Massimiliano Mancini

Affiliations

Sapienza University of Rome, Rome , Italy

papers

1,004

total citations

papers (23)

KG-SP: Knowledge Guided Simple Primitives for Open World Compositional Zero-Shot Learning

CVPR 2022arXiv

citations

Vocabulary-free Image Classification

NEURIPS 2023arXiv

citations

BayesCap: Bayesian Identity Cap for Calibrated Uncertainty in Frozen Neural Networks

ECCV 2022arXiv

citations

PDiscoNet: Semantically consistent part discovery for fine-grained recognition

ICCV 2023arXiv

citations

Abstracting Sketches through Simple Primitives

ECCV 2022arXiv

citations

Image-Free Classifier Injection for Zero-Shot Classification

ICCV 2023arXiv

citations

Iterative Superquadric Recomposition of 3D Objects from Multiple Views

ICCV 2023arXiv

citations

Rethinking Few-Shot Adaptation of Vision-Language Models in Two Stages

CVPR 2025arXiv

citations

MULTIFLOW: Shifting Towards Task-Agnostic Vision-Language Pruning

CVPR 2024arXiv

citations

ProbVLM: Probabilistic Adapter for Frozen Vison-Language Models

ICCV 2023arXiv

citations

Relational Proxies: Emergent Relationships as Fine-Grained Discriminators

NEURIPS 2022arXiv

citations

Transitivity Recovering Decompositions: Interpretable and Robust Fine-Grained Relationships

NEURIPS 2023arXiv

citations

Not Only Text: Exploring Compositionality of Visual Representations in Vision-Language Models

CVPR 2025arXiv

citations

Classifier-to-Bias: Toward Unsupervised Automatic Bias Detection for Visual Classifiers

CVPR 2025arXiv

citations

Compositional Caching for Training-free Open-vocabulary Attribute Detection

CVPR 2025arXiv

citations

On Large Multimodal Models as Open-World Image Classifiers

ICCV 2025arXiv

citations

Training-Free Personalization via Retrieval and Reasoning on Fingerprints

ICCV 2025arXiv

citations

Can Text-to-Video Generation help Video-Language Alignment?

CVPR 2025arXiv

citations

Massimiliano Mancini

Affiliations

papers (23)

Modeling the Background for Incremental Learning in Semantic Segmentation

Open World Compositional Zero-Shot Learning

Towards Recognizing Unseen Categories in Unseen Domains

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

Harnessing Large Language Models for Training-free Video Anomaly Detection

KG-SP: Knowledge Guided Simple Primitives for Open World Compositional Zero-Shot Learning

Vocabulary-free Image Classification

BayesCap: Bayesian Identity Cap for Calibrated Uncertainty in Frozen Neural Networks

PDiscoNet: Semantically consistent part discovery for fine-grained recognition

Abstracting Sketches through Simple Primitives

Image-Free Classifier Injection for Zero-Shot Classification

Iterative Superquadric Recomposition of 3D Objects from Multiple Views

Rethinking Few-Shot Adaptation of Vision-Language Models in Two Stages

MULTIFLOW: Shifting Towards Task-Agnostic Vision-Language Pruning

ProbVLM: Probabilistic Adapter for Frozen Vison-Language Models

Relational Proxies: Emergent Relationships as Fine-Grained Discriminators

Transitivity Recovering Decompositions: Interpretable and Robust Fine-Grained Relationships

Not Only Text: Exploring Compositionality of Visual Representations in Vision-Language Models

Classifier-to-Bias: Toward Unsupervised Automatic Bias Detection for Visual Classifiers

Compositional Caching for Training-free Open-vocabulary Attribute Detection

On Large Multimodal Models as Open-World Image Classifiers

Training-Free Personalization via Retrieval and Reasoning on Fingerprints

Can Text-to-Video Generation help Video-Language Alignment?

papers (23)

Modeling the Background for Incremental Learning in Semantic Segmentation

Open World Compositional Zero-Shot Learning

Towards Recognizing Unseen Categories in Unseen Domains

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

Harnessing Large Language Models for Training-free Video Anomaly Detection

KG-SP: Knowledge Guided Simple Primitives for Open World Compositional Zero-Shot Learning

Vocabulary-free Image Classification

BayesCap: Bayesian Identity Cap for Calibrated Uncertainty in Frozen Neural Networks

PDiscoNet: Semantically consistent part discovery for fine-grained recognition

Abstracting Sketches through Simple Primitives

Image-Free Classifier Injection for Zero-Shot Classification

Iterative Superquadric Recomposition of 3D Objects from Multiple Views

Rethinking Few-Shot Adaptation of Vision-Language Models in Two Stages

MULTIFLOW: Shifting Towards Task-Agnostic Vision-Language Pruning

ProbVLM: Probabilistic Adapter for Frozen Vison-Language Models

Relational Proxies: Emergent Relationships as Fine-Grained Discriminators

Transitivity Recovering Decompositions: Interpretable and Robust Fine-Grained Relationships

Not Only Text: Exploring Compositionality of Visual Representations in Vision-Language Models

Classifier-to-Bias: Toward Unsupervised Automatic Bias Detection for Visual Classifiers

Compositional Caching for Training-free Open-vocabulary Attribute Detection

On Large Multimodal Models as Open-World Image Classifiers

Training-Free Personalization via Retrieval and Reasoning on Fingerprints

Can Text-to-Video Generation help Video-Language Alignment?