Publications

Weakly-Supervised Visual Grounding of Phrases with Linguistic Structures

• July 21, 2017

• Fanyi Xiao (University of California Davis)
• Leonid Sigal
• Yong Jae Lee (University of California Davis)

• IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2017

• Press Release:  Computers using linguistic clues to deduce photo content

Learn How to Choose: Independent Detectors versus Composite Visual Phrases

• March 27, 2017

• Guy Rosenthal (Tel Aviv University)
• Ariel Shamir (The Interdisciplinary Center)
• Leonid Sigal

• IEEE Winter Conference on Applications of Computer Vision (WACV) 2017

Real-time Physics-based Motion Capture with Sparse Sensors

• December 12, 2016

• Sheldon Andrews
• Ivan Huerta
• Taku Komura (Taku Komura University of Edinburgh)
• Leonid Sigal
• Kenny Mitchell

• Conference for Visual Media Production (CVMP) 2016

Semi-Supervised Vocabulary-Informed Learning

• June 24, 2016

• Yanwei Fu
• Leonid Sigal

• IEEE Conference on Computer Vision Pattern Recognition (CVPR) 2016

• Press Release:  Computer vision system studies word use to recognize objects it has never seen before

Harnessing Object and Scene Semantics for Large-Scale Video Understanding

• June 24, 2016

• Zuxuan Wu (Fudan University)
• Yanwei Fu
• Yu-Gang Jiang (Fudan University)
• Leonid Sigal

• IEEE Conference on Computer Vision Pattern Recognition (CVPR) 2016

• Press Release:  Object and scene recognition software work together to understand video content

Learning Activity Progression in LSTMs for Activity Detection and Early Detection

• June 24, 2016

• Shugao Ma (Boston University)
• Leonid Sigal
• Stan Sclaroff (Boston University)

• IEEE Conference on Computer Vision Pattern Recognition (CVPR) 2016

• Press Release:  Disney method detects human activity in videos earlier and more accurately

Exploiting View-Specific Appearance Similarities Across Classes for Zero-Shot Pose Prediction: A Metric Learning Approach

• February 12, 2016

• Alina Kuznetsova (Leibniz University Hannover)
• Sung Ju Hwang (UNIST)
• Bodo Rosenhahn (Leibniz University Hannover)
• Leonid Sigal

• Association for the Advancement of Artificial Intelligence (AAAI) 2016

• Press Release:  New computer vision algorithm predicts orientation of objects

A Perceptual Control Space for Garment Simulation

• July 26, 2015

• Leonid Sigal
• Moshe Mahler
• Spencer Diaz
• Kyna McIntosh
• Elizabeth Carter (Disney Research Pittsburgh)
• Timothy Richards (Walt Disney Animation Studios)
• Jessica Hodgins

• ACM SIGGRAPH 2015

• Press Release:  Disney system uses everyday descriptions of cloth to aid garment design for animations

Expanding Object Detector’s HORIZON: Incremental Learning Framework for Object Detection in Videos

• June 8, 2015

• Alina Kuznetsova
• Sung Ju Hwang (UNIST)
• Bodo Rosenhahn (Leibniz University Hannover)
• Leonid Sigal

• IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2015

• Press Release:  Expanding Object Detector’s HORIZON: Incremental Learning Framework for Object Detection in Videos

Space-Time Tree Ensemble for Action Recognition

• June 8, 2015

• Shugao Ma (Boston University)
• Leonid Sigal
• Stan Sclaroff (Boston University)

• IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2015

• Press Release:  Space-Time Tree Ensemble for Action Recognition

Family Member Identification from Photo Collections

• January 6, 2015

• Qieyun Dai
• Peter Carr
• Leonid Sigal
• Darek Hoiem (University of Illinois at Urbana-Champaign)

• IEEE Workshop on the Applications of Computer Vision (WACV) 2015

Parameterizing Object Detectors in the Continuous Pose Space

• September 6, 2014

• Kun He (Boston University)
• Leonid Sigal
• Stan Sclaro (Boston University)

• European Conference on Computer Vision (ECCV) 2014