Video SnapCut: robust video object cutout using localized classifiers

By Xue Bai, Jue Wang, David Simons, Guillermo Sapiro. ACM Transactions on Graphics, 2009

469 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/cf56a043577e41e5e33a4722352108660f80258f

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

Key-segments for video object segmentation (2011, methodology): “Interactive methods require a user to annotate object boundaries in some key frames, which are then propagated to other frames while a user stands by to adjust errors [2, 22, 32].”
Efficient hierarchical graph-based video segmentation (2010, background): “Interactive object segmentation has recently shown significant progress [1, 2, 9, 13, 16].”
Fast Video Object Segmentation by Reference-Guided Mask Propagation (2018, methodology): “For professional video editing applications, interactive methods are often preferred over automatic methods [41, 11, 2, 25].”
Video Object Segmentation through Spatially Accurate and Temporally Dense Extraction of Primary Object Regions (2013, background): “In the latter class of approaches, [2, 15, 23] need annotations of object segments in key frames for initialization.”
TouchCut: Fast image and video segmentation using single-touch interaction (2014, unknown): “7.”
VideoMatch: Matching based Video Object Segmentation (2018, background): “, MSK [25], SFL [8], OSVOS [5], OnAVOS [53], PLM [59], MaskRNN [19], Lucid [26], SEA [1], HVS [15], JMP [13], FCP [41], BVS [34], OFL [50], CTN [24], VPN [23], SVC [54], JFS [36], LTV [37], HBT [14], AFS [51], SCF [21], RB [2] and DA [60].”
A Survey on Deep Learning Technique for Video Segmentation (2021, background): “Unlike classic models [48], [49], [52] requiring extensive and professional user intervention, recent deep learning-based IVOS solutions (Table 3) usually work with multiple rounds of scribble supervision, to minimize the user’s effort.”
Online Adaptation of Convolutional Neural Networks for Video Object Segmentation (2017, methodology): “For VOS, online adaptation is less well explored; mainly classical methods like online-updated color and/or shape models [3, 4, 32] and online random forests [10] have been proposed.”
Learning Video Object Segmentation from Static Images (2016, background): “Thus several works have also considered video segmentation with variable annotation effort, enabling human interaction using clicks [22, 47, 51] or strokes [1, 16, 57].”
A Fully-Connected Layered Model of Foreground and Background Flow (2013, unknown): “Motion estimation and segmentation results on “flowergarden” and “8 org” [3].”
Fast Object Segmentation in Unconstrained Video (2013, methodology): “The task has been addressed by methods requiring a user to annotate the object position in some frames [3, 20, 26, 24], and by fully automatic methods [14, 6, 18, 4], which input just the video.”
Human Instance Segmentation from Video using Detector-based Conditional Random Fields (2011, background): “Another prominent application area is video object-cutout and paste [2, 15], where human instances from one environment can be segmented, and pasted onto another environment.”
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].”
Video Segmentation by Non-Local Consensus voting (2014, methodology): “Finally, in semi-supervised methods [1, 6, 7, 21, 28, 35] the user manually annotates several video frames, and segmentation is then propagated to all other frames.”
Video-to-Video Synthesis (2018, background): “While video super-resolution [61, 62], video matting and blending [3, 12], and video inpainting [73] can be considered as special cases of the video-to-video synthesis problem, existing approaches rely on problem-specific constraints and designs.”
Click Carving: Segmenting Objects in Video with Point Clicks (2016, methodology): “2015), to human-in-the-loop methods where a user closely guides the system towards a good segmentation output (Wang et al. 2005; Li, Sun, and Shum 2005; Bai et al. 2009; Shankar Nagaraja, Schmidt, and Brox 2015).”
A Benchmark Dataset and Evaluation Methodology for Video Object Segmentation (2016, methodology): “Supervised approaches assume manual annotation to be repeatedly added during the segmentation process, with a human correcting the algorithm results in an iterative fashion [2, 14, 49, 53].”