Search For:

Displaying 1-31 out of 31 total
From Subcategories to Visual Composites: A Multi-level Framework for Object Detection
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Tian Lan,Michalis Raptis,Leonid Sigal,Greg Mori
Issue Date:December 2013
pp. 369-376
The appearance of an object changes profoundly with pose, camera view and interactions of the object with other objects in the scene. This makes it challenging to learn detectors based on an object-level label (e.g., "car"). We postulate that hav...
 
Compositional Models for Video Event Detection: A Multiple Kernel Learning Latent Variable Approach
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Arash Vahdat,Kevin Cannons,Greg Mori,Sangmin Oh,Ilseo Kim
Issue Date:December 2013
pp. 1185-1192
We present a compositional model for video event detection. A video is modeled using a collection of both global and segment-level features and kernel functions are employed for similarity comparisons. The locations of salient, discriminative video segment...
 
Handling Uncertain Tags in Visual Recognition
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Arash Vahdat,Greg Mori
Issue Date:December 2013
pp. 737-744
Gathering accurate training data for recognizing a set of attributes or tags on images or videos is a challenge. Obtaining labels via manual effort or from weakly-supervised data typically results in noisy training labels. We develop the FlipSVM, a novel a...
 
Discriminative figure-centric models for joint action localization and recognition
Found in: Computer Vision, IEEE International Conference on
By Tian Lan, Yang Wang,Greg Mori
Issue Date:November 2011
pp. 2003-2010
In this paper we develop an algorithm for action recognition and localization in videos. The algorithm uses a figure-centric visual word representation. Different from previous approaches it does not require reliable human detection and tracking as input. ...
 
Hidden Part Models for Human Action Recognition: Probabilistic versus Max Margin
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Yang Wang, Greg Mori
Issue Date:July 2011
pp. 1310-1323
We present a discriminative part-based approach for human action recognition from video sequences using motion features. Our model is based on the recently proposed hidden conditional random field (HCRF) for object recognition. Similarly to HCRF for object...
 
Recognizing human actions from still images with latent poses
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Weilong Yang, Yang Wang, Greg Mori
Issue Date:June 2010
pp. 2030-2037
We consider the problem of recognizing human actions from still images. We propose a novel approach that treats the pose of the person in the image as latent variables that will help with recognition. Different from other work that learns separate systems ...
 
Selecting and Commanding Individual Robots in a Multi-Robot System
Found in: Computer and Robot Vision, Canadian Conference
By Alex Couture-Beil, Richard T. Vaughan, Greg Mori
Issue Date:June 2010
pp. 159-166
We present a novel real-time computer vision-based system for facilitating interactions between a single human and a multi-robot system: a user first selects an individual robot from a group of robots, by simply looking at it, and then commands the selecte...
 
Max-Margin Offline Pedestrian Tracking with Multiple Cues
Found in: Computer and Robot Vision, Canadian Conference
By Bahman Yari Saeed Khanloo, Ferdinand Stefanus, Mani Ranjbar, Ze-Nian Li, Nicolas Saunier, Tarek Sayed, Greg Mori
Issue Date:June 2010
pp. 347-353
In this paper, we introduce MMTrack, a hybrid single pedestrian tracking algorithm that puts together the advantages of descriptive and discriminative approaches for tracking. Specifically, we combine the idea of cluster-based appearance modeling and onlin...
 
Human Action Recognition by Semilatent Topic Models
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Yang Wang, Greg Mori
Issue Date:October 2009
pp. 1762-1774
We propose two new models for human action recognition from video sequences using topic models. Video sequences are represented by a novel “bag-of-words” representation, where each frame corresponds to a “word.” Our models differ from previous latent topic...
 
Action recognition by learning mid-level motion features
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Alireza Fathi, Greg Mori
Issue Date:June 2008
pp. 1-8
This paper presents a method for human action recognition based on patterns of motion. Previous approaches to action recognition use either local features describing small patches or large-scale features describing the entire human figure. We develop a met...
 
Action-Based Multifield Video Visualization
Found in: IEEE Transactions on Visualization and Computer Graphics
By Ralf P. Botchen, Sven Bachthaler, Fabian Schick, Min Chen, Greg Mori, Daniel Weiskopf, Thomas Ertl
Issue Date:July 2008
pp. 885-899
One challenge in video processing is to detect actions and events, known or unknown, in video streams dynamically. This paper proposes a visualization solution, where a video stream is depicted as a series of snapshots at a relatively sparse interval, and ...
 
Human Pose Estimation with Rotated Geometric Blur
Found in: Applications of Computer Vision, IEEE Workshop on
By Bo Chen, Nhan Nguyen, Greg Mori
Issue Date:January 2008
pp. 1-6
We consider the problem of estimating the pose of a human figure in a single image. Our method uses an exemplar-matching framework, where a test image is matched to a database of exemplars upon which body joint positions have been marked. We find the best ...
 
Human Pose Estimation using Motion Exemplars
Found in: Computer Vision, IEEE International Conference on
By Alireza Fathi, Greg Mori
Issue Date:October 2007
pp. 1-8
We present a motion exemplar approach for finding body configuration in monocular videos. A motion correlation technique is employed to measure the motion similarity at various space-time locations between the input video and stored video templates. These ...
 
Detecting Pedestrians by Learning Shapelet Features
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Payam Sabzmeydani, Greg Mori
Issue Date:June 2007
pp. 1-8
In this paper, we address the problem of detecting pedestrians in still images. We introduce an algorithm for learning shapelet features, a set of mid-level features. These features are focused on local regions of the image and are built from low-level gra...
 
Human Limb Delineation and Joint Position Recovery Using Localized Boundary Models
Found in: Motion and Video Computing, IEEE Workshop on
By Chris McIntosh, Ghassan Hamarneh, Greg Mori
Issue Date:February 2007
pp. 31
We outline the development of a self-initializing kinematic tracker that automatically discovers its part appearance models from a video sequence. Through its unique combination of an existing global joint estimation technique and a robust physical deforma...
 
Expression-Invariant Face Recognition with Expression Classification
Found in: Computer and Robot Vision, Canadian Conference
By Xiaoxing Li, Greg Mori, Hao Zhang
Issue Date:June 2006
pp. 77
Face recognition is one of the most intensively studied topics in computer vision and pattern recognition. Facial expression, which changes face geometry, usually has an adverse effect on the performance of a face recognition system. On the other hand, fac...
 
Automatic Classification of Outdoor Images by Region Matching
Found in: Computer and Robot Vision, Canadian Conference
By Oliver van Kaick, Greg Mori
Issue Date:June 2006
pp. 9
This paper presents a novel method for image classification. It differs from previous approaches by computing image similarity based on region matching. Firstly, the images to be classified are segmented into regions or partitioned into regular blocks. Nex...
 
Unsupervised Discovery of Action Classes
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Yang Wang, Hao Jiang, Mark S. Drew, Ze-Nian Li, Greg Mori
Issue Date:June 2006
pp. 1654-1661
In this paper we consider the problem of describing the action being performed by human figures in still images. We will attack this problem using an unsupervised learning approach, attempting to discover the set of action classes present in a large collec...
 
Efficient Shape Matching Using Shape Contexts
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Greg Mori, Serge Belongie, Jitendra Malik
Issue Date:November 2005
pp. 1832-1837
We demonstrate that shape contexts can be used to quickly prune a search for similar shapes. We present two algorithms for rapid shape retrieval: representative shape contexts, performing comparisons based on a small number of shape contexts, and shapemes,...
 
Guiding Model Search Using Segmentation
Found in: Computer Vision, IEEE International Conference on
By Greg Mori
Issue Date:October 2005
pp. 1417-1423
In this paper we show how a segmentation as preprocessing paradigm can be used to improve the efficiency and accuracy of model search in an image. We operationalize this idea using an over-segmentation of an image into superpixels. The problem domain we ex...
 
Recovering Human Body Configurations: Combining Segmentation and Recognition
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Greg Mori, Xiaofeng Ren, Alexei A. Efros, Jitendra Malik
Issue Date:July 2004
pp. 326-333
The goal of this work is to take an image such as the one in Figure 1(a), detect a human figure, and localize his joints and limbs (b) along with their associated pixel masks (c). In this work we attempt to tackle this problem in a general setting. The dat...
 
Recognizing Action at a Distance
Found in: Computer Vision, IEEE International Conference on
By Alexei A. Efros, Alexander C. Berg, Greg Mori, Jitendra Malik
Issue Date:October 2003
pp. 726
Our goal is to recognize human actions at a distance, at resolutions where a whole person may be, say, 30 pixels tall. We introduce a novel motion descriptor based on optical flow measurements in a spatio-temporal volume for each stabilized human figure, a...
 
Recognizing Objects in Adversarial Clutter: Breaking a Visual CAPTCHA
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Greg Mori, Jitendra Malik
Issue Date:June 2003
pp. 134
In this paper we explore object recognition in clutter. We test our object recognition techniques on Gimpy and EZ-Gimpy, examples of visual CAPTCHAs. A CAPTCHA (
 
Shape contexts enable efficient retrieval of similar shapes
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Greg Mori, Serge Belongie, Jitendra Malik
Issue Date:December 2001
pp. 723
In this work we demonstrate that a recently introduced shape descriptor, the
 
Learning Class-to-Image Distance with Object Matchings
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Guang-Tong Zhou,Tian Lan,Weilong Yang,Greg Mori
Issue Date:June 2013
pp. 795-802
We conduct image classification by learning a class-to-image distance function that matches objects. The set of objects in training images for an image class are treated as a collage. When presented with a test image, the best matching between this collage...
 
A Max-Margin Riffled Independence Model for Image Tag Ranking
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Tian Lan,Greg Mori
Issue Date:June 2013
pp. 3103-3110
We propose Max-Margin Riffled Independence Model (MMRIM), a new method for image tag ranking modeling the structured preferences among tags. The goal is to predict a ranked tag list for a given image, where tags are ordered by their importance or relevance...
 
"You are green": a touch-to-name interaction in an integrated multi-modal multi-robot HRI system
Found in: Proceedings of the 2014 ACM/IEEE international conference on Human-robot interaction (HRI '14)
By Fei Zhan, Greg Mori, Jens Wawerla, Richard Vaughan, Seyed Abbas Sadat, Shokoofeh Pourmehr, Valiallah (Mani) Monajjemi
Issue Date:March 2014
pp. 266-267
We present a multi-modal multi-robot interaction whereby a user can identify an individual or a group of robots using haptic stimuli, and name them using a voice command (e.g."You two are green"). Subsequent commands can be addressed to the same robot(s) b...
     
Integrating multi-modal interfaces to command UAVs
Found in: Proceedings of the 2014 ACM/IEEE international conference on Human-robot interaction (HRI '14)
By Fei Zhan, Greg Mori, Jens Wawerla, Richard Vaughan, Seyed Abbas Sadat, Shokoofeh Pourmehr, Valiallah (Mani) Monajjemi
Issue Date:March 2014
pp. 106-106
We present an integrated human-robot interaction system that enables a user to select and command a team of two Unmanned Aerial Vehicles (UAV) using voice, touch, face engagement and hand gestures. This system integrates multiple human [multi]-robot intera...
     
Segmental multi-way local pooling for video recognition
Found in: Proceedings of the 21st ACM international conference on Multimedia (MM '13)
By Greg Mori, Kevin Cannons, A.G. Amitha Perera, Arash Vahdat, Ilseo Kim, Sangmin Oh
Issue Date:October 2013
pp. 637-640
In this work, we address the problem of complex event detection on unconstrained videos. We introduce a novel multi-way feature pooling approach which leverages segment-level information. The approach is simple and widely applicable to diverse audio-visual...
     
Selecting and commanding individual robots in a vision-based multi-robot system
Found in: Proceeding of the 5th ACM/IEEE international conference on Human-robot interaction (HRI '10)
By Alex Couture-Beil, Greg Mori, Richard T. Vaughan
Issue Date:March 2010
pp. 355-356
This video presents a computer vision based system for interaction between a single human and multiple robots. Face contact and motion-based gestures are used as two different non-verbal communication channels; a user first selects a particular robot by si...
     
Boosting with incomplete information
Found in: Proceedings of the 25th international conference on Machine learning (ICML '08)
By Feng Jiao, Gholamreza Haffari, Greg Mori, Shaojun Wang, Yang Wang
Issue Date:July 2008
pp. 368-375
In real-world machine learning problems, it is very common that part of the input feature vector is incomplete: either not available, missing, or corrupted. In this paper, we present a boosting approach that integrates features with incomplete information ...
     
 1