Full Description
The proceedings set LNCS 11727, 11728, 11729, 11730, and 11731 constitute the proceedings of the 28th International Conference on Artificial Neural Networks, ICANN 2019, held in Munich, Germany, in September 2019. The total of 277 full papers and 43 short papers presented in these proceedings was carefully reviewed and selected from 494 submissions. They were organized in 5 volumes focusing on theoretical neural computation; deep learning; image processing; text and time series; and workshop and special sessions.
Contents
Unsharp Masking Layer: Injecting Prior Knowledge in Convolutional Networks for Image Classification.- Distortion Estimation Through Explicit Modeling of the Refractive Surface.- Eye Movement-based Analysis on Methodologies and Efficiency in the Process of Image Noise Evaluation.- IBDNet: Lightweight Network for On-orbit Image Blind Denoising.- Aggregating Rich Deep Semantic Features for Fine-Grained Place Classification.- Improving Reliability of Object Detection for Lunar Craters using Monte Carlo Dropout.- An improved convolutional neural network for steganalysis in the scenario of reuse of the stego-key.- A New Learning-based One Shot Detection Framework For Natural Images.- Dense Receptive Field Network: A Backbone Network for Object Detection.- Referring Expression Comprehension via Co-attention and Visual Context.- Comparison between U-Net and U-ReNet models in OCR tasks.- Severe Convective Weather Classification in Remote Sensing Images by Semantic Segmentation.- Action Recognition Based on Divide-and-conquer.- An Adaptive Feature Channel Weighting Scheme for Correlation Tracking.- In-silico staining from bright-field and fluorescent images using deep learning.- A lightweight neural network for hard exudate segmentation of fundus image.- Attentional Residual Dense Factorized Network for Real-time Semantic Segmentation.- Random drop loss for tiny object segmentation: Application to lesion segmentation in fundus images.- Flow2Seg: Motion-Aided Semantic Segmentation.- COCO_TS Dataset: Pixel-level Annotations Based on Weak Supervision for Scene Text Segmentation.- Learning Deep Structured Multi-Scale Features for crisp and occlusion edge detection.- Graph-Boosted Attentive Network for Semantic Body Parsing.- A Global-Local Architecture Constrained by Multiple Attributes for Person Re-identification.- Recurrent Connections Aid Occluded Object Recognition by Discounting Occluders.- Learning Relational-Structural Networks for Robust Face Alignment.- An Efficient 3D-NAS Method for Video-based Gesture Recognition.- Robustness of deep LSTM networks in freehand gesture recognition.- Delving into the Impact of Saliency Detector: A GeminiNet for Accurate Saliency Detection.- FCN Salient Object Detection Using Region Cropping.- Object-Level Salience Detection By Progressively Enhanced Network.- Action unit assisted Facial Expression Recognition.- Discriminative Feature Learning using Two-stage Training Strategy for Facial Expression Recognition.- Action Units Classification using ClusWiSARD.- Automatic Estimation of Dog Age: The DogAge Dataset and Challenge.- Neural Network 3D Body Pose Tracking and Prediction for Motion-to-Photon Latency Compensation in Distributed Virtual Reality.- Variational Deep Embedding with Regularized Student-t Mixture Model.- A mixture-of-experts model for vehicle prediction using an online learning approach.- An Application of Convolutional Neural Networks for Analyzing Dogs' Sleep Patterns.- On the Inability of Markov Models to Capture Criticality in Human Mobility.- LSTM with Uniqueness Attention for Human Activity Recognition.- Comparative Research on SOM with Torus and Sphere Topologies for Peculiarity Classification of Flat Finishing Skill Training.- Generative Creativity: Adversarial Learning for Bionic Design.- Self-attention StarGAN for Multi-domain Image-to-image Translation.- Generative Adversarial Networks for Operational Scenario Planing of Renewable Energy Farms: A Study on Wind and Photovoltaic.- Constraint-Based Visual Generation.- Text to Image Synthesis based on Multiple Discrimination.- Disentangling Latent Factors of Variational Auto-Encoder with Whitening.- Training Discriminative Models to Evaluate Generative Ones.- Scene Graph Generation via Convolutional Message Passing and Class-aware Memory Embeddings.- Change Detection in Satellite Images using Reconstruction Errors of Joint Autoencoders.- Physical Adversarial Attacks by Projecting Perturbations.- Improved Forward-backward Propagation to Generate Adversarial Examples.- Incremental Learning of GAN for Detecting Multiple Adversarial Attacks.- Evaluating Defensive Distillation For Defending Text Processing Neural Networks Against Adversarial Examples.- DCT:Differential Combination Testing of Deep Learning Systems.- Restoration as a Defense Against Adversarial Perturbations for Spam Image Detection.- HLR: Generating Adversarial Examples by High-Level Representations.
