Home
Projects
Egocentric vision

Egocentric Computer Vision

Egocentric computer vision

Ego4d: Around the world in 3,000 hours of egocentric video

Kristen Grauman, Andrew Westbury, Eugene Byrne, Vincent Cartillier, Zachary Chavis, Antonino Furnari, Rohit Girdhar, et al.
PAMI 2025
[website] [video]

What Changed and What Could Have Changed? State-Change Counterfactuals for Procedure-Aware Video Representation Learning

Chi-Hsi Kung, Frangil M Ramirez, Juhyung Ha, Yi-Hsuan Tsai, Yi-Ting Chen, David J. Crandall
ICCV 2025
[paper]

LoCoNet: Long-Short Context Network for Active Speaker Detection

Xizi Wang, Feng Cheng, Gedas Bertasius
CVPR 2024
[paper] [video]

Fusing Personal and Environmental Cues for Identification and Segmentation of First-Person Camera Wearers in Third-Person

Ziwei Zhao, Yuchen Wang, Chuhua Wang
CVPR 2024
[paper]

Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives

Kristen Grauman, Andrew Westbury, Lorenzo Torresani, Kris Kitani, Jitendra Malik, Triantafyllos Afouras, Kumar Ashutosh, et al.
CVPR 2024
[paper] [website] [video]

DoTA: Unsupervised Detection of Traffic Anomaly in Driving Videos

Yu Yao, Xizi Wang, Mingze Xu, Zelin Pu, Yuchen Wang, Ella Atkins, David J. Crandall
PAMI 2023
[paper] [website]

Situated Cameras, Situated Knowledges: Towards an Egocentric Epistemology for Computer Vision

Sam Goree, David Crandall
CVPR Ego4d/EPIC Workshop 2023
[paper]

Stepwise Goal-Driven Networks for Trajectory Prediction

Chuhua Wang, Yuchen Wang, Mingze Xu, David Crandall
RA-L 2022
[paper] [video]

Can Gaze Inform Egocentric Action Recognition?

Zehua Zhang, David Crandall, Michael Proulx, Sachin Talathi, Abhishek Sharma
ETRA 2022
[paper]

Whose hand is this? Person Identification from Egocentric Hand Gestures

Satoshi Tsutsui, Yanwei Fu, David J. Crandall
WACV 2021
[paper] [video]

Localizing novel attended objects in egocentric views

Shujon Naha, Md Alimoor Reza, Chen Yu, David J. Crandall
BMVC 2020
[paper]

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

Bardia Doosti, Shujon Naha, Majid Mirbagheri, David Crandall
CVPR 2020
[paper] [website] [video]

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

Zehua Zhang, Ashish Tawari, Sujitha Martin, David Crandall
ICRA 2020
[paper] [video]

A Self Validation Network for Object-Level Human Attention Estimation

Zehua Zhang, Chen Yu, David Crandall
NeurIPS 2019
[paper] [website]

Embodied Visual Recognition: Learning to Move for Amodal Perception

Jianwei Yang, Zhile Ren, Mingze Xu, Xinlei Chen, David Crandall, Devi Parikh, Dhruv Batria
ICCV 2019
[paper]

Temporal Recurrent Networks for Online Action Detection

Mingze Xu, Mingfei Gao, Yi-Ting Chen, Larry Davis, David J. Crandall
ICCV 2019
[paper]

Unsupervised Traffic Accident Detection in First-Person Videos

Yu Yao, Mingze Xu, Yuchen Wang, David Crandall, Ella Atkins
IROS 2019
[paper]

Egocentric Vision-based Future Vehicle Localization for Intelligent Driving Assistance Systems

Yu Yao, Mingze Xu, Chiho Choi, David J. Crandall, Ella M. Atkins, Behzad Dariush
ICRA 2019
[paper]

Can Privacy Be Satisfying? On Improving Viewer Satisfaction for Privacy-Enhanced Photos Using Aesthetic Transforms

Rakibul Hasan, Yifang Li, Eman Hassan, Kelly Caine, David J. Crandall, Roberto Hoyle, Apu Kapadia
CHI 2019
[paper]

Active Object Manipulation Facilitates Visual Object Learning: An Egocentric Vision Study

Satoshi Tsutsui, Dian Zhi, Md Alimoor Reza, David Crandall, Chen Yu
EPIC 2019
[paper]

Deepdiary: Lifelogging image captioning and summarization

Chenyou Fan, Zehua Zhang, David Crandall
Journal of Visual Communication and Image Representation 2018
[paper] [website]

Toddler-Inspired Visual Object Learning

Sven Bambach, David Crandall, Linda Smith, Chen Yu
NeurIPS 2018
[paper]

Estimating Head Motion from Egocentric Vision

Satoshi Tsutsui, Sven Bambach, David Crandall, Chen Yu
ICMI 2018
[paper]

Joint Person Segmentation and Identification in Synchronized First- and Third-person Videos

Mingze Xu, Chenyou Fan, Yuchen Wang, Michael Ryoo, David Crandall
ECCV 2018
[paper] [website]

From Coarse Attention to Fine-Grained Gaze: A Two-stage 3D Fully Convolutional Network for Predicting Eye Gaze in First Person Video

Zehua Zhang, Sven Bambach, David Crandall, Chen Yu
BMVC 2018
[paper] [website]

An Egocentric Perspective on Active Vision and Visual Object Learning in Toddlers

Sven Bambach, David Crandall, Linda Smith, Chen Yu
ICDL 2017
[paper]

Identifying first-person camera wearers in third-person videos

Chenyou Fan, Jangwon Lee, Mingze Xu, Krishna Kumar Singh, Yong Jae Lee, David Crandall, Michael Ryoo
CVPR 2017
[paper] [website]

Exploring inter-observer differences in first-person object views using deep learning models

Sven Bambach, Zehua Zhang, David Crandall, Chen Yu
ICCV MBCC 2017
[paper]

Cartooning for enhanced privacy in lifelogging and streaming video

Eman Hassan, Rakibul Hasan, Patrick Shaffer, David Crandall, Apu Kapadia
CVPR CV-COPS 2017 2017
[paper]

Objects in the Center: How the Infant's Body Constrains Infant Scenes

Sven Bambach, Linda Smith, David Crandall, Chen Yu
ICDL 2016
[paper]

Active Viewing in Toddlers Facilitates Visual Object Learning: An Egocentric Vision Approach

Sven Bambach, David Crandall, Linda Smith, Chen Yu
CogSci 2016
[paper]

Lending A Hand: Detecting Hands and Recognizing Activities in Complex Egocentric Interactions

Sven Bambach, Stefan Lee, David Crandall, Chen Yu
ICCV 2015
[paper] [website]

Viewpoint Integration for Hand-Based Recognition of Social Interactions from a First-Person View

Sven Bambach, David Crandall, Chen Yu
ICMI 2015
[paper]

Sensitive Lifelogs: A Privacy Analysis of Photos from Wearable Cameras

Roberto Hoyle, Robert Templeman, Denise Anthony, David Crandall, Apu Kapadia
CHI 2015
[paper]

Challenges in Running Wearable Camera-Related User Studies

Roberto Hoyle, Apu Kapadia, David Crandall
ACM CSCW Workshop on The Future of Networked Privacy 2015
[paper]

Privacy Behaviors of Lifeloggers using Wearable Cameras

Roberto Hoyle, Robert Templeman, Steven Armes, Denise Anthony, David Crandall, Apu Kapadia
UbiComp 2014
[paper] [video]

Detecting Hands in Children's Egocentric Views to Understand Embodied Attention during Social Interaction

Sven Bambach, John Franchak, David Crandall, Chen Yu
CogSci 2014
[paper]

PlaceAvoider: Steering First-Person Cameras away from Sensitive Spaces

Robert Templeman, Mohammed Korayem, David Crandall, Apu Kapadia
NDSS 2014
[paper]

Reactive Security: Responding to Visual Stimuli from Wearable Cameras

Robert Templeman, Roberto Hoyle, David Crandall, Apu Kapadia
Ubicomp UPSIDE Workshop 2014
[paper]

This Hand is MyHand: A Probabilistic Approach to Hand Disambiguation in Egocentric Video

Stefan Lee, Sven Bambach, David Crandall, John M. Franchak, Chen Yu
CVPR Egovision Workshop 2014
[paper]

Understanding Embodied Visual Attention in Child-Parent Interaction

Sven Bambach, David Crandall, Chen Yu
ICDL 2013
[paper]

Egocentric Computer Vision

Egocentric computer vision

IU Computer Vision Lab resources