Our Publications

Lost and Found: Overcoming Detector Failures in Online Multi-Object Tracking

A Lie Group Approach to Riemannian Batch Normalization

Democratizing Fine-grained Visual Recognition with Large Language Models

Conditioned Prompt-Optimization for Continual Deepfake Detection

Text-Enhanced Zero-Shot Action Recognition: A training-free approach

Frustratingly Easy Test-Time Adaptation of Vision-Language Models

Adaptive Log-Euclidean Metrics for SPD Matrix Learning

Understanding Sparse Neural Networks from their Topology via Multipartite Graph Representations