SIFT meets CNN: A decade survey of instance retrieval

L Zheng, Y Yang, Q Tian - IEEE transactions on pattern …, 2017 - ieeexplore.ieee.org
In the early days, content-based image retrieval (CBIR) was studied with global features.
Since 2003, image retrieval based on local descriptors (de facto SIFT) has been extensively …

Bag‐of‐words representation in image annotation: a review

CF Tsai - International Scholarly Research Notices, 2012 - Wiley Online Library
Content‐based image retrieval (CBIR) systems require users to query images by their low‐
level visual content; this not only makes it hard for users to formulate queries, but also can …

[KİTAP][B] Data mining: concepts and techniques

J Han, J Pei, H Tong - 2022 - books.google.com
Data Mining: Concepts and Techniques, Fourth Edition introduces concepts, principles, and
methods for mining patterns, knowledge, and models from various kinds of data for diverse …

Learning a hierarchy of discriminative space-time neighborhood features for human action recognition

A Kovashka, K Grauman - 2010 IEEE computer society …, 2010 - ieeexplore.ieee.org
Recent work shows how to use local spatio-temporal features to learn models of realistic
human actions from video. However, existing methods typically rely on a predefined spatial …

[KİTAP][B] Visual object recognition

K Grauman, B Leibe - 2011 - books.google.com
The visual recognition problem is central to computer vision research. From robotics to
information retrieval, many desired applications demand the ability to identify and localize …

Grouplet: A structured image representation for recognizing human and object interactions

B Yao, L Fei-Fei - 2010 IEEE Computer Society Conference on …, 2010 - ieeexplore.ieee.org
Psychologists have proposed that many human-object interaction activities form unique
classes of scenes. Recognizing these scenes is important for many social functions. To …

Bundling features for large scale partial-duplicate web image search

Z Wu, Q Ke, M Isard, J Sun - 2009 IEEE Conference on …, 2009 - ieeexplore.ieee.org
In state-of-the-art image retrieval systems, an image is represented by a bag of visual words
obtained by quantizing high-dimensional local image descriptors, and scalable schemes …

Image retrieval with geometry-preserving visual phrases

Y Zhang, Z Jia, T Chen - CVPR 2011, 2011 - ieeexplore.ieee.org
The most popular approach to large scale image retrieval is based on the bag-of-visual-
word (BoV) representation of images. The spatial information is usually re-introduced as a …

Subsidiary prototype alignment for universal domain adaptation

JN Kundu, S Bhambri, AR Kulkarni… - Advances in …, 2022 - proceedings.neurips.cc
Abstract Universal Domain Adaptation (UniDA) deals with the problem of knowledge transfer
between two datasets with domain-shift as well as category-shift. The goal is to categorize …

Trajectory-based modeling of human actions with motion reference points

YG Jiang, Q Dai, X Xue, W Liu, CW Ngo - … 7-13, 2012, Proceedings, Part V …, 2012 - Springer
Human action recognition in videos is a challenging problem with wide applications. State-of-
the-art approaches often adopt the popular bag-of-features representation based on isolated …