Encoding Classes of Unaligned Objects Using Structural Similarity Cross-Covariance Tensors
نویسندگان
چکیده
Encoding an object essence in terms of self-similarities between its parts is becoming a popular strategy in Computer Vision. In this paper, a new similarity-based descriptor, dubbed Structural Similarity Cross-Covariance Tensor is proposed, aimed to encode relations among different regions of an image in terms of cross-covariance matrices. The latter are calculated between low-level feature vectors extracted from pairs of regions. The new descriptor retains the advantages of the widely used covariance matrix descriptors [1], extending their expressiveness from local similarities inside a region to structural similarities across multiple regions. The new descriptor, applied on top of HOG, is tested on object and scene classification tasks with three datasets. The proposed method always outclasses baseline HOG and yields significant improvement over a recently proposed self-similarity descriptor in the two most challenging datasets.
منابع مشابه
Encoding Structural Similarity by Cross-covariance Tensors for Image Classification
MARCO SAN BIAGIO1, SAMUELE MARTELLI1, MARCO CROCCO1, MARCO CRISTANI1,2, VITTORIO MURINO1,2 1 Pattern Analysis & Computer Vision Istituto Italiano di Tecnologia Via Morego 30, 16163, Genova, Italy 2 Università degli Studi di Verona Dipartimento di Informatica Strada le Grazie 15, 37134, Verona, Italy [email protected] http://iit.it/en/research/departments/pattern-analysis-and-computer-vision.html
متن کاملRNA sequence analysis using covariance models.
We describe a general approach to several RNA sequence analysis problems using probabilistic models that flexibly describe the secondary structure and primary sequence consensus of an RNA sequence family. We call these models 'covariance models'. A covariance model of tRNA sequences is an extremely sensitive and discriminative tool for searching for additional tRNAs and tRNA-related sequences i...
متن کاملCMfinder - a covariance model based RNA motif finding algorithm
MOTIVATION The recent discoveries of large numbers of non-coding RNAs and computational advances in genome-scale RNA search create a need for tools for automatic, high quality identification and characterization of conserved RNA motifs that can be readily used for database search. Previous tools fall short of this goal. RESULTS CMfinder is a new tool to predict RNA motifs in unaligned sequenc...
متن کاملRunning title: Covariance models of RNA RNA Sequence Analysis Using Covariance Models
We describe a general approach to several RNA sequence analysis problems using probabilistic models that exibly describe the secondary structure and primary sequence consensus of an RNA sequence family. We call these models \covariance models". A covariance model of tRNA sequences is an extremely sensitive and discriminative tool for searching for additional tRNAs and tRNA-related sequences in ...
متن کاملA Novel Method for Tracking Moving Objects using Block-Based Similarity
Extracting and tracking active objects are two major issues in surveillance and monitoring applications such as nuclear reactors, mine security, and traffic controllers. In this paper, a block-based similarity algorithm is proposed in order to detect and track objects in the successive frames. We define similarity and cost functions based on the features of the blocks, leading to less computati...
متن کامل