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
Joint Contrast: 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.