Massimiliano Mancini

32 papers · 2017–2026 · 8 conferences · across top CS/AI conferences

Achievements

+11 more ↓

🏃 Academic Marathon (9) 🌍 Conference Polyglot (7) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird

🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🌍 Conference Polyglot (7) 🤝 Dynamic Duo (16) 🧬 Topic Evolution 💎 Century Club (31) 📈 Trend Setter ⚡ Prolific Year (6) 🗃️ Keyword Collector (144) ❓ The Questioner 🔥 Unstoppable (10)

Conferences

CVPR (13) ICCV (6) NIPS (4) ECCV (3) WACV (3) AAAI (1) CONLL (1) ICLR (1)

Top co-authors

Elisa Ricci (16) Zeynep Akata (12) Yiming Wang (6) Shyamgopal Karthik (4) Matteo Farina (4) Barbara Caputo (4) Nicu Sebe (3) Samuel Rota Bulò (3) Anjan Dutta (3) Giovanni Iacca (3)

Keywords

vision-language model (8) zero-shot learning (6) vision language model (5) large language model (3) image classification (2) feature representation (2) fine-grained classification (2) pretrained model (2) knowledge graph (2) zero-shot classification (2) compositional learning (2) convolutional neural network (2) catastrophic forgetting (2) fine-grained recognition (2) compositional zero-shot learning (2) transfer learning (1) probabilistic modeling (1) concept-based explanation (1) iterative optimization (1) continual learning (1)

Papers

Safe Vision-Language Models via Unsafe Weights Manipulation WACV 2026 Benchmarking XAI Explanations with Human-Aligned Evaluations AAAI 2026 Compositional Caching for Training-free Open-vocabulary Attribute Detection CVPR 2025 Can Text-to-Video Generation help Video-Language Alignment? CVPR 2025 Not Only Text: Exploring Compositionality of Visual Representations in Vision-Language Models CVPR 2025 Classifier-to-Bias: Toward Unsupervised Automatic Bias Detection for Visual Classifiers CVPR 2025 Rethinking Few-Shot Adaptation of Vision-Language Models in Two Stages CVPR 2025 Training-Free Personalization via Retrieval and Reasoning on Fingerprints ICCV 2025 On Large Multimodal Models as Open-World Image Classifiers ICCV 2025 One VLM to Keep it Learning: Generation and Balancing for Data-Free Continual Visual Question Answering WACV 2025 3D Part Segmentation via Geometric Aggregation of 2D Visual Features WACV 2025 MULTIFLOW: Shifting Towards Task-Agnostic Vision-Language Pruning CVPR 2024 OpenBias: Open-set Bias Detection in Text-to-Image Generative Models CVPR 2024 Vision-by-Language for Training-Free Compositional Image Retrieval ICLR 2024 Frustratingly Easy Test-Time Adaptation of Vision-Language Models NIPS 2024 Harnessing Large Language Models for Training-free Video Anomaly Detection CVPR 2024 Image-Free Classifier Injection for Zero-Shot Classification ICCV 2023 PDiscoNet: Semantically consistent part discovery for fine-grained recognition ICCV 2023 Vocabulary-free Image Classification NIPS 2023 Iterative Superquadric Recomposition of 3D Objects from Multiple Views ICCV 2023 Transitivity Recovering Decompositions: Interpretable and Robust Fine-Grained Relationships NIPS 2023 ProbVLM: Probabilistic Adapter for Frozen Vison-Language Models ICCV 2023 KG-SP: Knowledge Guided Simple Primitives for Open World Compositional Zero-Shot Learning CVPR 2022 BayesCap: Bayesian Identity Cap for Calibrated Uncertainty in Frozen Neural Networks ECCV 2022 Abstracting Sketches through Simple Primitives ECCV 2022 Relational Proxies: Emergent Relationships as Fine-Grained Discriminators NIPS 2022 Open World Compositional Zero-Shot Learning CVPR 2021 Modeling the Background for Incremental Learning in Semantic Segmentation CVPR 2020 Towards Recognizing Unseen Categories in Unseen Domains ECCV 2020 AdaGraph: Unifying Predictive and Continuous Domain Adaptation Through Graphs CVPR 2019 Boosting Domain Adaptation by Discovering Latent Domains CVPR 2018 Embedding Words and Senses Together via Joint Knowledge-Enhanced Training CONLL 2017