GLAD: Towards Better Reconstruction with Global and Local Adaptive Diffusion Models for Unsupervised Anomaly Detection.- MedRAT: Unpaired Medical Report Generation via Auxiliary Tasks.- Are Synthetic Data Useful for Egocentric Hand-Object Interaction Detection?.- PoseEmbroider: Towards a 3D, Visual, Semantic-aware Human Pose Representation.- A Comparative Study of Image Restoration Networks for General Backbone Network Design.- Learned Image Enhancement via Color Naming.- Synthesizing Time-varying BRDFs via Latent Space.- HoloADMM: High-Quality Holographic Complex Field Recovery.- Fundamental Matrix Estimation Using Relative Depths.- Gaussian Splatting on the Move: Blur and Rolling Shutter Compensation for Natural Camera Motion.- MTaDCS: Moving Trace and Feature Density-based Confidence Sample Selection under Label Noise.- Towards Open-World Object-based Anomaly Detection via Self-Supervised Outlier Synthesis.- GroundUp: Rapid Sketch-Based 3D City Massing.- Guide-and-Rescale: Self-Guidance Mechanism for Effective Tuning-Free Real Image Editing.- DataDream: Few-shot Guided Dataset Generation.- LPViT: Low-Power Semi-structured Pruning for Vision Transformers.- CipherDM: Secure Three-Party Inference for Diffusion Model Sampling.- Weighted Ensemble Models Are Strong Continual Learners.- GGRt: Towards Generalizable 3D Gaussians without Pose Priors in Real-Time.- A Unified Image Compression Method for Human Perception and Multiple Vision Tasks.- UniVoxel: Fast Inverse Rendering by Unified Voxelization of Scene Representation.- Audio-visual Generalized Zero-shot Learning the Easy Way.- PartImageNet++ Dataset: Scaling up Part-based Models for Robust Recognition.- Learning Equilibrium Transformation for Gamut Expansion and Color Restoration.- Dyn-Adapter: Towards Disentangled Representation for Efficient Visual Recognition.- Physics-informed Knowledge Transfer for Underwater Monocular Depth Estimation.
