Matching Local Self-Similarities across Images and Videos

By Eli Shechtman, Michal Irani. 2007

1,208 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

SUN database: Large-scale scene recognition from abbey to zoo (2010, methodology): “SSIM: Self-similarity descriptors [26] are computed on a regular grid at steps of five pixels.”
SUN Database: Exploring a Large Collection of Scene Categories (2014, methodology): “SSIM: Self-similarity descriptors [40] are computed on a regular grid at steps of five pixels.”
Static and space-time visual saliency detection by self-resemblance. (2009, methodology): “Then, the saliency map from color channels can be analogously defined as follows: Si ¼ p̂ Fkyi ¼ 1ð Þ ¼ 1PN j¼1 exp j1 þ >ðFi;FjÞ A2 : ð17Þ In order to verify that this idea allows us to achieve a consistent result and leads us to a better performance than using fusion methods, we have compared thre”
Feature representation for statistical-learning-based object detection: A review (2015, neutral): “Categories Typical feature representation methods Engineering -based features Gradient features SIFT [2], PCA-SIFT1 [3], RIFT [4], GLOH1 [5], SURF [6], DAISY [7], GIST1 [8], RIFF [9], WLD [10], HOG [11][12], integral histogram [13], v-HoG [14][15], CoHOG [16], spHOG [17], PQ-HOG [18], WHO1 [19], ECM”
Learning Complexity-Aware Cascades for Deep Pedestrian Detection (2015, background): “SS: The self-similarity (SS) features of [28] capture the difference between local patches and have achieved good performance on edge detection tasks [18, 7].”
Text2LIVE: Text-Driven Layered Image and Video Editing (2022, methodology): “Inspired by classical and recent works [20,43,48], we adopt the self-similarity measure.”
Spatio-temporal Depth Cuboid Similarity Feature for Activity Recognition Using Depth Camera (2013, background): “The self-similarity based feature has been proven to work well at object detection/retrieval and action detection on RGB data [20] and object recognition tasks on depth data [8, 9].”
Recognizing scene viewpoint using panoramic place representation (2012, methodology): “Features and classifiers We select several popular stateof-art features used in scene classification tasks, including GIST [11], SIFT [7], HOG2×2 [17], texton, geometric map (GeoMap) and texton statistics (GeoTexton) [17], self-similarity (SSIM) [13], local binary pattern (LBP) [9], and tiny image [”
Ultra-wide Baseline Facade Matching for Geo-localization (2012, methodology): “al [14] by adding a SIFTlike scale-normalization to allow characterization of the self-similar structure in a scale-invariant manner.”
A performance evaluation of gradient field HOG descriptor for sketch based image retrieval (2013, methodology): “We now compare proposed GF-HOG with SIFT [62], Self Similarity (SSIM) [36], Shape Context [64], HOG [50] and the Structure Tensor (used for SBIR in [2]).”
Super-Resolution of Sentinel-2 Images: Learning a Globally Applicable Deep Neural Network (2018, result): “The literature on self-similarity in image analysis supports such an assumption ( e.g ., Shechtman and Irani, 2007; Glasner et al., 2009), at least over a certain scale range.”
SeqSLAM: Visual route-based navigation for sunny summer days and stormy winter nights (2012, background): “One promising step [15] towards reducing the reliance on consistent feature detection uses the self-similarity of objects within a frame or video sequence to robustly recognize objects under varying conditions.”
Nonparametric Scene Parsing via Label Transfer (2011, background): “Recently, context information has also been carefully modeled to capture the relationship between objects at the semantic level [20], [22].”
Local Trinary Patterns for human action recognition (2009, methodology): “The local self-similarity method [17], represents spacetime interest points as vectors based on the spatial histogram of similarities between a central cuboid (space-time patch) and nearby cuboids.”
Author Manuscript, Published in "ieee Conference on Computer Vision and Pattern Recognition on the Burstiness of Visual Elements (neutral): “Intra-image burstiness is related to the selfsimilarity property used in [19] and obviously appears on near-regular textures [8].”
MIND: Modality independent neighbourhood descriptor for multi-modal deformable registration (2012, background): “, 2008), image retrieval (Hörster and Lienhart, 2008), detection (Shechtman and Irani, 2007) and segmentation (Coupé et al.”
What Makes a Photograph Memorable? (2014, positive): “We tested a suite of global image descriptors that have been previously found to be effective at scene recognition tasks [28] as well as being able to predict the presence/absence of objects in images [38]–[40].”
Understanding Video Events: A Survey of Methods for Automatic Interpretation of Semantic Occurrences in Video (2009, background): “Examples of this abstract video input as intuitively meaningful features such as histograms of spatio-temporal gradients [25], spatio-temporal patches [31, 32, 33] and “self-similarity surfaces” [28].”
High-level event recognition in unconstrained videos (2012, neutral): “[123] for cross-view action recognition.”