Projects – Center for Research in Computer Vision

Computer Vision and NLU


	Video Fill In the Blank using LR/RL LSTMs with Spatial-Temporal Attentions Amir Mazaheri, Dong Zhang and Mubarak Shah

Multi-Camera Video Analysis

View All


	ego2Top: Matching Viewers in Egocentric and Top-view Videos (ECCV 2016) Shervin Ardeshir and Ali Borji
	Statistical Inference of Motion in the Invisible Haroon Idrees, Imran Saleemi, Mubarak Shah
	Motion Analysis on CLIF Dataset Vladimir Reilly, Haroon Idrees, Mubarak Shah
	Target Reacquisition in Aerial Videos Saad Ali
	Object Tracking: A Survey Alper Yilmaz, Omar Javed, Mubarak Shah
	Object Tracking Across Uncalibrated Moving Cameras Alper Yilmaz
	Multi-view Tracking in Crowded Scenes Saad M. Khan
	Tracking Across Multiple Moving Airborne Cameras Yaser Sheikh
	Trajectory Association across Non-overlapping Moving Cameras in Planar Scenes Yaser Sheikh, Xin Li, and Mubarak Shah
	Tracking Across Multiple Cameras with Disjointing Views Omar Javed, Zeeshan Rasheed, Khurram Shafique
	Tracking in Multiple Cameras with Overlapping FOV Saad M. Khan, Omar Javed, Zeeshan Rasheed
	Tracking People in Presence of Occlusion Sohaib Khan

Action and Activity Recognition

View All


	Human Action Recognition in Drone Videos using a Few Aerial Training Examples Waqas Sultani and Mubarak Shah
	TinyVIRAT: Low-resolution Video Action Recognition Ugur Demir, Yogesh Singh Rawat and Mubarak Shah
	Gabriella: An Online System for Real-Time Activity Detection in Untrimmed Security Videos Mamshad N Rizve, Ugur Demir, Praveen Tirupattur, Aayush J Rana, Kevin Duarte, Ishan Dave, Yogesh Singh Rawat and Mubarak Shah
	Multi-view Action Recognition using Cross-view Video Prediction Shruti Vyas, Yogesh Singh Rawat and Mubarak Shah
	VideoCapsuleNet: A Simplified Network for Action Detection Kevin Duarte, Yogesh Singh Rawat and Mubarak Shah
	Real-World Anomaly Detection in Surveillance Videos Waqas Sultani, Chen Chen and Mubarak Shah
	An End-to-end 3D Convolutional Neural Network for Action Detection and Segmentation in Videos Rui Hou, Chen Chen and Mubarak Shah
	Unsupervised Action Discovery and Localization in Videos Khurram Soomro and Mubarak Shah
	Tube Convolutional Neutral Network (T-CNN) for Action Detection in Videos Rui Hou, Chen Chen and Mubarak Shah
	Real-Time Temporal Action Localization in Untrimmed Videos by Sub-Action Discovery Rui Hou, Rahul Sukthankar and Mubarak Shah
	Automatic Action Annotation in Weakly Labeled Videos Waqas Sultani and Mubarak Shah
	Unsupervised Action Proposal Ranking through Proposal Recombination Waqas Sultani, Dong Zhang and Mubarak Shah
	Action Localization in Videos through Proposal Recombination Khurram Soomro, Haroon Idrees and Mubarak Shah
	Predicting the Where and What of actors and actions through Online Action Localization Khurram Soomro, Haroon Idrees and Mubarak Shah
	What if we do not have multiple videos of the same action? Video Action Localization Using Web Images Waqas Sultani and Mubarak Shah
	Video Classification using Semantic Concept Co-occurrences Shayan Modiri Assari, Amir Roshan Zamir and Mubarak Shah
	Cross Dataset Action Recognition Waqas Sultani and Mubarak Shah
	Action Recognition By Motion Decomposition Shandong Wu, Omar Oreifej and Mubarak Shah
	DaMN-Discriminative and Mutually Nearest Rui Hou, Amir Roshan Zamir, Rahul Sukthankar and Mubarak Shah
	Recognizing 50 Human Action Categories of Web Videos Kishore Reddy and Mubarak Shah
	HON4D: Histogram of Oriented 4D Normals for Activity Recognition for Depth Sequences Omar Oreifej and Zicheng Liu
	Classifying Web Videos using a Global Video Descriptor Berkan Solmaz, Shayan Modiri and Mubarak Shah
	Matching Trajectories of Anatomical Landmarks under Viewpoint Anthropometric, and Temporal Transforms Alexei Gritai, Yaser Sheikh, Cen Rao and Mubarak Shah
	Human Action Recognition in Videos Using Kinematic Features and Multiple Instance Learning Saad Ali
	KEYS - Incremental Action Recognition Using Feature-Tree Kishore Reddy and Jingen Liu
	Chaotic Invariants for Human Action Recognition Saad Ali and Arslan Basharat
	Action Recognition Using Bag of Video-Words Jingen Liu
	Action Recognition Using Multiple Features Jingen Liu
	Learning Semantic Visual Vocabularies Using Diffusion Distance Jingen Liu and Yang Yang
	Recognizing Realistic Actions from Videos "in the Wild" Jingen Liu and Jiebo Luo
	Learning 4D Action Feature Models for Arbitrary View Action Recognition Pingkun Yan and Saad M. Khan
	Activity Recognition in Groups of People Saad M. Khan
	View-Invariant Representations for Human Activity Recognition Cen Rao
	Monitoring Human Behavior in an Office Environment Douglas Ayers
	Detection of Armed Robbery Jaime Dever
	Person-on-Person Violence Detection in Video Data Ankur Datta
	Monitoring Head/Eye Motion for Driver Alertness with One Camera Raymond Paul Smith
	Monitoring Fast Food Production Richard Russo
	CASEE: A Hierarchical Event Representation for the Analysis of Videos Asaad Hakeem and Yaser Sheikh

Human Detection and Pose Estimation

View All


	Human Pose Estimation in Videos Dong Zhang and Mubarak Shah
	Detecting Humans in Dense Crowd Images Haroon Idrees, Khurram Soomro, Mubarak Shah
	Improving an Object Detector and Extracting Regions using Superpixel Guang Shu, Afshin Dehghan and Mubarak Shah
	Part-based Multiple-Person Tracking Guang Shu, Afshin Dehghan, Omar Oreifej, Emily Hand and Mubarak Shah

Human Re-Identification

View All


	Deep Constrained Dominant Sets for Person Re-Identification Leulseged Tesfaye Alemu, Mubarak Shah and Marcello Pelillo
	Re-Identification of Human in Crowds using Personal, Social and Environmental Constraints Shayan Modiri Assari, Haroon Idrees and Mubarak Shah

Human Mind and Vision

View All


	Deep Learning Human Mind for Automated Visual Classification Concetto Spampinato, S. Palazzo, I. Kavasidis, D. Giordano, Nasim Souly and Mubarak Shah

Few-Shot Learning

View All


	Unsupervised Meta-Learning for Few-Shot Image Classification Siavash Khodadadeh, Ladislau Bölöni and Mubarak Shah
	Iterative Projection and Matching Alireza Zaeemzadeh, Mohsen Joneidi, Nazanin Rahnavard and Mubarak Shah

Tracking

View All


	Multi-Target Tracking in Non-Overlapping Cameras using Fast-Constrained Dominant-sets Yonatan Tariku Tesfaye, Eyasu Zemene, Andrea Prati, Marcello Pelillo and Mubarak Shah
	Visual Tracking: An Experimental Survey Arnold W. M. Smeulders, Dung M. Chu, Rita Cucchiara, Simone Calderara, Afshin Dehghan and Mubarak Shah
	Multiframe Many-Many Point Correspondence for Vehicle Tracking in High Density Wide Area Aerial Videos Imran Saleemi and Mubarak Shah
	Target Identity-aware Network Flow for Online Multiple Target Tracking Afshin Dehghan, Yicong Tian, Philip H.S. Torr and Mubarak Shah
	GMMCP-Tracker: Globally Optimal Generalized Maximum Multi Clique Problem for Multiple Object Tracking Afshin Dehghan, Shayan Modiri Assari and Mubarak Shah
	Video Object Segmentation Dong Zhang, Omar Javed and Mubarak Shah
	Statistical Inference of Motion in the Invisible Haroon Idrees, Imran Saleemi, and Mubarak Shah
	(MP)² T: Multiple People Multiple Parts Tracker Hamid Izadinia , Imran Saleemi, Wenhui Li and Mubarak Shah
	GMCP-Tracker: Global Multi-object Tracking Using Generalized Minimum Clique Graphs Amir Roshan Zamir, Afshin Dehghan and Mubarak Shah
	Part-based Multiple-Person Tracking Guang Shu, Afshin Dehghan, Omar Oreifej, Emily Hand and Mubarak Shah
	Motion Analysis on CLIF Dataset Vladimir Reilly, Haroon Idrees, and Mubarak Shah
	Object Tracking: A Survey Alper Yilmaz, Omar Javed and Mubarak Shah
	Target Reacquisition in Aerial Videos Saad Ali
	Contour Based Object Tracking Alper Yilaz
	Target Tracking in Video Acquired Using Moving FLIR Sensors Alper Yilmaz
	Object Tracking Across Uncalibrated Moving Cameras Alper Yilmaz
	Multi-view Tracking in Crowded Scenes Saad M. Khan
	Tracking Across Multiple Moving Airborne Cameras Yaser Sheikh
	Trajectory Association across Non-overlapping Moving Cameras in Planar Scenes Yaser Sheikh, Xin Li and Mubarak Shah
	Tracking Across Multiple Cameras with Disjointed Views Omar Javed, Zeeshan Rasheed and Khurram Shafique
	Tracking in Multiple Cameras with Overlapping FOV Saad M. Khan, Omar Javed and Zeeshan Rasheed
	Tracking People in Presence of Occlusion Sohaid Khan
	Detection and Target Tracking in FLIR Imagery Alper Yilmaz and Khurram Shafique
	A Non Iterative Greedy Algorithm for Multi-Frame Point Correspondence Khurram Shafique
	Human Body Parts Tracking Alexei Gritai and Arslan Basharat

Video Object Segmentation

View All


	Visual-textual Capsule Routing for Text-based Video Segmentation Bruce McIntosh, Kevin Duarte, Yogesh Singh Rawat, Mubarak Shah
	CapsuleVOS: Semi-Supervised Video Object Segmentation Using Capsule Routing Kevin Duarte, Yogesh Singh Rawat, Mubarak Shah
	Video Object CoSegmentation Dong Zhang,Omar Javed, Mubarak Shah
	Video Object Segmentation Dong Zhang,Omar Javed, Mubarak Shah

Crowd Analysis

View All


	UCF-QNRF - A Large Crowd Counting Data Set Haroon Idrees, Muhammad Tayyab, Kishan Athrey, Dong Zhang,Somaya Al-Maadeed, Nasir Rajpoot and Mubarak Shah
	Detecting Humans in Dense Crowd Images Haroon Idrees, Khurram Soomro and Mubarak Shah
	Counting in Extremely Dense Crowd Images Haroon Idrees, Imran Saleemi, Cody Seibert and Mubarak Shah
	Identifying Behaviors in Crowd Scene Berkan Solmaz, Brain Moore and Mubarak Shah
	Video Scene Understanding Using Multi-scale Analysis Yang Yang, Jingen Liu and Mubarak Shah
	a Streakline Representation of Flow in Crowded Scenes Ramin Mehran, Brian Moore and Mubarak Shah
	Chaotic Invariants of Lagrangian Particle Trajectories for Anomaly Detection in Crowded Scenes Shandong Wu, Brian Moore and Mubarak Shah
	Abnormal Crowd Behavior Detection Using Social Force Models Ramin Mehran and Alexis Oyama
	Crowd Flow Segmentation & Stability Analysis Saad Ali
	Crowd Data Set (Data Set) Dataset used in the CVPR 2007 Paper [22MB] Slides of the Talk Given at CVPR 2007 [57MB] Dataset used in the CVPR 2007 Paper [22MB] Complete Dataset [128MB]
	Floor Fields for Tracking in High Density Crowds Saad Ali
	Learning Motion Patterns in Crowded Scenes Using Motion Flow Field Min Hu and Saad Ali
	Detecting Global Motion Patterns in Complex Videos Min Hu and Saad Ali
	Statistical Learning of Motion Patterns Imran Saleemi and Lance Hartung

Motion Patterns

View All


	Multi-agent Event Recognition by Preservation of Spatiotemporal Relationships Between Probabilistic Models Salman Khokhar, Imran Saleemi and Mubarak Shah
	Statistical Inference of Motion in the Invisible Haroon Idrees, Imran Saleemi and Mubarak Shah
	Discovering Motion Primitives for Unsupervised Grouping and One-shot Learning of Human Actions, Gestures, and Expressions Yang Yang, Imran Saleemi and Mubarak Shah
	Motion Pattern Matching Using Divergence Minimization Salman Khokhar
	Scene Understanding by Statistical Modeling of Motion Patterns Imran Saleemi and Lance Hartung
	Modeling Traffic Patterns for Vision based Surveillance Applications Imran Saleemi, Khurram Shafique and Mubarak Shah
	Learning Motion Patterns in Crowded Scenes Using Motion Flow Field Min Hu and Saad Ali
	Detecting Global Motion Patterns in Complex Videos Min Hu and Saad Ali
	Learning Scene Model from Surveillance Videos Arslan Basharat
	Video Scene Understanding Using Multi-scale Analysis Yang Yang, Jingen Liu and Mubarak Shah

UAV Video Analysis

View All


	Fully Convolutional Deep Neural Networks for Persistent Multi-Object Detection in Wide Area Aerial Videos Rodney Lalonde, Dong Zhang and Mubarak Shah
	Autonomous Navigation for Low-Altitude UAVs in urban areas Thomas Castelli, Aidean Sharghi, Don Harper, Alain Tremeau and Mubarak Shah
	Multiframe Many-Many Point Correspondence for Vehicle Tracking in High Density Wide Area Aerial Videos Imran Saleemi and Mubarak Shah
	Geometric Constraints for Human Detection in Aerial Imagery Vladimir Reilly, Berkan Solmaz and Mubarak Shah
	Motion Analysis on CLIF Dataset Vladimir Reilly, Haroon Idrees and Mubarak Shah
	COCOA: Alignment, Object Detection, Object Tracking and Indexing of Aerial Videos Saad Ali, Yaser Sheikh, Min Hu and Paul Scavanner
	Landing a UAV on a Runway Using Image Registration Andrew Miller and Don Harper
	Target Reacquisition in Aerial Videos Saad Ali
	Detection and Target Tracking in FLIR Imagery Alper Yilmaz and Khurram Shafique
	Autonomous Vision Based Navigation of a UAV Fahd Rafi, Don Harper and Saad Masood Khan

High Level Computer Vision

View All


	Ontology and Taxonomy Collaborated Framework for Meeting Classification Asaad Hakeem and Mubarak Shah
	Video Retrieval Utilizing Semantic Word Similarity Measures Yusuf Aytar, Jiebo Luo and Mubarak Shah
	Semantic Linkage of News Stories Yun Zhai
	Movie Genre Classification from Previews Zeeshan Rasheed
	CASEE: A Hierarchical Event Representation for the Analysis of Videos Asaad Hakeem and Yaser Sheikh

Object Detection and Scene Segmentation

View All


	Improved Scene Identification and Object Detection on Egocentric Vision of Daily Activities Gonzalo Vaca-Castano, Samarjit Das, Joao P. Sousa, Niels D. Lobo and Mubarak Shah
	Scene Labeling Using Sparse Precision Matrix Nasim Souly and Mubarak Shah
	Improving an Object Detector and Extracting Regions using Superpixel Guang Shu, Afshin Dehghan and Mubarak Shah
	Independently Moving Objects Detection in Non-Planar Scenes using Multi-Frame Monocular Epipolar Constraint Soumyabrata Dey, Vladimir Reilly, Imran Saleemi and Mubarak Shah
	Audio source localization and audio-visual synchronization using CCA Hamid Izadinia, Imran Saleemi and Mubarak Shah
	Simultaneous Video Stabilization and Moving Object Detection in Turbulence Omar Oreifej, Xin Li and Mubarak Shah
	Geometric Constraints for Human Detection in Aerial Imagery Vladimir Reilly, Berkan Solmaz and Mubarak Shah
	Human Identity Recognition in Aerial Images Omar Oreifej, Ramin Mehran and Mubarak Shah
	3D Model based Object Detection Pingkun Yan and Saad M. Khan
	Learning Scene Model from Surviellance Arslan Basharat
	Background Modeling Mubarak Shah
	Scene Understanding and Classification Jingen Liu
	Detecting and Segmenting Humans in Crowded Scenes Mikel Rodgriguez
	A Supervised Learning Framework for Generic Object Detection in Images Saad Ali
	Online Detection and Classification of Moving Objects Using Progressively Improving Detectors Omar Javed and Saad Ali
	Modeling Traffic Patterns for Vision based Surviellance Applications Imran Saleemi, Khurram Shafique and Mubarak Shah

Exploiting Multiple View Data for Tracking, Reconstruction & Recognition

View All


	Image Based 3D Reconstruction Saad M. Khan and Pingkun Yan
	3D Model based Object Detection Pingkun Yan and Saad M. Khan

Adversarial Attacks

View All


	Odyssey: Creation, Analysis and Detection of Trojan Models Marzieh Edraki, Nazmul Karim, Nazanin Rahnavard, Ajmal Mian and Mubarak Shah

Biomedical Image Analysis

View All


	Brain Tumor Detection Segmentation Kishore Reddy
	Automatic Identification of ADHD Subjects using functional Magnetic Resonance Imaging(fMRI) Data Soumyabrata Dey
	3D MRA Image Segmentation using Capillary Active Contour Pingkun Yan
	Segmentation of Neighboring Organs in Medical Image with Model Competition Pingkun Yan
	Segmentation of High Throughput RNAi Fluorescent Cellular Images Pingkun Yan
	Automatic Tracking of Escherichia Coli Bacteria Jun Xie and Shahid Khan

Geospatial Localization/Registration

View All


	GAMa: Cross-view Video Geo-localization Shruti Vyas, Chen Chen and Mubarak Shah
	Large-scale Image Geo-Localization Using Dominant Sets Eyasu Zemene, Yonatan Tariku Tesfaye, Haroon Idrees, Andrea Prati, Marcello Pelillo and Mubarak Shah
	Bridging the Domain Gap for Ground-to-Aerial Image Matching Krishna Regmi and Mubarak Shah
	Cross-View Image Matching for Geo-localization in Urban Environments Yicong Tian, Chen Chen and Mubarak Shah
	Geo-Semantic Segmentation Shervin Ardeshir and Kofi Malcolm Collins-Sibley
	Google Street View Data Set Amir Roshan Zamir
	GPS Tag Refinement Using Random Walks and Adaptive Damping Amir Roshan Zamir, Afshin Dehghan and Shervin Ardeshir
	GIS-Assisted Object Detection and Geospatial Localization Amir Roshan Zamir, Afshin Dehghan and Shervin Ardeshir
	Image Geo-Localization Based on Multiple Nearest Neighbor Feature Matching Using Generalized Graphs Amir Roshan Zamir
	Visual Business Recognition - A Multimodal Approach Amir Roshan Zamir
	City Scale Geo-Spatial Trajectory Estimation of a Moving Camera Gonzalo Vaca
	Geo-Spatial Localization Using Google Street View Amir Roshan Zamir
	ICCV Challenge Contest Where Am I Asaad Hakeem, Arslan Basharat, Saad M. Khan and Fahd Rafi
	Route Panoramas and Localization Saad M. Khan and Fahd Rafi
	Video Registration Mubarak Shah and Rakesh Kumar, Kluwer Academic Publishers, 2003
	Geo-Registration of Aerial Images Yaser Sheikh and Sohaib Khan
	Missile Route Planning using Image based GPS Localization Saad Ali
	Layer-Based Video Registration Jiangjian Xiao

Video Categorization, Retrieval and Temporal Segmentation

View All


	Visual Saliency Detection Using Group Lasso Regularization in Videos of Natural Scenes Nasim Souly and Mubarak Shah
	Semantic Image Search from Multiple Query Images Gonzalo Vaca
	Complex Events Detection using Data-driven Concepts Yang Yang and Mubarak Shah
	Video Matching Using Spatiotemporal Volumes Arslan Basharat and Mubarak Shah
	Time Series Prediction by Chaotic Modeling of Nonlinear Dynamical Systems Arslan Basharat
	Scene Segmentation of Video Sequences Yun Zhai
	Story Detection in News Videos Yun Zhai
	Scene Structuring in Continuously Recorded Videos Yun Zhai
	Spatiotemporal Visual Attention Detection Yun Zhai
	Movie Scene Classification using Finite State Machines Yun Zhai
	Relevance Feedback Using Keyword and Region-Based Refinement Yun Zhai
	Semantic Linkage of News Stories Yun Zhai
	Segmentation of Interview Videos Omar Javed, Sohaib Khan and Zeeshan Rasheed
	Video Segmentation through Com bination of Features Sohaib Khan
	Shot Detection using Principle Coordinate System Alper Yilmaz
	Movie Genre Classification from Previews Zeeshan Rasheed
	Scene Boundary Detection in Hollywood Movies and TV Show Zeeshan Rasheed

Multimedia Event Detection

View All


	Temporal Dynamixs between Concepts in Complex Events Yang Zhang, Boqing Gong and Mubarak Shah
	Video Classification using Semantic Concept Co-occurences Shayan Modiri Assari, Amir Roshan Zamir and Mubarak Shah
	Temporal Dynamics between Concepts in Complex Events Mahdi Kalayeh, Subhabrata Bhattacharya , Rahul Sukthankar and Mubarak Shah
	Complex Events Detection using Data-driven Concepts Yang Yang and Mubarak Shah

Shape from Shading

View All


	Papers on Shape from Shading

View Morphing

View All


	Motion Layer Extraction in the Presence of Occlusion using Graph Cuts Jiang Jian Xiao
	Motion Layer Segmentation and Matting Jiang Jian Xiao
	Dynamic View Morphing Jiang Jian Xiao
	Two-Frame Wide Baseline Matching Jiang Jian Xiao
	Triview Morphing Jiang Jian Xiao

Facial Analysis

View All


	Who's Your Daddy? Afshin Dehghan, Enrique G. Ortiz, Ruben Villegas and Mubarak Shah
	Web-Scale Face Recognition Enrique G. Ortiz, Brian C. Becker
	Video Face Recognition Enrique G. Ortiz, Alan Wright and Mubarak Shah
	Automatic Feature Detection and Pose Recovery for Faces Alper Yilmaz
	Estimation of rigid and non-rigid facial motion using anatomical face model Alper Yilmaz, Khurram Shafique

Computational Visual Aesthetics

View All


	Enhancing and Assessing Photo Quality: Compositional Perspective Subhabrata Bhattacharya, Rahul Sukthankar, Mubarak Shah
	Computational Model for Aesthetic Assessment of Videos Subhabrata Bhattacharya, Behnaz Nojavanasgheri, Mubarak Shah

Computer Vision Systems

View All


	KEYS Kishore Reddy and Jingen Liu
	COCOA: Alignment, Object Detection, Object Tracking and Indexing of Aerial Videos Saad Ali, Yaser Sheikh, Min hu and Paul Scovanner
	PEGASUS Yun Zhai and Jingen Liu
	KNIGHT: Real Time Automated Surveillance System Omar Javed
	HAWK - Video based Vehicle Speed Computation Janaka Liyanage and Mubarak Shah

Miscellaneous

View All


	SPatiotemporal REgularity Flow (SPREF) Orkun Alatas
	Seeing Through Water Omar Oreifej
	MinGPU: A minimum GPU library for Computer Vision Pavel Babenko
	Fire Dectection in Video Sequences Walter 'Rusty' Phillips
	A Vision-Based System for a UGV to Handle a Road Intersection Javed Ahmed, Mubarak Shah, Andrew Miller, Don Harper, M. N. Jafri