eye tracking data.”
Robust video segment proposals with painless occlusion handling (2015, background): “Many approaches focus on separating one foreground object from the background, using semi-supervised or unsupervised methods [4, 18, 28, 37, 38, 41, 45].”
Video Segmentation via Object Flow (2016, background): “In addition, several algorithms [18, 19, 21, 24, 45] focus on object-level segmentations that favor temporal consistency.”
A Benchmark Dataset and Evaluation Methodology for Video Object Segmentation (2016, background): “Unsupervised approaches have historically targeted over-segmentation [21, 51] or motion segmentation [5, 18] and only recently automatic methods for foregroundbackground separation have been proposed [13, 25, 33, 43, 45, 52].”
FusionSeg: Learning to Combine Motion and Appearance for Fully Automatic Segmentation of Generic Objects in Videos (2017, background): “In recent years, video object segmentation has received significant attention, with great progress on fully automatic algorithms [15, 56, 13, 23, 30, 58, 24, 35, 10], propagation methods [40, 47, 11, 50, 19, 53], and interactive methods [51, 26, 2, 42].”
Saliency-aware geodesic video object segmentation (2015, methodology): “Ours [32] [23] [15] [6] [19] [4] [22] [29] [9] birdfall 209 155 189 288 217 468 468 606 252 454 cheetah 796 633 806 905 890 1175 1968 11210 1142 1217 girl 1040 1488 1698 1785 3859 5683 7595 26409 1304 1755 monkeydog 562 365 472 521 284 1434 1434 12662 563 683 parachute 207 220 221 201 855 1595 1113 ”
Learning Motion Patterns in Videos (2016, methodology): “Some of these first estimate a region [27, 39] or regions [20, 43], which potentially correspond(s) to the foreground object, and then learn foreground/background appearance models.”
See More, Know More: Unsupervised Video Object Segmentation With Co-Attention Siamese Networks (2019, background): “Early UVOS models typically analyzed long-term motion information (trajectories) [4, 40, 17, 42, 28, 41], leveraged object proposals [31, 37, 70, 30, 18, 27] or utilized saliency information [60, 14, 55, 21], to infer the target.”
A Survey on Deep Learning Technique for Video Segmentation (2021, methodology): “Several methods [5], [38], [39], [40] explored object hypotheses or proposals [41] as middle-level object representations.”
Video Segmentation by Non-Local Consensus voting (2014, methodology): “Visual comparisons to [27, 38] using their publicly available code.”
Spatio-temporal Object Detection Proposals (2014, unknown): “Finally, several recent methods address the related but different problem of motion segmentation in video [25,31,49].”
Video Object Segmentation with Episodic Graph Memory Networks (2020, background): “This task has been widely studied over several decades which also called unsupervised video object segmentation [19, 22, 35, 71].”