• Publications
  • Influence
Multiscale Combinatorial Grouping
This work first develops a fast normalized cuts algorithm, then proposes a high-performance hierarchical segmenter that makes effective use of multiscale information, and proposes a grouping strategy that combines the authors' multiscales regions into highly-accurate object candidates by exploring efficiently their combinatorial space. Expand
Learning Rich Features from RGB-D Images for Object Detection and Segmentation
A new geocentric embedding is proposed for depth images that encodes height above ground and angle with gravity for each pixel in addition to the horizontal disparity to facilitate the use of perception in fields like robotics. Expand
Hypercolumns for object segmentation and fine-grained localization
Using hypercolumns as pixel descriptors, this work defines the hypercolumn at a pixel as the vector of activations of all CNN units above that pixel, and shows results on three fine-grained localization tasks: simultaneous detection and segmentation, and keypoint localization. Expand
The 2017 DAVIS Challenge on Video Object Segmentation
The scope of the benchmark, the main characteristics of the dataset, the evaluation metrics of the competition, and a detailed analysis of the results of the participants to the challenge are described. Expand
Semantic contours from inverse detectors
A simple yet effective method for combining generic object detectors with bottom-up contours to identify object contours is presented and a principled way of combining information from different part detectors and across categories is provided. Expand
Simultaneous Detection and Segmentation
This work builds on recent work that uses convolutional neural networks to classify category-independent region proposals (R-CNN), introducing a novel architecture tailored for SDS, and uses category-specific, top-down figure-ground predictions to refine the bottom-up proposals. Expand
Multiscale Combinatorial Grouping for Image Segmentation and Object Proposal Generation
We propose a unified approach for bottom-up hierarchical image segmentation and object proposal generation for recognition, called Multiscale Combinatorial Grouping (MCG). For this purpose, we firstExpand
Perceptual Organization and Recognition of Indoor Scenes from RGB-D Images
This work proposes algorithms for object boundary detection and hierarchical segmentation that generalize the gPb-ucm approach of [2] by making effective use of depth information and shows how this contextual information in turn improves object recognition. Expand
From contours to regions: An empirical evaluation
This work provides extensive experimental evaluation to demonstrate that, when coupled to a high-performance contour detector, the OWT-UCM algorithm produces state-of-the-art image segmentations. Expand
Using contours to detect and localize junctions in natural images
A new high-performance contour detector using a combination of local and global cues that provides the best performance to date on the Berkeley Segmentation Dataset (BSDS) benchmark and shows that improvements in the contour model lead to better junctions. Expand