E-raamat: PRICAI 2022: Trends in Artificial Intelligence: 19th Pacific Rim International Conference on Artificial Intelligence, PRICAI 2022, Shanghai, China, November 10-13, 2022, Proceedings, Part III

Recommender System.- Mixture of Graph Enhanced Expert Networks for
Multi-task Recommendation.- MF-TagRec: Multi-feature fused tag recommendation
for GitHub.- Co-contrastive Learning for Multi-behavior
Recommendation.- Pattern Matching and Information-aware between Reviews
and Ratings for Recommendation.- Cross-view Contrastive Learning for
Knowledge-aware Session-based Recommendation.- Reinforcement Learning.- HiSA:
Facilitating Efficient Multi-Agent Coordination and Cooperation by
Hierarchical Policy with Shared Attention.- DDMA: Discrepancy-Driven
Multi-Agent Reinforcement Learning.- PRAG: Periodic Regularized Action
Gradient for Efficient Continuous Control.- Identifying Multiple Influential
Nodes for Complex Networks based on Multi-Agent Deep Reinforcement
Learning.- Online Learning in Iterated Prisoners Dilemma to Mimic Human
Behavior.- Optimizing Exploration-Exploitation Trade-off in Continuous Action
Spaces via Q-ensemble.- Hidden Information General Game Playing With Deep
Learning and Search.- Sequential Decision Making with Sequential
Information in Deep Reinforcement
Learning.- Two-Stream Communication-Efficient Federated Pruning
Network.- Strong General AI.- Multi-scale Lightweight Neural Network for
Real-time Object Detection.- Hyperspectral Image Classification Based On
Transformer and Generative Adversarial Network.- Deliberation Selector for
Knowledge-grounded Conversation Generation.- Training a Lightweight ViT
Network for Image Retrieval.- Vision and Perception.- Segmentedoriginal
Image Pairs to Facilitate Feature Extraction in Deep Learning Models.-
FusionSeg: Motion Segmentation by Jointly Exploiting Frames and
Events.- Weakly-supervised Temporal Action Localization with Multi-head
Cross-modal Attention.- CrGAN: Continuous Rendering of Image Style.- DPCN:
Dual Path Convolutional Network for Single Image Deraining.- All Up to You:
Controllable Video Captioning With a Masked Scene Graph.- A Multi-Head
Convolutional Neural Network With Multi-path Attention improves Image
Denoising.- Learning Spatial Fusion and Matching for Visual Object
Tracking.- Lightweight Wavelet-based Transformer for Image Super-resolution.-
Efficient high-resolution human pose estimation.- The Geometry Enhanced Deep
Implicit Function based 3D Reconstruction for objects in a real-scene
image.- Multi-View Stereo Network with Attention Thin Volume.- 3D Point Cloud
Segmentation Leveraging Global 2D-view Features.- Self-Supervised
Indoor 360-Degree Depth Estimation via Structural Regularization.- Global
Boundary Refinement for Semantic Segmentation via Optimal
Transport.- Optimization-based Predictive Approach for On-Demand 
Transportation.- JointContrast: Skeleton-based Mutual Action Recognition with
Contrastive Learning.- Nested Multi-Axis Learning Network for Single
Image Super Resolution.- Efficient Scale Divide and Conquer Network for
Object Detection.- Video-Based Emotion Recognition in the Wild for Online
Education Systems.- Real-world Underwater Image Enhancement via
Degradation-aware Dynamic Network.- Self-Supervised Vision Transformer based
Nearest Neighbor Classification for Multi-Source Open-Set Domain
Adaptation.- Lightweight image dehazing neural network model based on
estimating medium transmission map by intensity.- CMNet: Cross-aggregation
Multi-branch Network for Salient Object Detection.- More than Accuracy: an
Empirical Study of Consistency between Performance and
Interpretability.- Object-scale Adaptive Optical Flow Estimation Network.- A
Task-aware Dual Similarity Network for Fine-grained Few-shot
Learning.- Rotating Target Detection Based On Lightweight Network.- Corner
Detection Based on a Dynamic Measure of Cornerity.