multi-scale feature

AKCMamba-YOLO: Selective State Space Models For Real-Time Object Detection CVPR 2026 Clear Sights on Site: A Spatial-Adaptive Channel Network for Deblurring Construction Site Images WACV 2026 Efficient Learned Data Compression via Dual-Stream Feature Decoupling ACL 2026 M3SR: Multi-Scale Multi-Perceptual Mamba for Efficient Spectral Reconstruction AAAI 2026 Moire Zero: An Efficient and High-Performance Neural Architecture for Moire Removal WACV 2026 MSPCaps: A Multi-Scale Patchify Capsule Network with Cross-Agreement Routing for Visual Recognition AAAI 2026 MSTDiff: Multiscale-Aware Transformer Diffusion Network for Video Object Detection AAAI 2026 MS-Temba: Multi-Scale Temporal Mamba for Understanding Long Untrimmed Videos CVPR 2026 RMFAT: Recurrent Multi-scale Feature Atmospheric Turbulence Mitigator AAAI 2026 AS-Det: Active Sampling for Adaptive 3D Object Detection in Point Clouds AAAI 2025 Auto-Regressive Transformation for Image Alignment ICCV 2025 BUFFER-X: Towards Zero-Shot Point Cloud Registration in Diverse Scenes ICCV 2025 Charm: The Missing Piece in ViT Fine-Tuning for Image Aesthetic Assessment CVPR 2025 CViT: Continuous Vision Transformer for Operator Learning ICLR 2025 D2FP: Learning Implicit Prior for Human Parsing WACV 2025 Diffusion Transformer meets Multi-level Wavelet Spectrum for Single Image Super-Resolution ICCV 2025 DiGIT: Multi-Dilated Gated Encoder and Central-Adjacent Region Integrated Decoder for Temporal Action Detection Transformer CVPR 2025 EchoDiffusion: Waveform Conditioned Diffusion Models for Echo-Based Depth Estimation AAAI 2025 ElaD-Net: An Elastic Semantic Decoupling Network for Lesion Segmentation in Breast Ultrasound Images IJCAI 2025 ESCNet:Edge-Semantic Collaborative Network for Camouflaged Object Detection ICCV 2025 FBRT-YOLO: Faster and Better for Real-Time Aerial Image Detection AAAI 2025 Frequency-Aware Deep Depth from Focus IJCAI 2025 HAMoBE: Hierarchical and Adaptive Mixture of Biometric Experts for Video-based Person ReID ICCV 2025 HeightMapNet: Explicit Height Modeling for End-to-End HD Map Learning WACV 2025 Hyper-Depth: Hypergraph-based Multi-Scale Representation Fusion for Monocular Depth Estimation ICCV 2025