Neural Information Processing

Anchor STARK: Query Design for Transformer-Based Target Tracking.- DACG-Net: A Dual Attention and Classifier Guided Network for Low-Light Image Enhancement.- Improved Aggregated Contextual Transformations Based on U-Net for Image Inpainting.- Mitigating Vanishing Activations in Deep CapsNets Using Channel Pruning.- A Novel Data Synthesis Method by Integration of Diffusion Model and GAN for Object Detection Task.- MOSSE-YOLOv8: A Two-Stage Approach for Small-Target Arc Detection in High-Speed Railways.- SAM-FL:Enhanced Generalizable Medical Image Segmentation via Sharpness-Aware Minimization and Focal Loss.- CP2PNet: A General End-to-End Framework for Plant Organs Counting and Phenological Stage Prediction.- Hierarchical Prompt-Enhanced Image Generation Using Hyperbolic Space.- Efficient Conditional Diffusion Model for Accurate Pedestrian
Trajectory Prediction.- MonoViM: Enhancing Self-supervised Monocular Depth Estimation via Mamba.- An End-to-End rPPG-Based Face Anti-Spoofing Network with Deception Enhancement Module.- Region-Aware Instruction-Guided Image Editing with Attention-Weighted Feature Fusion.- Multi-view Self-supervised 3D Human Pose and Shape Estimation on SMPL.- WT-based Feature Enhancement Network for Camouflaged Object Detection.- Multi-Headed Graph-based Attention aided U-Net Model for Nuclei Segmentation.- Research and Implementation of Fine-Grained Bird Image Classification.- LSC-YOLO: Small Target Defects Detection Model for Wind Turbine Blade based on YOLOv9.- SAU: A Dual-Branch Network to Enhance Long-Tailed Recognition via Generative Models.- Leveraging local similarity for token merging in Vision Transformers.- Semi-Supervised Domain Adaptation for All Weather Point Cloud Semantic Segmentation.- Federated Learning for Blind Image Super-Resolution.- Towards Better Text-to-Image Generation Alignment via Attention Modulation.- CLOFAI: A Dataset of Real And Fake Image Classification Tasks for Continual Learning.- AMSA-UNet: An Asymmetric Multiple Scales U-net Based on Self-attention for Deblurring.- MT-Net: A Dual-Encoder Multiscale Medical Segmentation Model.- ENHANCING ADVERSARIAL ROBUSTNESS OF DIFFUSION DENOISED SMOOTHING VIA IMAGE SUPER-RESOLUTION.- A simultaneous hierarchical count data clustering and feature selection based on Multinomial Nested Dirichlet Mixture using the Minorization-Maximization framework.