SOTAVerified

Motion Segmentation

Motion Segmentation is an essential task in many applications in Computer Vision and Robotics, such as surveillance, action recognition and scene understanding. The classic way to state the problem is the following: given a set of feature points that are tracked through a sequence of images, the goal is to cluster those trajectories according to the different motions they belong to. It is assumed that the scene contains multiple objects that are moving rigidly and independently in 3D-space.

Source: Robust Motion Segmentation from Pairwise Matches

Papers

Showing 151160 of 212 papers

TitleStatusHype
High-Rank Matrix Completion and Clustering under Self-Expressive Models0
A Detailed Rubric for Motion Segmentation0
Structured Sparse Subspace Clustering: A Joint Affinity Learning and Subspace Clustering Framework0
Clustering with Hypergraphs: The Case for Large Hyperedges0
Unbiased Sparse Subspace Clustering By Selective Pursuit0
Reconstructing Articulated Rigged Models from RGB-D Videos0
Temporally Consistent Motion Segmentation from RGB-D Video0
Object Detection, Tracking, and Motion Segmentation for Object-level Video Segmentation0
Incremental Real-Time Multibody VSLAM with Trajectory Optimization Using Stereo Camera0
A Multi-cut Formulation for Joint Segmentation and Tracking of Multiple Objects0
Show:102550
← PrevPage 16 of 22Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Rule BasedAccuracy90Unverified
2Rel-Att-GCNAccuracy89Unverified
3MRGCNAccuracy86Unverified
4MRGCN-LSTMAccuracy72Unverified
5St-RNNAccuracy63Unverified
#ModelMetricClaimedVerifiedStatus
1SSCClassification Error2.18Unverified
2T-LinkageClassification Error1.97Unverified
3RSIMClassification Error1.01Unverified
4MVCClassification Error0.31Unverified
#ModelMetricClaimedVerifiedStatus
1MultiViewClusteringError7.92Unverified
#ModelMetricClaimedVerifiedStatus
1MVCClassification Error0.65Unverified