Filters








104,434 Hits in 7.3 sec

DynamicGEM: A Library for Dynamic Graph Embedding Methods [article]

Palash Goyal, Sujit Rokka Chhetri, Ninareh Mehrabi, Emilio Ferrara, Arquimedes Canedo
2018 arXiv   pre-print
It consists of state-of-the-art algorithms for defining embeddings of nodes whose connections evolve over time.  ...  We have implemented various metrics to evaluate the state-of-the-art methods, and examples of evolving networks from various domains.  ...  We would also like to acknowledge support from the National Science Foundation (NSF grant IIS-9988642) and the Multidisciplinary Research Program of the Department of Defense (MURI N00014-00-1-0637).  ... 
arXiv:1811.10734v1 fatcat:276u6xjwvnhyboxxe3sa6lcd6u

Learning the Dynamics of Visual Relational Reasoning via Reinforced Path Routing

Chenchen Jing, Yunde Jia, Yuwei Wu, Chuanhao Li, Qi Wu
2022 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
Reasoning is a dynamic process. In cognitive theories, the dynamics of reasoning refers to reasoning states over time after successive state transitions.  ...  In this paper, we propose to learn the reasoning dynamics of visual relational reasoning by casting it as a path routing task.  ...  Acknowledgments This work was supported by the Natural Science Foundation of China (NSFC) under Grants No. 62172041 and No. 62176021.  ... 
doi:10.1609/aaai.v36i1.19997 fatcat:j2llabdqtrbixawiqrtup7hgpu

Attention-Driven Dynamic Graph Convolutional Network for Multi-Label Image Recognition [article]

Jin Ye, Junjun He, Xiaojiang Peng, Wenhao Wu, Yu Qiao
2020 arXiv   pre-print
current state-of-the-art methods with a clear margin.  ...  However, constructing a graph by counting the label co-occurrence possibilities of the training data may degrade model generalizability, especially when there exist occasional co-occurrence objects in  ...  This work is partially supported by National Natural Science Foundation of China (U1813218, U1713208), Science and Technology Service Network Initiative of Chinese Academy of Sciences (KFJ-STS-QYZX-092  ... 
arXiv:2012.02994v1 fatcat:arphfwobvvbbdmd3sclhbg4nxm

MAN: Moment Alignment Network for Natural Language Moment Retrieval via Iterative Graph Adjustment

Da Zhang, Xiyang Dai, Xin Wang, Yuan-Fang Wang, Larry S. Davis
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
We evaluate the proposed approach on two challenging public benchmarks DiDeMo and Charades-STA, where our MAN significantly outperforms the state-of-the-art by a large margin.  ...  Most importantly, we propose to explicitly model moment-wise temporal relations as a structured graph and devise an iterative graph adjustment network to jointly learn the best structure in an end-to-end  ...  Comparison with State-of-the-art We compare our MAN with other state-of-the-art methods on DiDeMo [18] and Charades-STA [14] .  ... 
doi:10.1109/cvpr.2019.00134 dblp:conf/cvpr/ZhangDWWD19 fatcat:mbglkapzw5hr5aoxrz6msvll5m

dg2pix: Pixel-Based Visual Analysis of Dynamic Graphs

Eren Cakmak, Dominik Jackle, Tobias Schreck, Daniel Keim
2020 2020 Visualization in Data Science (VDS)  
In summary, the contributions of this work are the following: (1) The novel dg2pix visualization technique, a time-scalable visual metaphor to reveal changes and similar temporal states in a dynamic graph  ...  RELATED WORK In the following, we briefly discuss related work from dynamic graph visualizations, the visual analysis of dimensionality reduction methods, and pixel-based visualization techniques.  ...  The (2-3) transformation steps (see Fig. 2 ) are, to the best of our knowledge, not considered in previous literature for dynamic graph visualizations even though graph embeddings outperform many state-of-the-art  ... 
doi:10.1109/vds51726.2020.00008 fatcat:yca23ponvbfcjnmuzqyyl7mdra

dg2pix: Pixel-Based Visual Analysis of Dynamic Graphs [article]

Eren Cakmak, Dominik Jäckle, Tobias Schreck, Daniel Keim
2020 arXiv   pre-print
We propose dg2pix, a novel pixel-based visualization technique, to visually explore temporal and structural properties in long sequences of large-scale graphs.  ...  exploration of long sequences of high-dimensional graph data, and enables the identification and comparison of similar temporal states.  ...  The (2-3) transformation steps (see Fig. 2 ) are, to the best of our knowledge, not considered in previous literature for dynamic graph visualizations even though graph embeddings outperform many state-of-the-art  ... 
arXiv:2009.07322v1 fatcat:dxrhzrrcpncallve4xg7sui67i

Learning Latent Graph Dynamics for Visual Manipulation of Deformable Objects [article]

Xiao Ma, David Hsu, Wee Sun Lee
2022 arXiv   pre-print
Preliminary experiments of G-DOOM on a set of challenging rope and cloth manipulation tasks indicate strong performance, compared with state-of-the-art methods.  ...  Manipulating deformable objects, such as ropes and clothing, is a long-standing challenge in robotics, because of their large degrees of freedom, complex non-linear dynamics, and self-occlusion in visual  ...  The authors are with the School of Computing, National University of Singapore.  ... 
arXiv:2104.12149v2 fatcat:btrvtsnu3jferj7nkav7rlssvi

Temporal Dynamic Graph LSTM for Action-driven Video Object Detection [article]

Yuan Yuan, Xiaodan Liang, Xiaolong Wang, Dit-Yan Yeung, Abhinav Gupta
2017 arXiv   pre-print
TD-Graph LSTM enables global temporal reasoning by constructing a dynamic graph that is based on temporal correlations of object proposals and spans the entire video.  ...  To tackle this problem, we propose a novel temporal dynamic graph Long Short-Term Memory network (TD-Graph LSTM).  ...  We further show the qualitative comparison with two state-of-the-arts in Figure 7 .  ... 
arXiv:1708.00666v1 fatcat:dqvgtiouaffjvcsb55cwwkw4z4

SPRING: a kinetic interface for visualizing high dimensional single-cell expression data

Caleb Weinreb, Samuel Wolock, Allon M Klein, Bonnie Berger
2017 Bioinformatics  
Visualizations from SPRING are also more reproducible than those of stochastic visualization methods such as tSNE, a state-of-the-art tool.  ...  Motivation: Single-cell gene expression profiling technologies can map the cell states in a tissue or organism.  ...  Graph invariance One drawback of tSNE -the state-of-the-art algorithm for visualizing high dimensional scSeq data -is that it is stochastic and therefore not perfectly reproducible.  ... 
doi:10.1093/bioinformatics/btx792 pmid:29228172 pmcid:PMC6030950 fatcat:xslrq5jxijctzoyucbmsztq4me

MAN: Moment Alignment Network for Natural Language Moment Retrieval via Iterative Graph Adjustment [article]

Da Zhang, Xiyang Dai, Xin Wang, Yuan-Fang Wang, Larry S. Davis
2019 arXiv   pre-print
We evaluate the proposed approach on two challenging public benchmarks DiDeMo and Charades-STA, where our MAN significantly outperforms the state-of-the-art by a large margin.  ...  Most importantly, we propose to explicitly model moment-wise temporal relations as a structured graph and devise an iterative graph adjustment network to jointly learn the best structure in an end-to-end  ...  Comparison with State-of-the-art We compare our MAN with other state-of-the-art methods on DiDeMo [18] and Charades-STA [14] .  ... 
arXiv:1812.00087v2 fatcat:cbxtybz4cnf3xbqiudlyj3rlm4

SPRING: a kinetic interface for visualizing high dimensional single-cell expression data [article]

Caleb Weinreb, Samuel Wolock, Allon Klein
2016 bioRxiv   pre-print
Visualizations from SPRING are also more reproducible than those of stochastic visualization methods such as tSNE, a state-of-the-art tool.  ...  Motivation: Single-cell gene expression profiling technologies can map the cell states in a tissue or organism.  ...  Graph invariance One drawback of tSNE -the state-of-the-art algorithm for visualizing high dimensional scSeq data -is that it is stochastic and therefore not perfectly reproducible.  ... 
doi:10.1101/090332 fatcat:b3bzqfd7pvf53nitrbbgktl3qm

MAAS: Multi-modal Assignation for Active Speaker Detection [article]

Juan León-Alcázar, Fabian Caba Heilbron, Ali Thabet, Bernard Ghanem
2021 arXiv   pre-print
Moreover, the temporal extension of this initial graph achieves a new state-of-the-art on the AVA-ActiveSpeaker dataset with a mAP of 88.8\%.  ...  In this paper we present a novel approach to active speaker detection that directly addresses the multi-modal nature of the problem, and provides a straightforward strategy where independent visual features  ...  State-of-the-art Comparison We begin our analysis by comparing MAAS to state-ofthe-art methods.  ... 
arXiv:2101.03682v2 fatcat:6in3oui5f5an7ke3a3mrddfqr4

(2.5+1)D Spatio-Temporal Scene Graphs for Video Question Answering

Anoop Cherian, Chiori Hori, Tim K. Marks, Jonathan Le Roux
2022 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
The nodes in the dynamic graph are enriched with motion features capturing their interactions with other graph nodes.  ...  Such a (2.5+1)D graph is then segregated into a static sub-graph and a dynamic sub-graph, corresponding to whether the objects within them usually move in the world.  ...  State-of-the-art Comparisons: In Tables 1 and 2 , we compare the performance of our full (2.5+1)D-Transformer pipeline against recent state-of-the-art methods.  ... 
doi:10.1609/aaai.v36i1.19922 fatcat:vvdnagxrc5dv3ghoiibdclypsm

Learning to Compose Dynamic Tree Structures for Visual Contexts [article]

Kaihua Tang, Hanwang Zhang, Baoyuan Wu, Wenhan Luo, Wei Liu
2018 arXiv   pre-print
Experimental results on two benchmarks, which require reasoning over contexts: Visual Genome for scene graph generation and VQA2.0 for visual Q&A, show that VCTree outperforms state-of-the-art results  ...  We propose to compose dynamic tree structures that place the objects in an image into a visual context, helping visual reasoning tasks such as scene graph generation and visual Q&A.  ...  Mean Recall for Scene Graph We also report more detailed results of the proposed Mean Recall (mR@K) in Table 6 . The proposed VC-TREE-HL shows best performance among all the ablative structures.  ... 
arXiv:1812.01880v1 fatcat:dkg6hgwrtjepdp2tdtn3njkezi

Graph Distillation for Action Detection with Privileged Modalities [article]

Zelun Luo, Jun-Ting Hsieh, Lu Jiang, Juan Carlos Niebles, Li Fei-Fei
2018 arXiv   pre-print
We evaluate our approach on action classification and detection tasks in multimodal videos, and show that our model outperforms the state-of-the-art by a large margin on the NTU RGB+D and PKU-MMD benchmarks  ...  Common methods in transfer learning do not take advantage of the extra modalities potentially available in the source domain.  ...  Comparison with State-of-the-Art Action Classification. Table 1 shows the comparison of action classification with state-of-the-art models on NTU RGB+D dataset.  ... 
arXiv:1712.00108v2 fatcat:vbvqueff4faahg365uzzgoffoq
« Previous Showing results 1 — 15 out of 104,434 results