Jianbo Shi
Professor, CIS
Jianbo’s group is developing vision algorithms for both human and image recognition. Their ultimate goal is to develop computation algorithms to understand human behavior and interaction with objects in video, and to do so at multiple levels of abstractions: from the basic body limb tracking, to human identification, gesture recognition, and activity inference. Jianbo and his group are working to develop a visual thinking model that allows computers not only to understand their surroundings, but also to achieve higher level cognitive abilities such as machine memory and learning.
Startups
Publications
Publisher IEEE Winter Conference on Applications of Computer Vision (WACV)
Enhanced generative adversarial network for 3D brain MRI super-resolution
Publisher IEEE Winter Conference on Applications of Computer Vision (WACV)
Force from Motion: Decoding Control Force of Activity in a First-Person Video
Publisher IEEE Transactions on Pattern Analysis and Machine Intelligence
FoveaBox: Beyound Anchor-based Object Detection
Publisher IEEE Transactions on Image Processing
Publisher Imaging Informatics for Healthcare, Research, and Applications
Multimodal image outpainting with regularized normalized diversification
Publisher IEEE Winter Conference on Applications of Computer Vision (WACV)
Nested Scale-Editing for Conditional Image Synthesis
Publisher IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR)
Adversarial structure matching for structured prediction tasks
Publisher IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR)
Consistent optimization for single-shot object detection
Publisher arXiv
Neural Embedding for Physical Manipulations
Publisher arXiv
Publisher IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR)
Publisher Angewandte Chemie
SegSort: Segmentation by discriminative sorting of segments
Publisher IEEE International Conference on Computer Vision (ICCV)
Trajectory Normalized Gradients for Distributed Optimization
Publisher arXiv
Zoom-in-to-check: Boosting video interpolation via instance-level discrimination
Publisher IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR)
Egocentric Basketball Motion Planning from a Single First-Person Image
Publisher IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR)
Learning discriminative motion features through detection
Publisher arXiv
Object detection in video with spatiotemporal sampling networks
Publisher Lecture Notes in Computer Science (LNCS)
Am i a Baller? Basketball Performance Assessment from First-Person Videos
Publisher IEEE International Conference on Computer Vision (ICCV)
Connecting the dots: Embodied visual perception from first-person cameras
Publisher IAPR International Conference on Machine Vision Applications (MVA)
Convolutional random walk networks for semantic image segmentation
Publisher IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR)
Customizing First Person Image Through Desired Actions
Publisher arXiv
First-person action-object detection with EgoNet
Publisher Robotics: Science and Systems (RSS)
Local perturb-and-MAP for structured prediction
Publisher International Conference on Artificial Intelligence and Statistics (AISTATS)
Motion-Based Temporal Alignment of Independently Moving Cameras
Publisher IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)
Predicting behaviors of basketball players from first person videos
Publisher IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR)
Synchronization of Video Sequences Through 3D Trajectory Reconstruction
Publisher Zidonghua Xuebao/Acta Automatica Sinica
Unsupervised Learning of Important Objects from First-Person Videos
Publisher IEEE International Conference on Computer Vision (ICCV)
Using Cross-Model EgoSupervision to Learn Cooperative Basketball Intention
Publisher IEEE International Conference on Computer Vision Workshops (ICCVW)
Publisher Lecture Notes in Computer Science (LNCS)
Egocentric future localization
Publisher IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR)
First person action-object detection with egonet
Publisher arXiv
Force from Motion: Decoding Physical Sensation in a First Person Video
Publisher IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR)
Integrated intelligence for human-robot teams
Publisher International Symposium on Experimental Robotics (ISER)
Rich Representations with Exposed Semantics for Deep Visual Reasoning
Publisher Carnegie Melon University Pittsburgh United States
Semantic Segmentation with Boundary Neural Fields
Publisher IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR)
Social behavior prediction from first person videos
Publisher arXiv
DeepEdge: A multi-scale bifurcated deep network for top-down contour detection
Publisher IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR)
Exploiting egocentric object prior for 3d saliency detection
Publisher arXiv
Future Localization from an Egocentric Depth Image
Publisher arXiv
Publisher IEEE International Conference on Computer Vision (ICCV)
Publisher IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR)
News
Faculty News
Profs at Penn’s GRASP Lab snagged Toyota Research Institute funding for robotics research
February 1, 2021
Faculty News
Penn Engineers Join Honda Research Institute’s ‘Curious Minded Machine’ Project
October 25, 2018
GRASP News
“Penn Engineering Offers an Online MicroMasters in Robotics” in Penn Engineering
February 28, 2017
GRASP News
Why 10 District teachers spent their summer doing grad-level STEM research
August 24, 2016
GRASP News
July 14, 2015
Students
Alumni
PhD, CIS '13 - JPMorgan Chase Assistant Professor, Machine Learning Department, CMU