IJCNN 2018

232 papers
The 2018 International Joint Conference on Neural Networks (IJCNN) featured 280 papers addressing diverse topics in neural computation and machine learning. Research themes focused heavily on enhancing model robustness and efficiency, with significant work in physics-constrained learning and hierarchical inductive biases for sequence modeling. Affective computing was a prominent area of study, particularly regarding multimodal fusion and bridging domain gaps in speech emotion recognition. Additionally, researchers explored the adaptation of vision foundation models to specialized medical domains and the representation of irregular time series as unordered sets. Methodological trends included the development of compact visual descriptors for large-scale image retrieval and class-blind pruning techniques for deep neural networks. Practical applications highlighted in the proceedings ranged from power grid contingency anticipation and multiagent path planning to 3D prostate MR segmentation. Prolific authors contributing to this year's edition included Stefan Wermter, Michael Blumenstein, and Badong Chen. Collectively, the research emphasized the integration of domain-specific knowledge into deep learning architectures to improve performance in "in-the-wild" scenarios and specialized technical fields.

Top Research Directions

Research directions most represented by IJCNN 2018 papers.

Topological Self Organization through Spatial Connectivity Constraints 2
Local Credit Assignment in Deep Neural Networks 2
Scaling Memory Banks for High Dimensional Features 2
The Natural to Medical Image Feature Mismatch 2
Equalizing Local Feature Contributions in Visual Pooling 1
Transforming Non-Metric Proximity into Euclidean Nearest Neighbor Search 1
Non-Uniform Landmark Selection for Nyström Approximations 1
Topographic Neural Organization via Distance Dependent Regularization 1
Selecting Representative Data via Cluster Centroids 1
Bidirectional Latent State Inference for Sequential Models 1
Mitigating the Combinatorial Explosion of Network Contingencies 1
Locally Connected Layers for Position-Dependent Features 1
Scaling Biologically Plausible Learning to Deep Networks 1
Locally Adaptive Distance Metrics 1
Bridging Millisecond Plasticity and Behavioral Timescales 1

Top Authors

AuthorPapers
Stefan Wermter10
Badong Chen5
Michael Blumenstein5
Dongbin Zhao4
Dongsheng Li4
Ana L. C. Bazzan3
Bernhard Sick3
Chuan Zhou3
João Paulo Pordeus Gomes3
Li Guo3
Long Lan3
Rodrigo C. Barros3
Shirui Pan3
Xiang Zhang3
Zhigang Luo3
Abigail Morrison2
Alessio Micheli2
Alexander N. Gorban2
Ali Ghodsi2
Bao-liang Lu2

Impactful Papers

Papers from IJCNN 2018 that shaped research clusters.

Influential

Papers

Title
Multi-granularity Hierarchical Attention Siamese Network for Visual Tracking
Multi-modal Feedback for Affordance-driven Interactive Reinforcement Learning
Multimodal Vigilance Estimation with Adversarial Domain Adaptation Networks
Multi-view Construction for Clustering Based on Feature set Partitioning
Neural Network based Distributed Adaptive Time-varying Formation Control for Multi-UAV Systems with Varying Time Delays
Neural Regression Trees
Noise Invariant Frame Selection: A Simple Method to Address the Background Noise Problem for Text-independent Speaker Verification
Non-Mercer Large Scale Multiclass Least Squares Minimal Complexity Machines
Nonnegative Matrix Factorization Using Autoencoders And Exponentiated Gradient Descent
Nonstationary topological learning with bridges and convex polytopes: the G-EXIN neural network
Object Detection Based on Hierarchical Multi-view Proposal Network for Autonomous Driving
Octree-based Convolutional Autoencoder Extreme Learning Machine for 3D Shape Classification
On Learning Community-specific Similarity Metrics for Cold-start Link Prediction
Online Feature Learning from a non-i.i.d. Stream in a Neuromorphic System with Synaptic Competition
Online Shortest Paths With Confidence Intervals for Routing in a Time Varying Random Network
Optimizing exchange confidence during collaborative clustering
Outlier Detection Based on the Data Structure
Parameter Transfer Extreme Learning Machine based on Projective Model
Path Planning of Multiagent Constrained Formation through Deep Reinforcement Learning
Person Head Detection in Multiple Scales Using Deep Convolutional Neural Networks
Point Cloud Object Recognition using 3D Convolutional Neural Networks
Predicting Concept Drift in Data Streams Using Metadata Clustering
Predicting Group Cohesiveness in Images
Prediction Error Meta Classification in Semantic Segmentation: Detection via Aggregated Dispersion Measures of Softmax Probabilities
PruNet: Class-Blind Pruning Method For Deep Neural Networks
Ranking-Embedded Transfer Canonical Correlation Analysis for Person Re-Identification
Real-Time Detection of Pedestrian Traffic Lights for Visually-Impaired People
Recognition and Prediction of Human-Object Interactions with a Self-Organizing Architecture
Reducing SqueezeNet Storage Size with Depthwise Separable Convolutions
Reducing the Computation Load of Convolutional Neural Networks through Gate Classification
Remaining Useful Life Estimation of Hard Disk Drives based on Deep Neural Networks
Response Characterization for Auditing Cell Dynamics in Long Short-term Memory Networks
Resset: A Recurrent Model for Sequence of Sets with Applications to Electronic Medical Records
Robust 2D Joint Sparse Principal Component Analysis With F-Norm Minimization For Sparse Modelling: 2D-RJSPCA
Robust Locality Preserving Projection Based on Kernel Risk-Sensitive Loss
Scalable NoC-based Neuromorphic Hardware Learning and Inference
Seamless Nudity Censorship: an Image-to-Image Translation Approach based on Adversarial Training
SegNetRes-CRF: A Deep Convolutional Encoder-Decoder Architecture for Semantic Image Segmentation
Selecting local ensembles for multi-class imbalanced data classification
Semantic Image Segmentation Based on Attentions to Intra Scales and Inner Channels
Semi-Supervised Clustering With Multiresolution Autoencoders
SensoryGANs: An Effective Generative Adversarial Framework for Sensor-based Human Activity Recognition
Short-term Traffic Flow Forecasting Using Transfer Ratio and Road Similarity
Similarity-based Multi-label Learning
Sleep Quality Estimation with Adversarial Domain Adaptation: From Laboratory to Real Scenario
Soccer Video Super-Resolution via Sub-Pixel Convolutional Neural Network
Sparse Autoencoders for Posture Recognition
Spiking Locality-Sensitive Hash: Spiking Computation with Phase Encoding Method
Spiking Neural Networks Enable Two-Dimensional Neurons and Unsupervised Multi-Timescale Learning
STDP Learning of Image Patches with Convolutional Spiking Neural Networks

« prev Page 4/5 next »