Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for David Crandall

Controlling the Quality of Distillation in Response-Based Network Compression


Dec 19, 2021
Vibhas Vats, David Crandall

* AAAI22-Workshop: 1st International Workshop on Practical Deep Learning in the Wild 

  Access Paper or Ask Questions

Polyline Based Generative Navigable Space Segmentation for Autonomous Visual Navigation


Oct 29, 2021
Zheng Chen, Zhengming Ding, David Crandall, Lantao Liu


  Access Paper or Ask Questions

Ego4D: Around the World in 3,000 Hours of Egocentric Video


Oct 13, 2021
Kristen Grauman, Andrew Westbury, Eugene Byrne, Zachary Chavis, Antonino Furnari, Rohit Girdhar, Jackson Hamburger, Hao Jiang, Miao Liu, Xingyu Liu, Miguel Martin, Tushar Nagarajan, Ilija Radosavovic, Santhosh Kumar Ramakrishnan, Fiona Ryan, Jayant Sharma, Michael Wray, Mengmeng Xu, Eric Zhongcong Xu, Chen Zhao, Siddhant Bansal, Dhruv Batra, Vincent Cartillier, Sean Crane, Tien Do, Morrie Doulaty, Akshay Erapalli, Christoph Feichtenhofer, Adriano Fragomeni, Qichen Fu, Christian Fuegen, Abrham Gebreselasie, Cristina Gonzalez, James Hillis, Xuhua Huang, Yifei Huang, Wenqi Jia, Weslie Khoo, Jachym Kolar, Satwik Kottur, Anurag Kumar, Federico Landini, Chao Li, Yanghao Li, Zhenqiang Li, Karttikeya Mangalam, Raghava Modhugu, Jonathan Munro, Tullie Murrell, Takumi Nishiyasu, Will Price, Paola Ruiz Puentes, Merey Ramazanova, Leda Sari, Kiran Somasundaram, Audrey Southerland, Yusuke Sugano, Ruijie Tao, Minh Vo, Yuchen Wang, Xindi Wu, Takuma Yagi, Yunyi Zhu, Pablo Arbelaez, David Crandall, Dima Damen, Giovanni Maria Farinella, Bernard Ghanem, Vamsi Krishna Ithapu, C. V. Jawahar, Hanbyul Joo, Kris Kitani, Haizhou Li, Richard Newcombe, Aude Oliva, Hyun Soo Park, James M. Rehg, Yoichi Sato, Jianbo Shi, Mike Zheng Shou, Antonio Torralba, Lorenzo Torresani, Mingfei Yan, Jitendra Malik


  Access Paper or Ask Questions

Applying the Case Difference Heuristic to Learn Adaptations from Deep Network Features


Jul 15, 2021
Xiaomeng Ye, Ziwei Zhao, David Leake, Xizi Wang, David Crandall

* 7 pages, 2 figures, 1 table. To be published in the IJCAI-21 Workshop on Deep Learning, Case-Based Reasoning, and AutoML: Present and Future Synergies 

  Access Paper or Ask Questions

A Survey on Deep Learning Technique for Video Segmentation


Jul 02, 2021
Wenguan Wang, Tianfei Zhou, Fatih Porikli, David Crandall, Luc Van Gool


  Access Paper or Ask Questions

Reverse-engineer the Distributional Structure of Infant Egocentric Views for Training Generalizable Image Classifiers


Jun 12, 2021
Satoshi Tsutsui, David Crandall, Chen Yu

* Accepted to 2021 CVPR Workshop on Egocentric Perception, Interaction and Computing (EPIC) 

  Access Paper or Ask Questions

How to Accelerate Capsule Convolutions in Capsule Networks


Apr 06, 2021
Zhenhua Chen, Xiwen Li, Qian Lou, David Crandall


  Access Paper or Ask Questions

Hierarchically Decoupled Spatial-Temporal Contrast for Self-supervised Video Representation Learning


Nov 23, 2020
Zehua Zhang, David Crandall


  Access Paper or Ask Questions

Whose hand is this? Person Identification from Egocentric Hand Gestures


Nov 17, 2020
Satoshi Tsutsui, Yanwei Fu, David Crandall

* Accepted to IEEE Winter Conference on Applications of Computer Vision (WACV) 2021 (First round acceptance) 

  Access Paper or Ask Questions

Deep Tiered Image Segmentation forDetecting Internal Ice Layers in Radar Imagery


Oct 08, 2020
Yuchen Wang, Mingze Xu, John Paden, Lora Koenig, Geoffrey Fox, David Crandall

* first version 

  Access Paper or Ask Questions

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


Jun 04, 2020
Satoshi Tsutsui, Arjun Chandrasekaran, Md Alimoor Reza, David Crandall, Chen Yu

* Accepted by Annual Conference of the Cognitive Science Society (CogSci) 2020. (Oral Acceptance Rate = 177/811 = 22%) 

  Access Paper or Ask Questions

When, Where, and What? A New Dataset for Anomaly Detection in Driving Videos


Apr 06, 2020
Yu Yao, Xizi Wang, Mingze Xu, Zelin Pu, Ella Atkins, David Crandall

* 23 pages, 11 figures, 6 tables 

  Access Paper or Ask Questions

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


Mar 31, 2020
Bardia Doosti, Shujon Naha, Majid Mirbagheri, David Crandall

* IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 

  Access Paper or Ask Questions

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


Mar 12, 2020
Zehua Zhang, Ashish Tawari, Sujitha Martin, David Crandall

* Accepted by ICRA 2020 

  Access Paper or Ask Questions

Learning Video Object Segmentation from Unlabeled Videos


Mar 10, 2020
Xiankai Lu, Wenguan Wang, Jianbing Shen, Yu-Wing Tai, David Crandall, Steven C. H. Hoi

* Accepted to CVPR 2020. Code: https://github.com/carrierlxk/MuG 

  Access Paper or Ask Questions

Zero-Shot Video Object Segmentation via Attentive Graph Neural Networks


Jan 19, 2020
Wenguan Wang, Xiankai Lu, Jianbing Shen, David Crandall, Ling Shao

* ICCV2019(Oral) 
* ICCV2019(Oral). Website: https://github.com/carrierlxk/AGNN 

  Access Paper or Ask Questions

P-CapsNets: a General Form of Convolutional Neural Networks


Dec 18, 2019
Zhenhua Chen, Xiwen Li, Chuhua Wang, David Crandall


  Access Paper or Ask Questions

Meta-Reinforced Synthetic Data for One-Shot Fine-Grained Visual Recognition


Nov 17, 2019
Satoshi Tsutsui, Yanwei Fu, David Crandall

* Accepted by Conference on Neural Information Processing System 2019 

  Access Paper or Ask Questions

A Self Validation Network for Object-Level Human Attention Estimation


Oct 31, 2019
Zehua Zhang, Chen Yu, David Crandall

* Accepted by NeurIPS 2019 

  Access Paper or Ask Questions

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


Jun 04, 2019
Satoshi Tsutsui, Dian Zhi, Md Alimoor Reza, David Crandall, Chen Yu

* Accepted at 2019 CVPR Workshop on Egocentric Perception, Interaction and Computing (EPIC) 

  Access Paper or Ask Questions

Embodied Visual Recognition


Apr 09, 2019
Jianwei Yang, Zhile Ren, Mingze Xu, Xinlei Chen, David Crandall, Devi Parikh, Dhruv Batra

* 14 pages, 13 figures, technical report 

  Access Paper or Ask Questions

Unsupervised Domain Adaptation using Generative Models and Self-ensembling


Dec 02, 2018
Eman T. Hassan, Xin Chen, David Crandall


  Access Paper or Ask Questions

Diverse Beam Search: Decoding Diverse Solutions from Neural Sequence Models


Oct 22, 2018
Ashwin K Vijayakumar, Michael Cogswell, Ramprasath R. Selvaraju, Qing Sun, Stefan Lee, David Crandall, Dhruv Batra

* 16 pages; accepted at AAAI 2018 

  Access Paper or Ask Questions

Generalized Capsule Networks with Trainable Routing Procedure


Aug 27, 2018
Zhenhua Chen, David Crandall


  Access Paper or Ask Questions

Detecting Small, Densely Distributed Objects with Filter-Amplifier Networks and Loss Boosting


May 07, 2018
Zhenhua Chen, David Crandall, Robert Templeman

* rejected by a conference 

  Access Paper or Ask Questions

A Data Driven Approach for Compound Figure Separation Using Convolutional Neural Networks


Aug 21, 2017
Satoshi Tsutsui, David Crandall

* Accepted to The International Conference on Document Analysis and Recognition (ICDAR) 2017 

  Access Paper or Ask Questions

Using Artificial Tokens to Control Languages for Multilingual Image Caption Generation


Jun 20, 2017
Satoshi Tsutsui, David Crandall

* This work appears as an Extended Abstract at the 2017 CVPR Language and Vision Workshop 

  Access Paper or Ask Questions

A Hybrid Supervised-unsupervised Method on Image Topic Visualization with Convolutional Neural Network and LDA


Apr 09, 2017
Kai Zhen, Mridul Birla, David Crandall, Bingjing Zhang, Judy Qiu

* 9 pages, 9 figures 

  Access Paper or Ask Questions

Stochastic Multiple Choice Learning for Training Diverse Deep Ensembles


Oct 05, 2016
Stefan Lee, Senthil Purushwalkam, Michael Cogswell, Viresh Ranjan, David Crandall, Dhruv Batra


  Access Paper or Ask Questions

Sentiment/Subjectivity Analysis Survey for Languages other than English


Aug 25, 2016
Mohammed Korayem, Khalifeh Aljadda, David Crandall

* This is an accepted version in Social Network Analysis and Mining journal. The final publication will be available at Springer via http://dx.doi.org/10.1007/s13278-016-0381-6 

  Access Paper or Ask Questions