Filters








21,509 Hits in 6.0 sec

Crowd Tracking with Dynamic Evolution of Group Structures [chapter]

Feng Zhu, Xiaogang Wang, Nenghai Yu
2014 Lecture Notes in Computer Science  
Patches are tracked together through occlusions with spatial constraints imposed by hierarchical tree structures within groups.  ...  Keypoint tracking guides the generation of patches with stable internal motions, and also organizes patches into hierarchical groups with collective motions.  ...  Patches are tracked together with the spatial constraints added by the dynamic hierarchical tree structures (Section 3.3).  ... 
doi:10.1007/978-3-319-10599-4_10 fatcat:f7z4gtuq55emrpngeodulb5mju

Evolutionary Bayesian Rose Trees

Shixia Liu, Xiting Wang, Yangqiu Song, Baining Guo
2015 IEEE Transactions on Knowledge and Data Engineering  
The state-of-the-art multi-branch clustering method, Bayesian rose trees, is employed to generate a topic tree with a high fitness value.  ...  We present an evolutionary multi-branch tree clustering method to model hierarchical topics and their evolutionary patterns over time.  ...  ACKNOWLEDGMENTS The authors would like to thank Hao Wei for helping generate the TextFlow visualization, and Charles Blundell for his insights.  ... 
doi:10.1109/tkde.2014.2373384 fatcat:dij4pym5frav5ihz4oolaahfhm

Use All The Labels: A Hierarchical Multi-Label Contrastive Learning Framework [article]

Shu Zhang and Ran Xu and Caiming Xiong and Chetan Ramaiah
2022 arXiv   pre-print
The loss function is data driven and automatically adapts to arbitrary multi-label structures.  ...  We introduce novel hierarchy preserving losses, which jointly apply a hierarchical penalty to the contrastive loss, and enforce the hierarchy constraint.  ...  A tree data structure is used to to visualize the multi-labels. Figure 2 . 2 Figure 2. Conceptual visualization of the losses.  ... 
arXiv:2204.13207v1 fatcat:zux6lp24drbbhbbzoflhomhwyi

Interactive Steering of Hierarchical Clustering

Weikai Yang, Xiting Wang, Jie Lu, Wenwen Dou, Shixia Liu
2020 IEEE Transactions on Visualization and Computer Graphics  
Given the constraint tree, the data items are hierarchically clustered using evolutionary Bayesian rose tree.  ...  An initial constraint tree is then extracted using the ant colony optimization algorithm. The algorithm balances the tree width and depth and covers the data items with high confidence.  ...  They presented a tree-cutting model to address the challenges of visualizing streaming data with a changing hierarchical topic tree layout.  ... 
doi:10.1109/tvcg.2020.2995100 pmid:32746252 fatcat:fdwsn4qkzffrjgn2hrjhb47bqe

Hierarchical Control for Multi-Agent Autonomous Racing [article]

Rishabh Saumil Thakkar, Aryaman Singh Samyal, David Fridovich-Keil, Zhe Xu, Ufuk Topcu
2022 arXiv   pre-print
We show that hierarchical planning for game-theoretic reasoning produces competitive behavior even when challenged with complex rules and constraints.  ...  We develop a hierarchical controller for multi-agent autonomous racing.  ...  This result indicates that some type of hierarchical structure is favorable.  ... 
arXiv:2202.12861v3 fatcat:55iyuw5a7jcg5ew5kybuujxzwq

Author Index

2010 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition  
Gait Recognition based on Local Motion Feature Selection Multi-View Structure Computation without Explicitly Estimating Motion Li, Hongsheng Object Matching with a Locally Affine-Invariant Constraint  ...  Estimation of Image Bias Field with Sparsity Constraints Gehrig, Stefan K.  ... 
doi:10.1109/cvpr.2010.5539913 fatcat:y6m5knstrzfyfin6jzusc42p54

Learning Local Structured Correlation Filters for Visual Tracking via Spatial Joint Regularization

Chenggang Guo, Dongyi Chen, Zhiqi Huang
2019 IEEE Access  
In this paper, we introduce the tree-structured group sparsity regularization into the DCF-based formula. The correlation filter to be learned is divided into hierarchical local groups.  ...  INDEX TERMS Correlation filter, spatial regularization, structure sparsity, visual tracking. 39158 2169-3536  ...  [46] utilized the tree-structured group joint sparse representation to combine multi-level cues for image illumination estimation.  ... 
doi:10.1109/access.2019.2906508 fatcat:3dqg45gfsbdjvpmgj4his3yrda

Visual perception driven 3D building structure representation from airborne laser scanning point cloud

Pingbo Hu, Bisheng Yang
2020 Virtual Reality & Intelligent Hardware  
Finally, a visual plane fitted residual or area constraint process is adopted to generate the RSG model with different levels of details.  ...  mutual relationships between the roof plane geometry and roof structure units are expressed by a hierarchical topology tree.  ...  The output of the building reconstruction is a visually pleasing structural model and the consistent geometry-structure-topology is organized by a hierarchical topology tree.  ... 
doi:10.1016/j.vrih.2020.05.004 fatcat:4eo472mchbahhk4rfbn5c6r4vy

Ten-fold Improvement in Visual Odometry Using Landmark Matching

Zhiwei Zhu, Taragay Oskiper, Supun Samarasekera, Rakesh Kumar, Harpreet S. Sawhney
2007 2007 IEEE 11th International Conference on Computer Vision  
First, a dynamic local landmark tracking technique is proposed to track a set of local landmarks across image frames and select an optimal set of tracked local landmarks for pose computation.  ...  We demonstrate that a real-time visual odometry system using local and global landmarks can precisely locate a user within 1 meter over 1000 meters in unknown indoor/outdoor environments with challenging  ...  In [9] , using a hierarchical k-means clustering to build a visual vocabulary tree, the efficiency can be further improved.  ... 
doi:10.1109/iccv.2007.4409062 dblp:conf/iccv/ZhuOSKS07 fatcat:dkgsv5dstzawdnuob6fuybizjy

A Novel Decomposition Model for Visual Rail Surface Inspection

Ziwen Zhang, Mangui Liang, Zhiyu Liu
2021 Electronics  
To better capture the compactness and completeness of a defect, we introduce a tree-shaped hierarchical structure of sparse induction norms to encode the spatial structure of the defect area.  ...  In this paper, we fully explore and use the essential attributes of our defect structure data and the inherent temporal and spatial characteristics of the track to establish a general theoretical framework  ...  This type of hierarchical tree structure constraint induces superpixels in the same group that share similar representations.  ... 
doi:10.3390/electronics10111271 fatcat:7owqp2beafggtpzv2cfoipi7pq

Visual Modelling of Complex Business Processes with Trees, Overlays and Distortion-based Displays

Lei Li, John Hosking, John Grundy
2007 IEEE Symposium on Visual Languages and Human-Centric Computing (VL/HCC 2007)  
We describe a prototype support tool, MaramaEML, that provides support for multiple visual notations including the Business Process Modelling Notation (BPMN), the EML tree-based, multi-layer hierarchical  ...  EML utilizes several visual metaphors to enhance the representation, navigation and management of large organizational hierarchies and process flows.  ...  This hierarchical structure is a natural way to model business structure and users are familiar with using it to model complex organizational hierarchies.  ... 
doi:10.1109/vlhcc.2007.28 dblp:conf/vl/LiHG07 fatcat:wgvadfqgevfvlcay5jyn4jlify

Leveraging Hierarchical Structures for Few-Shot Musical Instrument Recognition

Hugo F Flores Garcia, Aldo Aguilar, Ethan Manilow, Bryan Pardo
2021 Zenodo  
We apply a hierarchical loss function to the training of prototypical networks, combined with a method to aggregate prototypes hierarchically, mirroring the structure of a predefined musical instrument  ...  These extensions require no changes to the network architecture and new levels can be easily added or removed.  ...  MedleyDB contains multi-track recordings of musical instruments and vocals.  ... 
doi:10.5281/zenodo.5624615 fatcat:kwpblujcsffbbckacgrkurqzp4

Leveraging Hierarchical Structures for Few-Shot Musical Instrument Recognition [article]

Hugo Flores Garcia, Aldo Aguilar, Ethan Manilow, Bryan Pardo
2021 arXiv   pre-print
We apply a hierarchical loss function to the training of prototypical networks, combined with a method to aggregate prototypes hierarchically, mirroring the structure of a predefined musical instrument  ...  These extensions require no changes to the network architecture and new levels can be easily added or removed.  ...  MedleyDB contains multi-track recordings of musical instruments and vocals.  ... 
arXiv:2107.07029v2 fatcat:hcsakt427jdxtgjfrnitvcktsi

Surface As Structure: The Multi-Touch Controller As Map Of Musical State Space

Oliver Bown, Daniel Jones, Sam Britton
2012 Proceedings of the SMC Conferences  
Massive -Graphical surfaces can contain visual structures of unlimited size, accessed through zooming and tracking.  ...  In this case, unlike the drawn example in Figure 1 the hierarchical structure does not clearly visually correspond to the nesting of polygons.  ... 
doi:10.5281/zenodo.850157 fatcat:kintp6c3dvfermeal433q53wi4

Automatically and efficiently inferring the hierarchical structure of visual maps

Margarita Chli, Andrew J. Davison
2009 2009 IEEE International Conference on Robotics and Automation  
Via tree factorisation, we are able to determine not just a single level submap division but a powerful fully hierarchical correlation and clustering structure.  ...  Our analysis and experiments reveal particularly interesting structure in visual maps and give pointers to more efficient approximate visual SLAM algorithms.  ...  extract the full hierarchical correlation structure of a visual map as it is built.  ... 
doi:10.1109/robot.2009.5152530 dblp:conf/icra/ChliD09 fatcat:zhdvauxn6ndf3fvq3ipo55fwo4
« Previous Showing results 1 — 15 out of 21,509 results