148 citations · 151 across the 12 of their papers we have counts for
21 papers
Query-Conditioned Spherical Centroid Aggregation for Multimodal Retrieval
Ambuj Mehrish, Anindya Nag, Sebastiano Vascon
Multimodal retrieval integrates video, audio, subtitles, and text; however, recent geometric aggregators, such as Gramian volumes, hyperbolic volumes, and spectral objectives, trea…
Hypergraph-Regularized Gramian Volumes for Multimodal Retrieval
Anindya Nag, Ambuj Mehrish, Sebastiano Vascon
Volume-based multimodal retrieval jointly scores a text query with a candidate's video, audio, and subtitle embeddings. While this approach captures higher-order within-candidate a…
RAG-Audio: Retrieval-Augmented Generation for Faithful Brain-to-Audio Reconstruction
Ambuj Mehrish, Sebastiano Vascon
Brain-to-audio reconstruction is limited by \emph{prior domination}: when a pretrained generator is conditioned on a weak neural signal, it produces realistic but stimulus-inaccura…
CoRE: Consensus Rewards via Equilibrium for Test-Time Reinforcement Learning
Ambuj Mehrish, Sebastiano Vascon
On unlabeled test data, reinforcement learning lacks a ground-truth reward; test-time RL methods derive one from the model's own roll-outs, rewarding those that match the majority…
Constrained Dominant Sets for Multimodal Document Question Answering
Ambuj Mehrish, Sebastiano Vascon
Long multimodal document question answering is limited by which evidence reaches the reader, rather than by the quantity retrieved. In lengthy documents, findings often recur acros…
Min-Cost Flow Routing for Evidence Assembly in Long Multimodal Documents
Ambuj Mehrish, Sebastiano Vascon
Answering questions about long multimodal documents requires distributing a fixed evidence budget across relevant facets in text, tables, figures, and slides while avoiding near-du…
Reassembling Broken Objects using Breaking Curves
Ali Alagrami, Luca Palmieri, Sinem Aslan +2
Reassembling 3D broken objects is a challenging task. A robust solution that generalizes well must deal with diverse patterns associated with different types of broken objects. We…
Geolocation of Cultural Heritage using Multi-View Knowledge Graph Embedding
Hebatallah A. Mohamed, Sebastiano Vascon, Feliks Hibraj +4
Knowledge Graphs (KGs) have proven to be a reliable way of structuring data. They can provide a rich source of contextual information about cultural heritage collections. However,…
Wild Patterns Reloaded: A Survey of Machine Learning Security against Training Data Poisoning
Antonio Emanuele Cinà, Kathrin Grosse, Ambra Demontis +7
The success of machine learning is fueled by the increasing availability of computing power and large training datasets. The training data is used to learn new models or update exi…
The Group Loss++: A deeper look into group loss for deep metric learning
Ismail Elezi, Jenny Seidenschwarz, Laurin Wagner +4
Deep metric learning has yielded impressive results in tasks such as clustering and image retrieval by leveraging neural networks to obtain highly discriminative feature embeddings…
Relaxation Labeling Meets GANs: Solving Jigsaw Puzzles with Missing Borders
Marina Khoroshiltseva, Arianna Traviglia, Marcello Pelillo +1
This paper proposes JiGAN, a GAN-based method for solving Jigsaw puzzles with eroded or missing borders. Missing borders is a common real-world situation, for example, when dealing…
The Hammer and the Nut: Is Bilevel Optimization Really Needed to Poison Linear Classifiers?
Antonio Emanuele Cinà, Sebastiano Vascon, Ambra Demontis +3
One of the most concerning threats for modern AI systems is data poisoning, where the attacker injects maliciously crafted training data to corrupt the system's behavior at test ti…
Transductive Visual Verb Sense Disambiguation
Sebastiano Vascon, Sinem Aslan, Gianluca Bigaglia +2
Verb Sense Disambiguation is a well-known task in NLP, the aim is to find the correct sense of a verb in a sentence. Recently, this problem has been extended in a multimodal scenar…
DSLib: An open source library for the dominant set clustering method
Sebastiano Vascon, Samuel Rota Bulò, Vittorio Murino +1
DSLib is an open-source implementation of the Dominant Set (DS) clustering algorithm written entirely in Matlab. The DS method is a graph-based clustering technique rooted in the e…
The Group Loss for Deep Metric Learning
Ismail Elezi, Sebastiano Vascon, Alessandro Torcinovich +2
Deep metric learning has yielded impressive results in tasks such as clustering and image retrieval by leveraging neural networks to obtain highly discriminative feature embeddings…
Unsupervised Domain Adaptation using Graph Transduction Games
Sebastiano Vascon, Sinem Aslan, Alessandro Torcinovich +3
Unsupervised domain adaptation (UDA) amounts to assigning class labels to the unlabeled instances of a dataset from a target domain, using labeled instances of a dataset from a rel…
Characterization of Visual Object Representations in Rat Primary Visual Cortex
Sebastiano Vascon, Ylenia Parin, Eis Annavini +3
For most animal species, quick and reliable identification of visual objects is critical for survival. This applies also to rodents, which, in recent years, have become increasingl…
Ancient Coin Classification Using Graph Transduction Games
Sinem Aslan, Sebastiano Vascon, Marcello Pelillo
Recognizing the type of an ancient coin requires theoretical expertise and years of experience in the field of numismatics. Our goal in this work is automatizing this time consumin…
Transductive Label Augmentation for Improved Deep Network Learning
Ismail Elezi, Alessandro Torcinovich, Sebastiano Vascon +1
A major impediment to the application of deep learning to real-world problems is the scarcity of labeled data. Small training sets are in fact of no use to deep networks as, due to…
Speaker Clustering Using Dominant Sets
Feliks Hibraj, Sebastiano Vascon, Thilo Stadelmann +1
Speaker clustering is the task of forming speaker-specific groups based on a set of utterances. In this paper, we address this task by using Dominant Sets (DS). DS is a graph-based…
Context Aware Nonnegative Matrix Factorization Clustering
Rocco Tripodi, Sebastiano Vascon, Marcello Pelillo
In this article we propose a method to refine the clustering results obtained with the nonnegative matrix factorization (NMF) technique, imposing consistency constraints on the fin…