Neural Information Processing 28th International Conference, ICONIP 2021, Sanur, Bali, Indonesia, December 8–12, 2021, Proceedings, Part IV /
Neural Information Processing 28th International Conference, ICONIP 2021, Sanur, Bali, Indonesia, December 8–12, 2021, Proceedings, Part IV / [electronic resource] :
edited by Teddy Mantoro, Minho Lee, Media Anugerah Ayu, Kok Wai Wong, Achmad Nizar Hidayanto.
- 1st ed. 2021.
- XXV, 695 p. 261 illus., 233 illus. in color. online resource.
- Theoretical Computer Science and General Issues, 13111 2512-2029 ; .
- Theoretical Computer Science and General Issues, 13111 .
Applications -- Deep Supervised Hashing By Classification For Image Retrieval -- Towards Human-level Performance in Solving Double Dummy Bridge Problem -- Coarse-to-Fine Visual Place Recognition -- BFConv: Improving Convolutional Neural Networks with Butterfly Convolution -- Integrating Rich Utterance Features for Emotion Recognition in Multi-party Conversations -- Vehicle Image Generation Going Well with the Surroundings -- Scale Invariant Domain Generalization Image Recapture Detection -- Tile2Vec with Predicting Noise for Land Cover Classification -- A Joint Representation Learning Approach for Social Media Tag Recommendation -- Identity-based Data Augmentation via Progressive Sampling for One-Shot Person Re-identification -- Feature Fusion Learning Based on LSTM and CNN Networks for Trend Analysis of Limit Order Books -- WikiFlash: Generating Flashcards from Wikipedia Articles -- Video Face Recognition with Audio-Visual Aggregation Network -- WaveFuse: A Unified Unsupervised Framework forImage Fusion with Discrete Wavelet Transform -- Manipulation-invariant Fingerprints for Cross-dataset Deepfake Detection -- Low-resource Neural Machine Translation Using Fast Meta-Learning method -- Efficient, Low-Cost, Real-Time Video Super-Resolution Network -- On the Unreasonable Effectiveness of Centroids in Image Retrieval -- Few-shot Classification with Multi-task Self-supervised Learning -- Self-Supervised Compressed Video Action Recognition via Temporal-Consistent Sampling -- Stack-VAE network for Zero-Shot Learning -- TRUFM: a Transformer-guided Framework for Fine-grained Urban Flow Inference -- Saliency Detection Framework Based on Deep Enhanced Attention Network -- SynthTriplet GAN: Synthetic Query Expansion for Multimodal Retrieval -- SS-CCN: Scale Self-guided Crowd Counting Network -- QS-Hyper: A Quality-Sensitive Hyper Network for the No-Reference Image Quality Assessment -- An Efficient Manifold Density Estimator for All Recommendation Systems -- Cleora: A Simple, Strong and ScalableGraph Embedding Scheme -- STA3DCNN: Spatial-temporal Attention 3D Convolutional Neural Network for Citywide Crowd Flow Prediction -- Learning Pre-Grasp Pushing Manipulation of Wide and Flat Objects using Binary Masks -- Multi-DIP: A General Framework For Unsupervised Multi-degraded Image Restoration -- Multi-Attention Network for Arbitrary Style Transfer -- Image Brightness Adjustment with Unpaired Training -- Self-Supervised Image-to-Text and Text-to-Image Synthesis -- TextCut: A Multi-region Replacement Data Augmentation Approach for Text Imbalance Classification -- A Multi-task Model for Sentiment aided Cyberbullying Detection in Code-Mixed Indian Languages -- A Transformer-based Model for Low-resource Event Detection -- Malicious Domain Detection on Imbalanced Data with Deep Reinforcement Learning -- Designing and Searching for Lightweight Monocular Depth Network -- Improving Question Answering over Knowledge Graphs Using Graph Summarization -- Multi-Stage Hybrid Attentive Networks for Knowledge-Driven Stock Movement Prediction -- End-to-End Edge Detection via Improved Transformer Model -- Isn’t it ironic, don’t you think -- Neural Local and Global Contexts Learning for Word Sense Disambiguation -- Towards Better Dermoscopic Image Feature Representation Learning for Melanoma Classification -- Paraphrase Identification with Neural Elaboration Relation Learning -- Hybrid DE-MLP-based Modeling Technique for Prediction of Alloying Element Proportions and Process Parameters -- A Mutual Information-based Disentanglement Framework for Cross-Modal Retrieval -- AGRP:A Fused Aspect-Graph Neural Network for Rating Prediction -- Classmates Enhanced Diversity-self-attention Network for Dropout Prediction in MOOCs -- A Hierarchical Graph-based Neural Network for Malware Classification -- A Visual Feature Detection Algorithm Inspired by Spatio-temporal Properties of Visual Neurons -- Knowledge Distillation Method for Surface Defect Detection -- Adaptive Selection of Classifiers for Person Recognitionby Iris Pattern and Periocular Image -- Multi-Perspective Interactive Model for Chinese Sentence Semantic Matching -- An Effective Implicit Multi-Interest Interaction Network for Recommendation.
The four-volume proceedings LNCS 13108, 13109, 13110, and 13111 constitutes the proceedings of the 28th International Conference on Neural Information Processing, ICONIP 2021, which was held during December 8-12, 2021. The conference was planned to take place in Bali, Indonesia but changed to an online format due to the COVID-19 pandemic. The total of 226 full papers presented in these proceedings was carefully reviewed and selected from 1093 submissions. The papers were organized in topical sections as follows: Part I: Theory and algorithms; Part II: Theory and algorithms; human centred computing; AI and cybersecurity; Part III: Cognitive neurosciences; reliable, robust, and secure machine learning algorithms; theory and applications of natural computing paradigms; advances in deep and shallow machine learning algorithms for biomedical data and imaging; applications; Part IV: Applications.
9783030922733
10.1007/978-3-030-92273-3 doi
Pattern recognition systems.
Artificial intelligence.
Education--Data processing.
Computer engineering.
Computer networks .
Social sciences--Data processing.
Automated Pattern Recognition.
Artificial Intelligence.
Computers and Education.
Computer Engineering and Networks.
Computer Application in Social and Behavioral Sciences.
Q337.5 TK7882.P3
006.4
Applications -- Deep Supervised Hashing By Classification For Image Retrieval -- Towards Human-level Performance in Solving Double Dummy Bridge Problem -- Coarse-to-Fine Visual Place Recognition -- BFConv: Improving Convolutional Neural Networks with Butterfly Convolution -- Integrating Rich Utterance Features for Emotion Recognition in Multi-party Conversations -- Vehicle Image Generation Going Well with the Surroundings -- Scale Invariant Domain Generalization Image Recapture Detection -- Tile2Vec with Predicting Noise for Land Cover Classification -- A Joint Representation Learning Approach for Social Media Tag Recommendation -- Identity-based Data Augmentation via Progressive Sampling for One-Shot Person Re-identification -- Feature Fusion Learning Based on LSTM and CNN Networks for Trend Analysis of Limit Order Books -- WikiFlash: Generating Flashcards from Wikipedia Articles -- Video Face Recognition with Audio-Visual Aggregation Network -- WaveFuse: A Unified Unsupervised Framework forImage Fusion with Discrete Wavelet Transform -- Manipulation-invariant Fingerprints for Cross-dataset Deepfake Detection -- Low-resource Neural Machine Translation Using Fast Meta-Learning method -- Efficient, Low-Cost, Real-Time Video Super-Resolution Network -- On the Unreasonable Effectiveness of Centroids in Image Retrieval -- Few-shot Classification with Multi-task Self-supervised Learning -- Self-Supervised Compressed Video Action Recognition via Temporal-Consistent Sampling -- Stack-VAE network for Zero-Shot Learning -- TRUFM: a Transformer-guided Framework for Fine-grained Urban Flow Inference -- Saliency Detection Framework Based on Deep Enhanced Attention Network -- SynthTriplet GAN: Synthetic Query Expansion for Multimodal Retrieval -- SS-CCN: Scale Self-guided Crowd Counting Network -- QS-Hyper: A Quality-Sensitive Hyper Network for the No-Reference Image Quality Assessment -- An Efficient Manifold Density Estimator for All Recommendation Systems -- Cleora: A Simple, Strong and ScalableGraph Embedding Scheme -- STA3DCNN: Spatial-temporal Attention 3D Convolutional Neural Network for Citywide Crowd Flow Prediction -- Learning Pre-Grasp Pushing Manipulation of Wide and Flat Objects using Binary Masks -- Multi-DIP: A General Framework For Unsupervised Multi-degraded Image Restoration -- Multi-Attention Network for Arbitrary Style Transfer -- Image Brightness Adjustment with Unpaired Training -- Self-Supervised Image-to-Text and Text-to-Image Synthesis -- TextCut: A Multi-region Replacement Data Augmentation Approach for Text Imbalance Classification -- A Multi-task Model for Sentiment aided Cyberbullying Detection in Code-Mixed Indian Languages -- A Transformer-based Model for Low-resource Event Detection -- Malicious Domain Detection on Imbalanced Data with Deep Reinforcement Learning -- Designing and Searching for Lightweight Monocular Depth Network -- Improving Question Answering over Knowledge Graphs Using Graph Summarization -- Multi-Stage Hybrid Attentive Networks for Knowledge-Driven Stock Movement Prediction -- End-to-End Edge Detection via Improved Transformer Model -- Isn’t it ironic, don’t you think -- Neural Local and Global Contexts Learning for Word Sense Disambiguation -- Towards Better Dermoscopic Image Feature Representation Learning for Melanoma Classification -- Paraphrase Identification with Neural Elaboration Relation Learning -- Hybrid DE-MLP-based Modeling Technique for Prediction of Alloying Element Proportions and Process Parameters -- A Mutual Information-based Disentanglement Framework for Cross-Modal Retrieval -- AGRP:A Fused Aspect-Graph Neural Network for Rating Prediction -- Classmates Enhanced Diversity-self-attention Network for Dropout Prediction in MOOCs -- A Hierarchical Graph-based Neural Network for Malware Classification -- A Visual Feature Detection Algorithm Inspired by Spatio-temporal Properties of Visual Neurons -- Knowledge Distillation Method for Surface Defect Detection -- Adaptive Selection of Classifiers for Person Recognitionby Iris Pattern and Periocular Image -- Multi-Perspective Interactive Model for Chinese Sentence Semantic Matching -- An Effective Implicit Multi-Interest Interaction Network for Recommendation.
The four-volume proceedings LNCS 13108, 13109, 13110, and 13111 constitutes the proceedings of the 28th International Conference on Neural Information Processing, ICONIP 2021, which was held during December 8-12, 2021. The conference was planned to take place in Bali, Indonesia but changed to an online format due to the COVID-19 pandemic. The total of 226 full papers presented in these proceedings was carefully reviewed and selected from 1093 submissions. The papers were organized in topical sections as follows: Part I: Theory and algorithms; Part II: Theory and algorithms; human centred computing; AI and cybersecurity; Part III: Cognitive neurosciences; reliable, robust, and secure machine learning algorithms; theory and applications of natural computing paradigms; advances in deep and shallow machine learning algorithms for biomedical data and imaging; applications; Part IV: Applications.
9783030922733
10.1007/978-3-030-92273-3 doi
Pattern recognition systems.
Artificial intelligence.
Education--Data processing.
Computer engineering.
Computer networks .
Social sciences--Data processing.
Automated Pattern Recognition.
Artificial Intelligence.
Computers and Education.
Computer Engineering and Networks.
Computer Application in Social and Behavioral Sciences.
Q337.5 TK7882.P3
006.4