Nicu Sebe

Motion-Aligned Word Embeddings for Text-to-Motion Generation

Riemannian High-Order Pooling for Brain Foundation Models

Fast and Stable Riemannian Metrics on SPD Manifolds via Cholesky Product Geometry

Inverse Virtual Try-On: Generating Multi-Category Product-Style Images from Clothed Individuals

Rethinking Expressivity and Degradation-Awareness in Attention for All-in-One Blind Image Restoration

HiViBiX: Hierarchical Visually-informed Binaural Audio Generation using Ambisonics

Proper Velocity Neural Networks

VideoExplorer: Boosting Long Video Understanding with Dynamic Temporal Grounding

Riemannian Networks over Full-Rank Correlation Matrices

Intrinsic Lorentz Neural Network

Prototype-based Regularization Learning For Text-Video Retrieval

Benchmarking Physical Reasoning of Video Generative Models with Real Physical Experiments

Efficient Degradation-agnostic Image Restoration via Channel-Wise Functional Decomposition and Manifold Regularization

Building Transformation Layers for Riemannian Neural Networks

VidText: Towards Comprehensive Evaluation for Video Text Understanding

AdvFLYP: Adversarially Finetune Like You Pretrain for Zero-shot Robustness of CLIP

EarthMind: Leveraging Cross-Sensor Data for Advanced Earth Observation Interpretation with a Unified Multimodal LLM

Robust Consensus Anchor Learning for Efficient Multi-view Subspace Clustering

Gyrogroup Batch Normalization

Robust Consensus Anchor Learning for Efficient Multi-view Subspace Clustering

Towards a General Attention Framework on Gyrovector Spaces for Matrix Manifolds

When Semantics Mislead Vision: Mitigating Large Multimodal Models Hallucinations in Scene Text Spotting and Understanding

GyroAtt: A Gyro Attention Framework for Matrix Manifolds

Understanding Matrix Function Normalizations in Covariance Pooling through the Lens of Riemannian Geometry

Hierarchical Information Flow for Generalized Efficient Image Restoration

Riemannian Transformation Layers for General Geometries

Towards Better Understanding Open-set Noise in Learning with Noisy Labels

Algebraic SPD and Correlation Geometry: A Gyro Approach

Enhancing Robustness of Vision-Language Models through Orthogonality Learning and Self-Regularization