Object detection: current and future directions
R Verschae, J Ruiz-del-Solar - Frontiers in Robotics and AI, 2015 - frontiersin.org
Object detection is a key ability required by most computer and robot vision systems. The
latest research on this area has been making great progress in many directions. In the …
latest research on this area has been making great progress in many directions. In the …
[PDF][PDF] Survey of the problem of object detection in real images
DK Prasad - International Journal of Image Processing (IJIP), 2012 - researchgate.net
Object detection and recognition are important problems in computer vision. Since these
problems are meta-heuristic, despite a lot of research, practically usable, intelligent, real …
problems are meta-heuristic, despite a lot of research, practically usable, intelligent, real …
Image retrieval based on multi-texton histogram
This paper presents a novel image feature representation method, called multi-texton
histogram (MTH), for image retrieval. MTH integrates the advantages of co-occurrence …
histogram (MTH), for image retrieval. MTH integrates the advantages of co-occurrence …
Large-margin multi-modal deep learning for RGB-D object recognition
Most existing feature learning-based methods for RGB-D object recognition either combine
RGB and depth data in an undifferentiated manner from the outset, or learn features from …
RGB and depth data in an undifferentiated manner from the outset, or learn features from …
Semantics-preserving bag-of-words models and applications
The Bag-of-Words (BoW) model is a promising image representation technique for image
categorization and annotation tasks. One critical limitation of existing BoW models is that …
categorization and annotation tasks. One critical limitation of existing BoW models is that …
Variational Bayesian learning for Dirichlet process mixture of inverted Dirichlet distributions in non-Gaussian image feature modeling
In this paper, we develop a novel variational Bayesian learning method for the Dirichlet
process (DP) mixture of the inverted Dirichlet distributions, which has been shown to be very …
process (DP) mixture of the inverted Dirichlet distributions, which has been shown to be very …
Contextual bag-of-words for visual categorization
Bag-of-words (BOW), which represents an image by the histogram of local patches on the
basis of a visual vocabulary, has attracted intensive attention in visual categorization due to …
basis of a visual vocabulary, has attracted intensive attention in visual categorization due to …
Look-ahead techniques for fast beam search
S Ortmanns, H Ney - Computer Speech & Language, 2000 - Elsevier
This paper presents two look-ahead techniques for speeding up large vocabulary
continuous speech recognition. These two techniques are the language model look-ahead …
continuous speech recognition. These two techniques are the language model look-ahead …
Improved approaches with calibrated neighboring joint density to steganalysis and seam-carved forgery detection in JPEG images
Steganalysis and forgery detection in image forensics are generally investigated separately.
We have designed a method targeting the detection of both steganography and seam …
We have designed a method targeting the detection of both steganography and seam …
Systems and methods for image classification by correlating contextual cues with images
L Bourdev, B Paluri - US Patent 10,169,686, 2019 - Google Patents
US10169686B2 - Systems and methods for image classification by correlating contextual
cues with images - Google Patents US10169686B2 - Systems and methods for image …
cues with images - Google Patents US10169686B2 - Systems and methods for image …