Fast Object Segmentation in Unconstrained Video

By Anestis Papazoglou, Vittorio Ferrari. IEEE International Conference on Computer Vision, 2013

611 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/7a59518a2bf7c24f775e3ce7bf98fceefada3e8f

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

Video Segmentation via Object Flow (2016, methodology): “Both of the pairwise terms are defined as in [24].”
Track and Segment: An Iterative Unsupervised Approach for Video Object Proposals (2016, methodology): “We [53] [58] [40] [7] Ours Average Pixel Error 4766 25289 5859 16074 2464.”
See More, Know More: Unsupervised Video Object Segmentation With Co-Attention Siamese Networks (2019, methodology): “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.”
Content-Aware Multi-Level Guidance for Interactive Instance Segmentation (2019, methodology): “Previous works have shown that most, if not all, pixels in a superpixel belong to the same category [17, 42, 25].”
Video Object Segmentation with Joint Re-identification and Attention-Aware Mask Propagation (2018, background): “Prior to the prevalence of deep learning, most approaches to semantic video segmentation are graph based [8, 18, 36, 25].”
Bayesian Joint Modelling for Object Localisation in Weakly Labelled Images (2015, methodology): “1 percent accuracy) recently by a model purposefully designed for video segmentation [71], which performed much more intensive spatio-temporal modelling and used superpixel segmentation within each frame andmotion segmentation across frames.”
Saliency-Aware Video Object Segmentation (2018, methodology): “The segmentation methods in [1], [7], [8], [9], [22], [23], [27], [60], [61] and our method are unsupervised, while other methods in [59], [62] are supervised.”
Stereo Video Object Segmentation Using Stereoscopic Foreground Trajectories (2019, methodology): “First, we present the qualitative results for stereo video segmentation compared with seven existing unsupervised methods [5], [8], [13], [14], [31], [32], [35].”
Click Carving: Segmenting Objects in Video with Point Clicks (2016, methodology): “Other methods extract “object-like” segments in video (Lee, Kim, and Grauman 2011; Papazoglou and Ferrari 2013), typically by learning the category-independent properties of good regions, and employing some form of tracking.”
Object Detection from Video Tubelets with Convolutional Neural Networks (2016, methodology): “Object localization and co-localization [27, 25, 14, 18], which have mainly focused on the YouTube Object Dataset (YTO) [27], seems to be a similar topic to the VID task.”
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].”
One-Shot Video Object Segmentation (2016, methodology): “We also add the unsupervised techniques: FST [36], SAL [46], KEY [24], MSG [5], TRC [13], CVOS [48], and NLC [10].”
Unsupervised Object Discovery and Tracking in Video Collections (2015, methodology): “Localization accuracy is measured using CorLoc [17, 25, 27], which is deﬁned as the percentage of images correctly localized according to the P ASCAL criterion: area ( r p ∩ r gt ) area ( r p ∪ r gt ) > 0 .”
AMP: Adaptive Masked Proxies for Few-Shot Segmentation (2019, neutral): “Measure FST [21] CVOS [34] CUT [11] MPNet-V[35] LVO[36] MotAdapt [30] AMP (ours) P 76.”
A Benchmark Dataset and Evaluation Methodology for Video Object Segmentation (2016, methodology): “Interestingly the assumption of a completely closed motion boundary curve coinciding with the object contours can robustly accommodate background deformations (FST).”
Pyramid Dilated Deeper ConvLSTM for Video Salient Object Detection (2018, background): “ARP*[20] LVO[34] FSEG[19] LMP[33] SFL*[5] FST*[30] SAGE*[42] Ours Ours+”
VideoMatch: Matching based Video Object Segmentation (2018, methodology): “Different methods such as motion analysis [39], trajectory clustering [37], and saliency-based spatio-temporal propagation [12, 20] have been proposed to identify the foreground objects.”
Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015 (2015, background): “Each frame is coarsely segmented (over-segmented) based on the optical ﬂow vectors, inspired by [10].”
Learning Video Object Segmentation with Visual Memory (2017, methodology): “Our robust model outperforms all these methods [11, 25, 31, 41, 45], as shown in Section 5.”