A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Filters
Unifying Text, Metadata, and User Network Representations with a Neural Network for Geolocation Prediction
2017
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Preserved Fulltext
We propose a novel geolocation prediction model using a complex neural network. ...
In an evaluation using two open datasets, the proposed model exhibited a maximum 3.8% increase in accuracy and a maximum of 6.6% increase in ac-curacy@161 against previous models. ...
Acknowledgments We would like to thank the members of Okumura-Takamura Group at Tokyo Institute of Technology for having insightful discussions about user profiling models in social media. ...
doi:10.18653/v1/p17-1116
dblp:conf/acl/MiuraTTO17
fatcat:gaewrqkw75gn7fsqzud3gqe4by
TPPO: A Novel Trajectory Predictor with Pseudo Oracle
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2021 pre-print arXiv:2002.01852v2 fatcat:b2jjy4rwgfeohdiqk3ovsf7iyuOther Versions
Forecasting pedestrian trajectories in dynamic scenes remains a critical problem in various applications, such as autonomous driving and socially aware robots. ...
In this work, we propose the Trajectory Predictor with Pseudo Oracle (TPPO), which is a generative model-based trajectory predictor. ...
In the (a) training stage, the generator and discriminator are trained in an adversarial manner. ...
arXiv:2002.01852v3
fatcat:45g6rucccrcmrd6qtbjrshrng4
It Is Not the Journey but the Destination: Endpoint Conditioned Trajectory Prediction
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
In this work, we present Predicted Endpoint Conditioned Network (PECNet) for flexible human trajectory prediction. ...
Human trajectory forecasting with multiple socially interacting agents is of critical importance for autonomous navigation in human environments, e.g., for self-driving cars and social robots. ...
However, such a choice will decouple training of the Endpoint VAE (which would then train only with KL Divergence and AWL loss, refer Section 3.3) and social pooling network (which would then train only ...
arXiv:2004.02025v3
fatcat:3io6h3ogrjfuxmzbovdxowc5qy
Fine-tuning Graph Neural Networks by Preserving Graph Generative Patterns
[article]
2023
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2024; you can also visit the original URL.
The file type is application/pdf.
Recently, the paradigm of pre-training and fine-tuning graph neural networks has been intensively studied and applied in a wide range of graph mining tasks. ...
To overcome this challenge, we provide a theoretical analysis that establishes the existence of a set of alternative graphons called graphon bases for any given graphon. ...
Acknowledgments This work is supported by NSFC (No.62322606) and the Fundamental Research Funds for the Central Universities. ...
arXiv:2312.13583v1
fatcat:opyqcznipfdoph2sn2ve63t6my
Anticipating Human Intention for Full-Body Motion Prediction in Object Grasping and Placing Tasks
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
We propose dedicated function networks for graspability and placebility affordances and we make use of a dedicated RNN for short-term motion prediction. ...
Motion prediction in unstructured environments is a difficult problem and is essential for safe and efficient human-robot space sharing and collaboration. ...
The authors thank the International Max Planck Research School for Intelligent Systems (IMPRS-IS) for supporting Philipp Kratzer. ...
arXiv:2007.10038v1
fatcat:a73cyc24wvgydi2o4znqedb7bi
Distinguishing Oracle Variants Based on the Isomorphism and Symmetry Invariances of Oracle-bone Inscriptions
2020
IEEE Access
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
get sufficient training samples in the first stage. ...
In the second stage, on the basis of the first stage, a set of recognition results that cannot be determined roughly is selected, and a priori knowledge is introduced to integrate multi-domain methods ...
It refers to that for each type of the oracle glyph pictures in the test set, a label whose classification result predicted by the training model is likely to be greater than a certain threshold value ...
doi:10.1109/access.2020.3017533
fatcat:llilwg6p3fette7coqxcgz6y5a
Internal Similarity Network for Rejoining Oracle Bone Fragment Images
2022
Symmetry
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
However, current computer vision technology has a low accuracy in judging whether the texture of oracle bone fragment image pairs can be put back together. ...
similarity network (ISN) to rejoin the fragment image automatically. ...
[7] gave a shortest path optimization method that uses a neural network to predict positions of archaeological fragments, and a graph that leads to the best reassembly is made from these predictions ...
doi:10.3390/sym14071464
fatcat:nzt3dp7cb5exxjpdxjmvmijxu4
Power system online stability assessment using active learning and synchrophasor data
2013
2013 IEEE Grenoble Conference
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2014; you can also visit the original URL.
The file type is application/pdf.
Results show that the advantage of active learning approach is greater on more complicated prediction tasks, those requiring a large amount of data for accurate predictions. ...
Advancements in machine learning may make it possible to reduce the amount of data that need to be analyzed without decreasing accuracy of predictions. ...
of networked data, such as links in web pages or social network data [7] . ...
doi:10.1109/ptc.2013.6652213
fatcat:cq74pg4wm5ctlbxyiohpmjzktm
Improving Semantic Parsing with Neural Generator-Reranker Architecture
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
The generator produces a list of potential candidates and the reranker, which consists of a pre-processing step for the candidates followed by a novel critic network, reranks these candidates based on ...
In this work, we propose a generator-reranker architecture for semantic parsing. ...
In this work we propose a generator-reranker architecture that uses two neural networks for semantic parsing: a generator network, which generates a list of potential candidates, and a reranker system, ...
arXiv:1909.12764v1
fatcat:7kmrfwmo4bazjhdf2zeg3zseee
On Quantitative Evaluations of Counterfactuals
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
In this paper, we consolidate the work on evaluating visual counterfactual examples through an analysis and experiments. ...
To mitigate this issue, we propose two new metrics, the Label Variation Score and the Oracle score, which are both less vulnerable to such tiny changes. ...
Finally, we know of no publicly available pre-trained auto-encoders for computing the score. ...
arXiv:2111.00177v1
fatcat:moyfvvmztfgpvngngzpayj6soq
Deep Distance Sensitivity Oracles
[article]
2023
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2022 pre-print arXiv:2211.02681v1 fatcat:bvuwovji7jhsnafbreqyagqlci
referred to as a Distance Sensitivity Oracle (DSO). ...
One way to overcome this problem is to shift computational burden from the queries into a pre-processing step, where a data structure is computed that allows for fast querying of replacement paths, typically ...
Such a data structure is called a distance sensitivity oracle (or DSO for short). ...
arXiv:2211.02681v2
fatcat:qq5k4xjkozhd5gb264l26e3gw4
An Oracle Bone Inscription Detector Based on Multi-Scale Gaussian Kernels
2021
Applied Mathematics
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Besides, based on the kernel predictions of different scales, a novel post-processing pipeline is used to obtain accurate predictions of bounding boxes. ...
The existing methods are based on the scheme of anchor boxes, involving complex network design and a great number of anchor boxes. ...
Introduction Oracle Bone Inscriptions (OBIs) are of the oldest and the most mysterious ancient characters in china, which record a large number of unknown ancestors' lives, thoughts, and social states ...
doi:10.4236/am.2021.123014
fatcat:7pn45sluqrdwnblrygxz34pmli
About latent roles in forecasting players in team sports
[article]
2023
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2023; you can also visit the original URL.
The file type is application/pdf.
Other Versions
In this work, we hypothesize that each participant has a specific function in each action and that role-based interaction is critical for predicting players' future moves. ...
Forecasting players in sports has grown in popularity due to the potential for a tactical advantage and the applicability of such research to multi-agent interaction systems. ...
Moreover, the EuclDistEst variant attempts to answer part of this question.Here we used a pre-trained Neural Network module to approximate the Euclidean distance based on the player's performance.We then ...
arXiv:2304.08272v2
fatcat:fmb3vmeq3ra2pivuf74gu5oj6u
A Survey on Graph Counterfactual Explanations: Definitions, Methods, Evaluation
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Other Versions
In recent years, Graph Neural Networks have reported outstanding performance in tasks like community detection, molecule classification and link prediction. ...
In this survey, we analyse the existing Graph Counterfactual Explanation methods, by providing the reader with an organisation of the literature according to a uniform formal notation for definitions, ...
space without a pre-trained generative model or set of reaction rules [90] . ...
arXiv:2210.12089v1
fatcat:fvcbx2cslfhs5fz5xikjie6mxa
Meta-learning with Latent Space Clustering in Generative Adversarial Network for Speaker Diarization
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
To this end, we fetch the pre-trained encoder from the ClusterGAN and fine-tune it by using prototypical loss (meta-ClusterGAN or MCGAN) under the meta-learning paradigm. ...
Earlier work on speaker diarization using generative adversarial network (GAN) with an encoder network (ClusterGAN) to project input x-vectors into a latent space has shown promising performance on meeting ...
In the second phase of MCGAN training, we fine-tune the pre-trained encoder with meta-learning based prototypical loss. a) Meta-learning using prototypical networks: Prototypical networks, or protonets ...
arXiv:2007.09635v1
fatcat:lsd724sw5rhwbi7q7hsehsfgim
« Previous
Showing results 1 — 15 out of 4,793 results