Author: Sejong Yoon

1. Overview

Modeling and classification of human actions are important problems that have received significant attention in pattern recognition.  Mocap data is widely available and can serve as a good proxy for assessing action models before they are applied to … Read the rest

1. Abstract
We propose an autocorrelation Cox process that extends the traditional bag-of-words representation to model the spatio-temporal context within a video sequence. Bag-of-words models are effective tools for representing a video by a histogram of visual words that describe … Read the rest

1. Abstract

Smartphone based indoor localization caught massive interest of the localization community in recent years.  Combining pedestrian dead reckoning obtained using the phone’s inertial sensors with the GraphSLAM (Simultaneous Localization and Mapping) algorithm is one of the most effective … Read the rest

1. Overview

Most traditional image annotation approaches focus on tagging of images with labels: textual labels from a lexicon of words are either assigned or not assigned to an image based on its visual content or the content of similar … Read the rest

1. Overview

Experiments on Animals with Attributes dataset demonstrate the performance of the proposed method and show its advantages over previous methods based on binary tagging and multi-class classification.Object classes are then predicted using these ratings.In this work, we propose … Read the rest

1. Goal of the Project
For a given Roman coin image, the goal is to

1. to automatically find visual characteristics of the coin which make it distinguishable from the others
2. to identify Roman Imperial Coinage (RIC) label of the coin

… Read the rest

The problem of sequence alignment arises in many fields of science as a consequence of dealing with data that does not live in fixed dimensional Euclidean spaces. In computer vision, sequence alignment is an important first step used to solve … Read the rest

… Read the rest

Adaptive tracking-by-detection methods use previous tracking results to generate a new training set for object appearance, and update the current model to predict the object location in subsequent frames. Such approaches are typically bootstarpped by manual or semi-automatic initialization in … Read the rest

Multiple object tracking has numerous applications in video surveillance, human behavior analysis, visual navigation and sports video analysis. In contrast to applying independent individual trackers, the multi-object tracker handles all of the objects simultaneously in order to exploit the cross-object … Read the rest