This paper proposes a novel graph matching algorithm and applies it to shape recognition based on object silhouettes. The main idea is to match skeleton graphs by comparing the geo...
Object detection and recognition has achieved a significant progress in recent years. However robust 3D object detection and segmentation in noisy 3D data volumes remains a challen...
Le Lu, Adrian Barbu, Matthias Wolf, Jianming Liang...
It’s common experience for human vision to perceive full 3D shape and scene from a single 2D image with the occluded parts “filled-in” by prior visual knowledge. In this pa...
Abstract. In this paper a rigorous mathematical framework of deterministic annealing and mean-field approximation is presented for a general class of partitioning, clustering and ...
This paper examines the performance of several source separation systems on a speech separation task for which human intelligibility has previously been measured. For anechoic mixt...
Michael I. Mandel, S. Bressler, Barbara G. Shinn-C...