Testoni, Alberto

Testoni, Alberto  

Mostra records
Risultati 1 - 18 di 18 (tempo di esecuzione: 0.03 secondi).
Titolo Anno di pubblicazione Autori Unitn File
A Small but Informed and Diverse Model: The Case of the Multimodal GuessWhat!? Guessing Game 1-gen-2022 Greco, ClaudioTestoni, AlbertoBernardi, RaffaellaFrank, Stella
ACT-Thor: A Controlled Benchmark for Embodied Action Understanding in Simulated Environments 1-gen-2022 Testoni, AlbertoBernardi, Raffaella +
Artificial Intelligence models do not ground negation, humans do. GuessWhat?! dialogues as a case study 1-gen-2022 Testoni, AlbertoGreco, ClaudioBernardi, Raffaella
Asking Strategic and Informative Questions in Visual Dialogue Games: Strengths and Weaknesses of Neural Generative Models 24-feb-2023 Testoni, Alberto
Garbage In, Flowers Out: Noisy Training Data Help Generative Models at Test Time 1-gen-2022 Testoni, AlbertoBernardi, Raffaella
Grounding Dialogue History: Strengths and Weaknesses of Pre-trained Transformers 1-gen-2021 Greco, ClaudioTestoni, AlbertoBernardi, Raffaella
Jointly learning to see, ask, decide when to stop, and then GuessWhat 1-gen-2019 Shekhar RaviTestoni AlbertoBernardi Raffaella +
Looking for Confirmations: An Effective and Human-Like Visual Dialogue Strategy 1-gen-2021 Testoni, AlbertoBernardi, Raffaella
Overprotective Training Environments Fall Short at Testing Time: Let Models Contribute to Their Own Training 1-gen-2020 Testoni, AlbertoBernardi, Raffaella
Probability Distributions as a Litmus Test to Inspect NNs Grounding Skills 1-gen-2022 Testoni, A.Bernardi, Raffaella +
Quantifiers in a MultimodalWorld: Hallucinating Vision with Language and Sound 1-gen-2019 Testoni AlbertoPezzelle SandroBernardi Raffaella
The Devil is in the Detail: A Magnifying Glass for the GuessWhich Visual Dialogue Game 1-gen-2019 Testoni, AlbertoShekhar RaviBernardi Raffaella +
The Efficiency of Question-Asking Strategies in a Real-World Visual Search Task 1-gen-2023 Testoni A.Bernardi R. +
The Interplay of Task Success and Dialogue Quality: An in-depth Evaluation in Task-Oriented Visual Dialogues 1-gen-2021 Testoni, AlbertoBernardi, Raffaella
They Are Not All Alike: Answering Different Spatial Questions Requires Different Grounding Strategies 1-gen-2020 Testoni, AlbertoGreco, ClaudioBenotti, LucianaBernardi, Raffaella +
Visually Grounded Follow-up Questions: a Dataset of Spatial Questions Which Require Dialogue History 1-gen-2021 Testoni, AlbertoBernardi, Raffaella +
Which Turn do Neural Models Exploit the Most to Solve GuessWhat? Diving into the Dialogue History Encoding in Transformers and LSTMs 1-gen-2020 Greco, ClaudioTestoni, AlbertoBernardi, Raffaella
“I’ve Seen Things You People Wouldn’t Believe”: Hallucinating Entities in GuessWhat?! 1-gen-2021 Testoni, AlbertoBernardi, Raffaella