Filters








120,385 Hits in 4.6 sec

Latent Variable Modeling for Generative Concept Representations and Deep Generative Models [article]

Daniel T. Chang
2018 arXiv   pre-print
For latent representations to be useful as generative concept representations, their latent space must support latent space interpolation, attribute vectors and concept vectors, among other things.  ...  We investigate and discuss latent variable modeling, including latent variable models, latent representations and latent spaces, particularly hierarchical latent representations and latent space vectors  ...  The inference model and learning for hierarchical LVMs vary. See 3.3 Hierarchical Latent Representations for discussion.  ... 
arXiv:1812.11856v1 fatcat:zsqsvtrt3rgjbdnwpvnvnd5aki

Style-aware Neural Model with Application in Authorship Attribution [article]

Fereshteh Jafariakinabad, Kien A. Hua
2019 arXiv   pre-print
Subsequently, we employ an attention-based hierarchical neural network to encode the syntactic and semantic structure of sentences in documents while rewarding the sentences which contribute more to capturing  ...  First, we propose a simple way to jointly encode syntactic and lexical representations of sentences.  ...  Subsequently, this representation is fed to a hierarchical attention network to learn the final document representation.  ... 
arXiv:1909.06194v1 fatcat:tgwzbswymnh6ljwdbvoiubl5ra

Rapid Clothing Retrieval via Deep Learning of Binary Codes and Hierarchical Search

Kevin Lin, Huei-Fang Yang, Kuan-Hsien Liu, Jen-Hao Hsiao, Chu-Song Chen
2015 Proceedings of the 5th ACM on International Conference on Multimedia Retrieval - ICMR '15  
We develop a hierarchical deep search framework to tackle this problem. We use a pretrained network model that has learned rich mid-level visual representations in module 1.  ...  Then, in module 2, we add a latent layer to the network and have neurons in this layer to learn hashes-like representations while fine-tuning it on the clothing dataset.  ...  They train a deep CNN that incorporates a tree-structured clothes attributes for feature learning.  ... 
doi:10.1145/2671188.2749318 dblp:conf/mir/LinYLHC15 fatcat:6tgk7yfj4rbghe5lca6uvzkhzq

A Hierarchical Generative Embedding Model for Influence Maximization in Attributed Social Networks

Luodi Xie, Huimin Huang, Qing Du
2022 Applied Sciences  
Inspired by the powerful ability of neural networks in the field of representation learning, we designed a hierarchical generative embedding model (HGE) to map nodes into latent space automatically.  ...  Then, with the learned latent representation of each node, we proposed a HGE-GA algorithm to predict influence strength and compute the top-K influential nodes.  ...  The reason is that HGE-1N-GA and HGE-GA consider the general network structure, hierarchical network structure as well as node attributes to learn users' latent feature representations for predicting the  ... 
doi:10.3390/app12031321 fatcat:ynhgx54x2bh7xdvv5jqsftahjy

Imitation Learning for Fashion Style Based on Hierarchical Multimodal Representation [article]

Shizhu Liu, Shanglin Yang, Hui Zhou
2020 arXiv   pre-print
In this work, we propose an adversarial inverse reinforcement learning formulation to recover reward functions based on hierarchical multimodal representation (HM-AIRL) during the imitation process.  ...  The hierarchical joint representation can more comprehensively model the expert composited outfit demonstrations to recover the reward function.  ...  Hierarchical Multimodal Representation for Fashion Outfit Fusion Representation for Fashion Item For one fashion item, it is obvious that the corresponding image and attribute tags have the complementary  ... 
arXiv:2004.06229v1 fatcat:7ddx2atnmbfvdifubptflwmqje

User Cold-start Recommendation via Inductive Heterogeneous Graph Neural Network

Desheng Cai, Shengsheng Qian, Quan Fang, Jun Hu, Changsheng Xu
2022 ACM Transactions on Information Systems  
meaningless and noisy connected neighbors to generate high-quality representations for user cold-start recommendations.  ...  In user cold-start recommendation systems, the user attribute information is often used by existing approaches to learn user preferences due to the unavailability of the user action data.  ...  multi-modal attributes are not also taken into consideration for learning representations.  ... 
doi:10.1145/3560487 fatcat:at4e5mfq6vgujbfaiijo22yvtq

Hi-CMD: Hierarchical Cross-Modality Disentanglement for Visible-Infrared Person Re-Identification

Seokeon Choi, Sumin Lee, Youngeun Kim, Taekyung Kim, Changick Kim
2020 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
To implement our approach, we introduce an IDpreserving person image generation network and a hierarchical feature learning module.  ...  Our generation network learns the disentangled representation by generating a new cross-modality image with different poses and illuminations while preserving a person's identity.  ...  Disentangled representation learning for recognition.  ... 
doi:10.1109/cvpr42600.2020.01027 dblp:conf/cvpr/ChoiLKKK20 fatcat:hv6wkhcbrbdzfexnpscxw7laay

Hi-CMD: Hierarchical Cross-Modality Disentanglement for Visible-Infrared Person Re-Identification [article]

Seokeon Choi, Sumin Lee, Youngeun Kim, Taekyung Kim, Changick Kim
2020 arXiv   pre-print
To implement our approach, we introduce an ID-preserving person image generation network and a hierarchical feature learning module.  ...  Our generation network learns the disentangled representation by generating a new cross-modality image with different poses and illuminations while preserving a person's identity.  ...  Disentangled representation learning for recognition.  ... 
arXiv:1912.01230v3 fatcat:knie4ib675h6hnkmt6ztbgupna

Hyperbolic Self-supervised Contrastive Learning Based Network Anomaly Detection [article]

Yuanjun Shi
2022 arXiv   pre-print
With the wide application of deep learning on graph representations, existing approaches choose to apply euclidean graph encoders as their backbone, which may lose important hierarchical information, especially  ...  Anomaly detection on the attributed network has recently received increasing attention in many research fields, such as cybernetic anomaly detection and financial fraud detection.  ...  Problem Definition: Anomaly Detection on Attributed Networks Attributed Network.  ... 
arXiv:2209.05049v1 fatcat:l32dxb25pbd5jc3hd5tewjhkre

Cash-Out User Detection Based on Attributed Heterogeneous Information Network with a Hierarchical Attention Mechanism

Binbin Hu, Zhiqiang Zhang, Chuan Shi, Jun Zhou, Xiaolong Li, Yuan Qi
2019 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
Conventional solutions for the cash-out user detection are to perform subtle feature engineering for each user and then apply a classifier, such as GDBT and Neural Network.  ...  Specifically, we model different types of objects and their rich attributes and interaction relations in the scenario of credit payment service with an Attributed Heterogeneous Information Network (AHIN  ...  representation learning.  ... 
doi:10.1609/aaai.v33i01.3301946 fatcat:4k22nudqhzbzhakfr2fbonfsni

Interpreting Trajectories from Multiple Views: A Hierarchical Self-Attention Network for Estimating the Time of Arrival

Zebin Chen, Xiaolin Xiao, Yue-Jiao Gong, Jun Fang, Nan Ma, Hua Chai, Zhiguang Cao
2022 Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining  
The hierarchical encoders and the attentive decoder are simultaneously learned to achieve an overall optimality.  ...  To fulfill the purpose, we design a hierarchical self-attention network (HierETA) that accurately models the local traffic conditions and the underlying trajectory structure.  ...  Research Funds for the Central Universities.  ... 
doi:10.1145/3534678.3539051 fatcat:6mszaekod5dhldadnm6ir4elny

Deep Representation Learning for Social Network Analysis

Qiaoyu Tan, Ninghao Liu, Xia Hu
2019 Frontiers in Big Data  
First, we introduce the basic models for learning node representations in homogeneous networks.  ...  A fundamental step for analyzing social networks is to encode network data into low-dimensional representations, i.e., network embeddings, so that the network topology structure and other attribute information  ...  ., node attributes) into representation learning, as will be introduced below.  ... 
doi:10.3389/fdata.2019.00002 pmid:33693325 pmcid:PMC7931936 fatcat:w7kfbniaf5ctzp3swdttp52h3m

Deep Representation Learning for Social Network Analysis [article]

Qiaoyu Tan, Ninghao Liu, Xia Hu
2019 arXiv   pre-print
First, we introduce the basic models for learning node representations in homogeneous networks.  ...  Then, we introduce the techniques for embedding subgraphs. After that, we present the applications of network representation learning.  ...  ., node attributes) into representation learning, as to be introduced below.  ... 
arXiv:1904.08547v1 fatcat:b7ifkbs2ajggljwntruhn57l3y

MaskMTL: Attribute prediction in masked facial images with deep multitask learning [article]

Prerana Mukherjee, Vinay Kaushik, Ronak Gupta, Ritika Jha, Daneshwari Kankanwadi, Brejesh Lall
2022 arXiv   pre-print
The source code is available at https://github.com/ritikajha/Attribute-prediction-in-masked-facial-images-with-deep-multitask-learning  ...  This paper presents a deep Multi-Task Learning (MTL) approach to jointly estimate various heterogeneous attributes from a single masked facial image.  ...  Parameter sharing in neural networks The widely used approach for multitask learning (MTL) with neural networks (NNs) is hard parameter sharing in which a common space representation is learned that generalize  ... 
arXiv:2201.03002v2 fatcat:cukwzfuzojgnnee6s6chypghaa

Generative Adversarial Image Synthesis with Decision Tree Latent Controller [article]

Takuhiro Kaneko, Kaoru Hiramatsu, Kunio Kashino
2018 arXiv   pre-print
This paper proposes the decision tree latent controller generative adversarial network (DTLC-GAN), an extension of a GAN that can learn hierarchically interpretable representations without relying on detailed  ...  ., MNIST, CIFAR-10, Tiny ImageNet, 3D Faces, and CelebA, and confirmed that the DTLC-GAN can learn hierarchically interpretable representations with either unsupervised or weakly supervised settings.  ...  We used the DTLC 3 -GAN WS , where k 1 = 2 and k 2 , k 3 = 3, and particularly hierarchical representations are learned only for the attribute presence state.  ... 
arXiv:1805.10603v1 fatcat:y4sfmjwrhbdcziyoar7frm3xgy
« Previous Showing results 1 — 15 out of 120,385 results