Filters








189,181 Hits in 3.1 sec

Hierarchical Graph Attention Network for Visual Relationship Detection

Li Mi, Zhenzhong Chen
2020 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
Visual Relationship Detection (VRD) aims to describe the relationship between two objects by providing a structural triplet shown as .  ...  In this work, a Hierarchical Graph Attention Network (HGAT) is proposed to capture the dependencies on both object-level and triplet-level.  ...  Related Work Visual Relationships Detection Visual relationship detection offers a comprehensive scene understanding of an image by providing several triplets of <subject-predicate-object>.  ... 
doi:10.1109/cvpr42600.2020.01390 dblp:conf/cvpr/MiC20 fatcat:czorfgebyzem7g232niwny4lqe

Visualizing criminal relationships: comparison of a hyperbolic tree and a hierarchical list

Yang Xiang, Michael Chau, Homa Atabakhsh, Hsinchun Chen
2005 Decision Support Systems  
In this paper, we propose the use of a hyperbolic tree view and a hierarchical list view to visualize criminal relationships.  ...  Our results indicate that both views can help in criminal relationship visualization.  ...  Can we apply the hyperbolic tree and the hierarchical list to criminal relationship visualization? ! Is the hyperbolic tree a better method than the hierarchical list for users to find information?  ... 
doi:10.1016/j.dss.2004.02.006 fatcat:ayvfpmp7vza7vgg7osoy5aaha4

Better Understanding Hierarchical Visual Relationship for Image Caption [article]

Zheng-cong Fei
2019 arXiv   pre-print
It takes into account the hierarchical interactions between different abstraction levels of visual information in the images and their bounding-boxes.  ...  However, it fails to get the relationship between images/objects and their hierarchical interactions which can be helpful for representing and describing an image.  ...  Visual relationship is the interactions or relative positions between objects detected in an image [42] .  ... 
arXiv:1912.01881v1 fatcat:ja7cbiqv7vavdgcuqag665zkii

HR-RCNN: Hierarchical Relational Reasoning for Object Detection [article]

Hao Chen, Abhinav Shrivastava
2021 arXiv   pre-print
In this paper, we propose a hierarchical relational reasoning framework (HR-RCNN) for object detection, which utilizes a novel graph attention module (GAM).  ...  Leveraging heterogeneous relationships, our HR-RCNN shows great improvement on COCO dataset, for both object detection and instance segmentation.  ...  Figure 1 : 1 Figure 1: The Hierarchical Relational Reasoning Framework for object detection, where pixel relationships, scale relationships, RoI relationships are incorporated in one network.  ... 
arXiv:2110.13892v2 fatcat:lj4pymrm2vfp7ed3g3jabcfjhi

ORD: Object Relationship Discovery for Visual Dialogue Generation [article]

Ziwei Wang, Zi Huang, Yadan Luo, Huimin Lu
2020 arXiv   pre-print
Specifically, a hierarchical graph convolutional network (HierGCN) is proposed to retain the object nodes and neighbour relationships locally, and then refines the object-object connections globally to  ...  In this paper, we propose an object relationship discovery (ORD) framework to preserve the object interactions for visual dialogue generation.  ...  Different from all existing visual dialogue methods, the proposed ORD model detects fine-grained object-level regions, encodes the scene with hierarchical understanding of visual relationships, rather  ... 
arXiv:2006.08322v1 fatcat:6ic2p2p2zbcj5jeaqp35e5hlwq

Semantic Hierarchies for Visual Object Recognition

Marcin Marszalek, Cordelia Schmid
2007 2007 IEEE Conference on Computer Vision and Pattern Recognition  
We use the semantics of image labels to integrate prior knowledge about inter-class relationships into the visual appearance learning.  ...  We show how to build and train a semantic hierarchy of discriminative classifiers and how to use it to perform object detection.  ...  Querying the semantic network of WordNet, one can determine semantic relationships between class labels that are assigned to the observed visual object instances during visual object recognition.  ... 
doi:10.1109/cvpr.2007.383272 dblp:conf/cvpr/MarszalekS07a fatcat:d4rvtb5zlzac3k4g5j4aei5v5i

Adaptive Image-to-Video Scene Graph Generation via Knowledge Reasoning and Adversarial Learning

Jin Chen, Xiaofeng Ji, Xinxiao Wu
2022 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
Scene graph in a video conveys a wealth of information about objects and their relationships in the scene, thus benefiting many downstream tasks such as video captioning and visual question answering.  ...  We tackle the second challenge by hierarchical adversarial learning to reduce the data distribution discrepancy between images and video frames.  ...  Relationship detection aims at first detecting objects and then predicting the relationships of detected objects.  ... 
doi:10.1609/aaai.v36i1.19903 fatcat:6qhmaidrhbc3hd4h54fm2ndpum

Integrating Concept Ontology and Multitask Learning to Achieve More Effective Classifier Training for Multilevel Image Annotation

Jianping Fan, Yuli Gao, Hangzai Luo
2008 IEEE Transactions on Image Processing  
To tackle the problem of huge intraconcept visual diversity, multiple types of kernels are integrated to characterize the diverse visual similarity relationships between the images more precisely, and  ...  classifiers hierarchically.  ...  Hierarchical Boosting Because the mapping functions between the low-level visual features and the high-level image concepts with larger intraconcept visual diversity may not be obvious, automatic detection  ... 
doi:10.1109/tip.2008.916999 pmid:18270128 fatcat:bxokhjalpzcfdpwyk3yajzl3ni

Saliency Detection using regression trees on hierarchical image segments

Gokhan Yildirim, Appu Shaji, Sabine Susstrunk
2014 2014 IEEE International Conference on Image Processing (ICIP)  
Finally, we use regression trees to learn the relationship between the feature values and visual saliency.  ...  They require parameter tuning, and the relationship between the parameter value and visual saliency is often not well understood.  ...  We abstract an image via hierarchical segmentation and analyze the relationship between the visual properties of the image segments and corresponding saliency values by using regression trees.  ... 
doi:10.1109/icip.2014.7025668 dblp:conf/icip/YildirimSS14 fatcat:mln6ut6f3jdmzdptxw3zfr3jma

Hierarchical Category Detector for Clothing Recognition from Visual Data

Suren Kumar, Rui Zheng
2017 2017 IEEE International Conference on Computer Vision Workshops (ICCVW)  
Our approach learns the visual similarities between various clothing categories and predicts a tree of categories.  ...  Detection of this new category will require adding annotated data specific to jegging class and subsequently relearning the weights for the deep network.  ...  However, WordNet hierarchy and relationships are predefined by conceptual-semantic and lexi- cal relationship.  ... 
doi:10.1109/iccvw.2017.272 dblp:conf/iccvw/KumarZ17 fatcat:rt75luddpjfmbib6ure23474zi

Hierarchical Novelty Detection for Visual Object Recognition

Kibok Lee, Kimin Lee, Kyle Min, Yuting Zhang, Jinwoo Shin, Honglak Lee
2018 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition  
In this paper, we study more informative novelty detection schemes based on a hierarchical classification framework.  ...  Deep neural networks have achieved impressive success in large-scale visual object recognition tasks with a predefined set of classes.  ...  Our approach is also motivated by a strong empirical correlation between hierarchical semantic relationships and the visual appearance of objects [5] .  ... 
doi:10.1109/cvpr.2018.00114 dblp:conf/cvpr/LeeLMZSL18 fatcat:faqkpwivwjerbf3jw6cyssftzm

A multi-level visualization method for IT system structure

Mo Su, ZhenYong Ma, QiLe Wang, JiNa Wang, JingFeng Wei, Hong Jiang
2021 Procedia Computer Science  
internal structural relationships And the relationship between nodes is clear and intuitive.This article uses different layout algorithms such as hierarchical layout algorithm, circular distribution algorithm  ...  internal structural relationships And the relationship between nodes is clear and intuitive.This article uses different layout algorithms such as hierarchical layout algorithm, circular distribution algorithm  ...  Among them, the hierarchical layout algorithm can intuitively show the level of IT architecture, which is convenient for users to visually view the relationship between levels.  ... 
doi:10.1016/j.procs.2021.02.112 fatcat:pk4geksjqjbk3orm3oei4ga4xm

Extracting hierarchical structure of content groups from different social media platforms using multiple social metadata

Daichi Takehara, Ryosuke Harakawa, Takahiro Ogawa, Miki Haseyama
2017 Multimedia tools and applications  
The extracted hierarchical structure shows various abstraction levels of content groups and their hierarchical relationships, which can help users select topics related to the input query.  ...  This paper has two contributions: (1) A new feature extraction method, Locality Preserving Canonical Correlation Analysis with multiple social metadata (LPCCA-MSM) that can detect content groups without  ...  We then hierarchically detect content groups in the heterogeneous graph on the basis of a well-known community detection method [4] , and the hierarchical structure can thus be extracted.  ... 
doi:10.1007/s11042-017-4717-7 fatcat:35rmmanldndfdhrpl6s5b7r3nq

An integer programming approach and visual analysis for detecting hierarchical community structures in social networks

Chun-Cheng Lin, Jia-Rong Kang, Jyun-Yu Chen
2015 Information Sciences  
The relationship among subcommunities in each community can further be identified as hierarchical community structures, in which each super node at each hierarchical level represents a nested structure  ...  Visual analysis of experimental results shows that the proposed model with different settings for level numbers can analyze reasonable and sophisticated hierarchical community structures, such that the  ...  Finally, visual analysis of detected hierarchical community structures for three real social network instances helps elucidate detection results.  ... 
doi:10.1016/j.ins.2014.12.009 fatcat:cfm4fyrycng7fcb7c224n3d4wy

Page 3278 of The Journal of Neuroscience Vol. 20, Issue 9 [page]

2000 The Journal of Neuroscience  
There is physiological evidence in favor of FEF not having a purely FB relationship with extrastriate visual areas.  ...  Relationship of visual areas with FEF It is known that area V4 projects to FEF in an FF manner (Barbas and Mesulam, 1981). However, little is known about the reciprocal projection.  ... 
« Previous Showing results 1 — 15 out of 189,181 results