Intersecting Manifolds: Detection, Segmentation, and Labeling
Authors: Shay Deutsch, Gerard Guy Medioni
IJCAI 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We experiment with our method on a wide range of geometrically complex settings of convoluted intersecting manifolds, on which we demonstrate higher clustering performance than the state of the art. This includes tackling challenging geometric structures such as when the tangent spaces at the intersections points are not orthogonal. |
| Researcher Affiliation | Academia | Shay Deutsch and G erard Medioni University of Southern California Los Angeles, USA {shaydeut, medioni}@usc.edu |
| Pseudocode | Yes | Algorithm 1 Ambiguity Resolution Algorithm |
| Open Source Code | No | The paper does not provide any concrete access to source code for the methodology described. |
| Open Datasets | Yes | For experiments with real data-sets, we tested our method on the problems of human action classification and two view motion segmentation problems. Motion Capture using the CMU Motion capture data set Classification of human motion sequences as a prepossessing step is important for many tasks in video annotation. The CMU motion capture data-set is a popular and widely used real data set for motion capture. [...] Next we show evaluation on the problem of motion segmentation from two-views, using the 155 motion segmentation data-set benchmark, which is a well known dataset for motion segmentation. |
| Dataset Splits | No | The paper describes the total number of points used for synthetic datasets (e.g., "n=1000 points") and sample counts for real datasets, but it does not specify explicit training, validation, or test dataset splits. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., CPU, GPU models) used for running its experiments. |
| Software Dependencies | No | The paper mentions using Tensor Voting and Spectral Clustering, but it does not provide specific version numbers for any software or libraries used. |
| Experiment Setup | Yes | In our method, we chose a scale σ such that the average number of votes from each point in the Tensor Voting iteration equals to n/20, and the number of k nearest neighbors on the Tensor Voting was tested in {n/40, n/40 + 5, n/40 + 10}. [...] For the choice of parameters we tested the k nearest neighborhood size k {10, 20, 30, 40, 50, 60, 70, 80}. For the second parameter in SMMC and SSC we tested in {10, 20, 30, 40, 50, 60, 70, 80} and {0.001, 0.001, 0.1, 1}, respectively. |