Motion Trajectory Segmentation via Minimum Cost Multicuts

By Margret Keuper, Bjoern Andres, Thomas Brox. 2015

209 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

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

FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks (2016, methodology): “[14] was built on Large Displacement Optical Flow [7].”
Efficient Decomposition of Image and Mesh Graphs by Lifted Multicuts (2015, background): “The VI is split into a distance due to false joins, plus a distances due to false cuts, as in [30].”
Learning Unsupervised Video Object Segmentation Through Visual Attention (2019, methodology): “Dataset Metric Ours PDB [64] ARP [40] LVO [67] FSEG [33] LMP [66] SFL [11] FST [56] CUT [38] NLC [13] MSG [53] KEY [43] CVOS [65] TRC [17]”
Instance Embedding Transfer to Unsupervised Video Object Segmentation (2018, background): “NLC [9] CUT [18] FST [32] CVOS[35] LVO [37] MP [36] ARP[20] Ours”
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.”
A Survey on Deep Learning Technique for Video Segmentation (2021, background): “Among the big family of motion segmentation algorithms, trajectory segmentation attained particular attention [4], [33], [34], [35], [36].”
Learning Video Object Segmentation with Visual Memory (2017, methodology): “Left to right: ground truth, results of CUT [22], FST [31], MP-Net-Frame [43], and our method.”
Video Object Segmentation with Episodic Graph Memory Networks (2020, methodology): “Traditional methods usually leverage motion [18,29] or saliency cues [12,54] to obtain a heuristic representation for inferring the primary objects.”
Learning Motion Patterns in Videos (2016, unknown): “We also evaluated this combination (‘MP+Obj + FST’) on the FBMS test set, where it achieves 77.5% in F-measure, and is better than state-ofthe-art methods: FST [27] (69.2), CVOS [34] (74.9), and CUT [17] (76.8).”
AMP: Adaptive Masked Proxies for Few-Shot Segmentation (2019, unknown): “Measure FST [21] CVOS [34] CUT [11] MPNet-V[35] LVO[36] MotAdapt [30] AMP (ours) P 76.”
Occlusions, Motion and Depth Boundaries with a Generic Network for Disparity, Optical Flow or Scene Flow Estimation (2018, methodology): “We apply the estimated occlusions to the motion segmentation framework from Keuper et al. [22].”