Filters








38 Hits in 3.5 sec

Image and Video Retargetting by Darting [chapter]

Matthew Brand
2009 Lecture Notes in Computer Science  
with gaps filled by a rudimentary form of texture synthesis; temporal video summarization by "packing" motion in time; and an extension to spatial video retargetting that avoids motion artifacts by preserving  ...  with gaps filled by a rudimentary form of texture synthesis; temporal video summarization by "packing" motion in time; and an extension to spatial video retargetting that avoids motion artifacts by preserving  ...  Video retargetting These methods are particularly suitable for spatially darting an XYT video volume.  ... 
doi:10.1007/978-3-642-02611-9_4 fatcat:lqh7b5zkjvhvznf5yrcux7bjoe

DexPilot: Vision Based Teleoperation of Dexterous Robotic Hand-Arm System [article]

Ankur Handa, Karl Van Wyk, Wei Yang, Jacky Liang, Yu-Wei Chao, Qian Wan, Stan Birchfield, Nathan Ratliff, Dieter Fox
2019 arXiv   pre-print
The videos of the experiments can be found at https://sites.google.com/view/dex-pilot.  ...  Herein, a low-cost, vision based teleoperation system, DexPilot, was developed that allows for complete control over the full 23 DoA robotic system by merely observing the bare human hand.  ...  We generate new images by shifting the original image by random shifts and pass them all through the network in one batch.  ... 
arXiv:1910.03135v2 fatcat:qhhkpmouhbhljma5zfysdjcyte

Learning a Shared Shape Space for Multimodal Garment Design [article]

Tuanfeng Y. Wang and Duygu Ceylan and Jovan Popovic and Niloy J. Mitra
2018 arXiv   pre-print
Instead, we present a data-driven approach wherein the user directly indicates desired fold patterns simply by sketching while our system estimates corresponding garment and body shape parameters at interactive  ...  This requires time and experience.  ...  due to wrinkles and folds to the coarse meshes captured from the multi-view video input.  ... 
arXiv:1806.11335v2 fatcat:dzjya3hu2nfvbph5ok7j6gik4y

ContactGrasp: Functional Multi-finger Grasp Synthesis from Contact [article]

Samarth Brahmbhatt, Ankur Handa, James Hays, Dieter Fox
2019 arXiv   pre-print
Grasping and manipulating objects is an important human skill. Since most objects are designed to be manipulated by human hands, anthropomorphic hands can enable richer human-robot interaction.  ...  Our contact representation is object-centric and allows functional grasp synthesis even for hand models different than the one used for demonstration.  ...  video for other objects).  ... 
arXiv:1904.03754v3 fatcat:q4vvfyokjzbl3oqqknlk4psjx4

A Survey on Deep Learning for Skeleton-Based Human Animation [article]

L. Mourot, L. Hoyet, F. Le Clerc, François Schnitzler
2021 arXiv   pre-print
Human character animation is often critical in entertainment content production, including video games, virtual reality or fiction films.  ...  research to alleviate current limitations and meet animators' needs.  ...  Acknowledgements This work was supported by the European Commission under European Horizon 2020 Programme, grant number 951911 -AI4Media. Acronyms  ... 
arXiv:2110.06901v1 fatcat:abppln4rbbeufiw4z6a3wnk7oy

Author Index

2010 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition  
Model Mixing 3D and 2D Primitives for View Invariant Object Recognition Hu, Xiaoyan Evaluation of Stereo Confidence Indoors and Outdoors Hu, Yiqun Hybrid Shift Map for Video Retargeting Hu, Zhanyi Line  ...  Seam-Carving for Video Retargeting Player Localization Using Multiple Static Cameras for Sports Visualization Efficient Hierarchical Graph-Based Video Segmentation Grzeszczuk, Radek Unified Real-Time  ... 
doi:10.1109/cvpr.2010.5539913 fatcat:y6m5knstrzfyfin6jzusc42p54

Real-time Physics-based Motion Capture with Sparse Sensors

Sheldon Andrews, Ivan Huerta, Taku Komura, Leonid Sigal, Kenny Mitchell
2016 Proceedings of the 13th European Conference on Visual Media Production (CVMP 2016) - CVMP 2016  
An inverse dynamics solver and physics-based body model are used, ensuring physical plausibility by computing joint torques and contact forces.  ...  An inverse dynamics solver generates motion that satisfies the orientation and position constraints introduced by the sensors, as well as pose constraints from the motion prior.  ...  This work was funded by the Innovate UK project "Real-time Digital Acting" (# 101857).  ... 
doi:10.1145/2998559.2998564 dblp:conf/cvmp/AndrewsCKSM16 fatcat:op5eyryidbe3faysro2qyv7jbq

The human motion database: A cognitive and parametric sampling of human motion

Gutemberg Guerra-Filho, Arnab Biswas
2011 Face and Gesture 2011  
Calibration is required by a motion capture system to compute the extrinsic (position and orientation) properties and the intrinsic properties (focal length, geometric image distortion) of cameras [9]  ...  Retargeting Retargeting is the problem of adapting the motion performed by one subject to consider the articulated figure of another target subject that is structurally different from the source subject  ... 
doi:10.1109/fg.2011.5771381 dblp:conf/fgr/Guerra-FilhoB11 fatcat:ofsk4cxlqzeopbizth4k2hez4u

Adaptive Scratch Pad Memory Management for Dynamic Behavior of Multimedia Applications

Doosan Cho, S. Pasricha, I. Issenin, N.D. Dutt, Minwook Ahn, Yunheung Paek
2009 IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems  
These types of applications are normally hard to optimize by static compiler optimizations. The reason is that their behavior stays unknown until runtime and may even change during computation.  ...  Guided by compiler analysis for generating scratch pad data layouts and hardware components for tracking dynamic memory accesses, the scratch pad data layout adapts to an input data pattern with the help  ...  In these works, the authors identify the reused block or tile which is accessed through indirectly indexed arrays in video/image processing applications.  ... 
doi:10.1109/tcad.2009.2014002 fatcat:dhlcctxwxjavdehpujptcgacdm

Toolkit Support for Integrating Physical and Digital Interactions

Scott Klemmer, James Landay
2009 Human-Computer Interaction  
There is great potential in enabling users to interact with digital information by integrating it with everyday physical objects.  ...  Papier-Mâché's input architecture is inspired by software design patterns for handling input in GUIs. Model-View-Controller (MVC) is the predominant software design pattern for developing GUIs.  ...  We thank James Lin, Jack Li, and Andy Kung for their implementation assistance. Authors  ... 
doi:10.1080/07370020902990428 fatcat:6tfjqtuxdfgudd6ermcp5nls5u

Contact Transfer: A Direct, User-Driven Method for Human to Robot Transfer of Grasps and Manipulations [article]

Arjun Lakshmipathy, Dominik Bauer, Cornelia Bauer, Nancy S. Pollard
2022 arXiv   pre-print
Finally, we demonstrate a solution generated by our method on a physical, custom designed prosthetic hand.  ...  morphology or kinematics, and allows user control over both transfer parameters and solution optimization.  ...  All simulations were conducted using the Dynamic Animation and Robotics Toolkit (DART) [43] . A.  ... 
arXiv:2110.15532v2 fatcat:kek3raimove2dbyferkrwypg5u

Learning to Correspond Dynamical Systems [article]

Nam Hee Kim, Zhaoming Xie, Michiel van de Panne
2020 arXiv   pre-print
Many dynamical systems exhibit similar structure, as often captured by hand-designed simplified models that can be used for analysis and control.  ...  We demonstrate the approach using pairs of controlled bipedal walkers, as well as by pairing a walker with a controlled pendulum.  ...  These systems are simulated with DART (Lee et al., 2018) . The neural networks and learning algorithms are implemented in PyTorch (Steiner et al., 2019) .  ... 
arXiv:1912.03015v3 fatcat:75brccd7zrftvkw4a5qs7jouay

Content Creation and Authoring Challenges for Virtual Environments: From User Interfaces to Autonomous Virtual Characters [chapter]

Ralf Dörner, Marcelo Kallmann, Yazhou Huang
2015 Lecture Notes in Computer Science  
One highly relevant use case is the definition of motions to be executed by virtual characters.  ...  How is behavior and motion in VEs specified? How are user interfaces designed and implemented for VEs? Authoring is a crucial aspect for using VEs successfully.  ...  This is similar to recording video sequences from a video camera and preparing the sequences for later editing.  ... 
doi:10.1007/978-3-319-17043-5_11 fatcat:66wvzhtvvrbrbgkfcjtqwv5ftm

Introduction to deep learning [article]

Lihi Shiloh-Perl, Raja Giryes
2020 arXiv   pre-print
It includes both the basic structures used to design deep neural networks and a brief survey of some of its popular use cases.  ...  1.2 Million images for training and 150000 images for testing.  ...  Classification and localization: The main object in the image is detected and then localized by a surrounding bounding box and classified from a pre-known set. 2.  ... 
arXiv:2003.03253v1 fatcat:65ywiu2wlzcgvgkaqco2hpe3ve

Translation and Clinical Development of Bispecific T-cell Engaging Antibodies for Cancer Treatment

T Yuraszeck, S Kasichayanula, JE Benjamin
2017 Clinical Pharmacology and Therapeutics  
Herein we review the pharmacology, safety, and efficacy observed in studies of blinatumomab and other BiTE V R antibody constructs.  ...  Bispecific T-cell Engagers (BiTE V R ) antibody constructs enable a polyclonal T-cell response to cell-surface tumor-associated antigens, bypassing the narrow specificities of T-cell receptors and the  ...  then injected intravenously with 89 Zr-AMG 110 and imaged with positron emission tomography (PET).  ... 
doi:10.1002/cpt.651 pmid:28182247 pmcid:PMC5763312 fatcat:hp6ax7rzxjcmdlozdkakfjhwyi
« Previous Showing results 1 — 15 out of 38 results