Using Segmentation to Verify Object Hypotheses

By Deva Ramanan. 2007

89 citations recorded by the source corpus.

Subfields: Artificial Intelligence, 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 Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

An empirical study of context in object detection (2009, methodology): “Image segmentation, object boundary extraction, and various object shape/contour models are also examples of local pixel context, as they use the object’s surroundings to define its shape/boundary [31].”
Hough Regions for Joining Instance Localization and Segmentation (2012, background): “Related work in this field, as will be discussed in detail in the next section, either tries to combine detection and segmentation in separate subsequent stages [1] or aims at full scene understanding by jointly estimating a complete scene segmentation of an image for all object categories [2].”
Symbiotic Segmentation and Part Localization for Fine-Grained Categorization (2013, methodology): “Later methods used these masks to initialize graph-cuts based segmentations [7] that could take advantage of image specific color distributions, giving crisper and more accurate foreground segmentations [17, 19, 26].”
Detection Evolution with Multi-order Contextual Co-occurrence (2013, background): “High level image contexts such as semantic context [4], image statistics [27], and 3D geometric context [15], are used as well as low level image contexts, including local pixel context [5] and shape context [23].”
A discriminatively trained, multiscale, deformable part model (2008, unknown): “19 adds a segmentation-based verification step [20].”
Learning to localize detected objects (2012, unknown): “Ramanan and colleagues [18, 25] incorporate position pri-”
Layered object detection for multi-class segmentation (2010, unknown): “Early approaches bias a segmentation engine using the output of object models [27, 17], while others iterate between bottom-up and top-down cues [14, 15, 23].”
The truth about cats and dogs (2011, background): “Previous work has combined object category detection and segmentation in various ways [16, 19, 22, 33, 34, 36].”
Segmentation using Deformable Spatial Priors with Application to Clothing (2010, unknown): “In work that partly motivated our proposed approach, Ramanan [17], Lee et al.”
Shape-based pedestrian parsing (2011, methodology): “We can exploit this fact in order to rescore the detection, similar to the work of [23].”
Filtered channel features for pedestrian detection (2015, background): “Local structure) Instead of simple pixel values, some approaches try to encode a larger local struc ture based on colour similarities (soft-cue) [40, ]5], seg mentation methods (hard-decision) [27, 32, 36], or by es timating local boundaries [21].”