Our Publications

Retrieval-enriched zero-shot image classification in low-resource domains

AL-GTD: Deep Active Learning for Gaze Target Detection

UVMap-ID: A Controllable and Personalized UV Map Generative Model

Harnessing Large Language Models for Training-free Video Anomaly Detection

MULTIFLOW: Shifting Towards Task-Agnostic Vision-Language Pruning

OpenBias: Open-set Bias Detection in Text-to-Image Generative Models

PAIR-Diffusion: A Comprehensive Multimodal Object-Level Image Editor

Riemannian Multinomial Logistics Regression for SPD Neural Networks

SHiNe: Semantic Hierarchy Nexus for Open-vocabulary Object Detection

Test-Time Zero-Shot Temporal Action Localization

Less is more: Summarizing Patch Tokens for efficient Multi-Label Class-Incremental Learning

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