Videos and presentations | IU Computer Vision Lab

Videos

ICCC 2022:
Generation and Evaluation of Creative Images from Limited Data: A Class-to-Class VAE Approach

CVPR 2021:
The Affective Growth of Computer Vision

WACV 2021:
Whose hand is this? Person Identification from Egocentric Hand Gestures

WACV 2021:
Part Segmentation of Unseen Objects Using Keypoint Guidance

IJCAI Workshop on Deep Learning, Case-Based Reasoning, and AutoML: Present and Future Synergies 2021:
Applying the Case Difference Heuristic to Learn Adaptations from Deep Network Features

CHI Workshop on Realizing AI in Healthcare: Challenges Appearing in the Wild 2021:
Computer Vision for Dietary Assessment

COGSCI 2020:
A Computational Model of Early Word Learning from the Infant's Point of View

OAKLAND 2020:
Automatically Detecting Bystanders in Photos to Reduce Privacy Risks

CVPR 2020:
HOPE-Net: A Graph-based Model for Hand-Object Pose Estimation

ICRA 2020:
Interaction Graph for Object Importance Estimation in On-road Driving Videos

NAML 2021 talk:
Combining Deep Learning and Case-based Reasoning for Robust, Accurate, Explainable Systems

SRCD 2021 talk:
Active Viewing in Infants Facilitates Visual Object Learning: A computational modeling approach

WTIU PBS (2017):
IU Matters: Artificial Intelligence

IU Bloomington Emerging Areas of Research (2017):
Learning: Machines, Brains, and Children

Faculty lightning talk (2016):
IU Computer Vision Lab

UCLA IPAM Workshop on Culture Analytics talk:
Wearable cameras, for fun and science (2016)

ICCV 2015 Video Spotlight:
Lending A Hand: Detecting Hands and Recognizing Activities in Complex Egocentric Interactions
More info: [paper] [project]

SPIDAL tech talk:
Computer vision meets high-performance computing

Ubicomp 2014 talk video:
Privacy Behaviors of Lifeloggers using Wearable Cameras
More info: [paper]

Spotlight video (2015):
A Socio-Technical Approach to Privacy in a Camera-Rich World
More info: [project]

Overview video:
Large-scale 3d reconstruction from social photo-sharing websites
More info: [project]

D2I center colloquium video (2013):
Studying the World by Mining Photo-Sharing Websites

WSDM 2012 talk video:
Beyond Co-occurrence: Discovering and Visualizing Tag Relationships from Geo-spatial and Temporal Similarities
More info: [paper] [project]

CVPR 2011 talk video:
Discrete-Continuous Optimization for Large-scale Structure from Motion
More info: [paper] [project]

KDD 2008 talk video:
Feedback Effects between Similarity and Social Influence in Online Communities
More info: [paper]

Posters and slides

NAML 2022 poster:
Deep Learning to Enhance Similarity Assessment for Case-Based Reasoning

CVPR 2016 tutorial slides:
Training Diverse Ensembles of Deep Networks
More info: [project]

NIPS 2016 poster:
Stochastic Multiple Choice Learning for Training Diverse Deep Ensembles
More info: [paper]

AGU 2016 poster:
3d Imaging and Automated Ice Bottom Tracking of (Canadian) Arctic Aripelago Ice Sounding Data

ICCV 2015 poster:
Lending A Hand: Detecting Hands and Recognizing Activities in Complex Egocentric Interactions
More info: [paper]

WACV 2015 poster:
Predicting Geo-informative Attributes in Large-scale Image Collections using Convolutional Neural Networks
More info: [paper] [project]

CVPR BigVision 2015 poster:
Linking Past to Present: Discovering Style in Two Centuries of Architecture
More info: [paper] [project]

ICCP 2015 talk slides:
Linking Past to Present: Discovering Style in Two Centuries of Architecture
More info: [paper] [project]

ICMI 2015 poster:
Viewpoint Integration for Hand-Based Recognition of Social Interactions from a First-Person View
More info: [paper]

CVPR EgoVision 2014 poster:
This Hand is My Hand: A Probabilistic Approach to Hand Disambiguation in Egocentric Video
More info: [paper]

CVPR 2014 poster:
Multimodal Learning in Loosely-organized Web Images
More info: [paper]

WACV 2014 poster:
Vehicle Recognition with Constrained Multiple Instance SVMs
More info: [paper]

ICWSM 2013 poster:
De-anonymizing users across heterogeneous social computing platforms
More info: [paper]

WSDM 2012 poster:
Beyond Co-occurrence: Discovering and Visualizing Tag Relationships from Geo-spatial and Temporal Similarities
More info: [paper] [project]

BMVC 2012 poster:
A Multi-layer Composite Model for Human Pose Estimation
More info: [paper] [project]

ICPR 2012 talk slides:
Layer-finding in radar echograms using probabilistic graphical models
More info: [paper] [project]

CVPR 2012 poster:
Discovering Localized Attributes for Fine-grained Recognition
More info: [paper] [project]

WSDM 2012 talk slides:
Beyond Co-occurrence: Discovering and Visualizing Tag Relationships from Geo-spatial and Temporal Similarities
More info: [paper] [project]

WWW 2012 talk slides:
Mining Photo-sharing Websites to Study Ecological Phenomena
More info: [paper] [project]

CVPR 2011 talk slides:
Discrete-Continuous Optimization for Large-scale Structure from Motion
More info: [paper] [project]

ICCV 2009 poster:
Landmark Classification in Large-scale Image Collections
More info: [paper]

The IU Computer Vision Lab's projects and activities have been funded, in part, by grants and contracts from the Air Force Office of Scientific Research (AFOSR), the Defense Threat Reduction Agency (DTRA), Dzyne Technologies, EgoVid, Inc., ETRI, Facebook, Google, Grant Thornton LLP, IARPA, the Indiana Innovation Institute (IN3), the IU Data to Insight Center, the IU Office of the Vice Provost for Research through an Emerging Areas of Research grant, the IU Social Sciences Research Commons, the Lilly Endowment, NASA, National Science Foundation (IIS-1253549, CNS-1834899, CNS-1408730, BCS-1842817, CNS-1744748, IIS-1257141, IIS-1852294), NVidia, ObjectVideo, Office of Naval Research (ONR), Pixm, Inc., and the U.S. Navy. The views and conclusions contained herein are those of the authors and should not be interpreted as necessarily representing the official policies or endorsements, either expressed or implied, of the U.S. Government, or any sponsor.