Improved soccer action spotting using both audio and video streams

B Vanderplaetse, S Dupont - Proceedings of the IEEE/CVF …, 2020 - openaccess.thecvf.com
In this paper, we propose a study on multi-modal (audio and video) action spotting and
classification in soccer videos. Action spotting and classification are the tasks that consist in …

A neuro-symbolic approach to structured event recognition

G Apriceno, A Passerini, L Serafini - … PROCEEDINGS IN INFORMATICS, 2021 - iris.unitn.it
Events are structured entities with multiple components: the event type, the participants with
their roles, the outcome, the sub-events etc. A fully end-to-end approach for event …

Think before You Simulate: Symbolic Reasoning to Orchestrate Neural Computation for Counterfactual Question Answering

A Ishay, Z Yang, J Lee, I Kang… - Proceedings of the IEEE …, 2024 - openaccess.thecvf.com
Causal and temporal reasoning about video dynamics is a challenging problem. While
neuro-symbolic models that combine symbolic reasoning with neural-based perception and …

A neuro-symbolic approach for real-world event recognition from weak supervision

G Apriceno, A Passerini, L Serafini - … International Symposium on …, 2022 - drops.dagstuhl.de
Events are structured entities involving different components (eg, the participants, their roles
etc.) and their relations. Structured events are typically defined in terms of (a subset of) …

Untangling braids with multi-agent q-learning

A Khan, A Vernitski, A Lisitsa - 2021 23rd International …, 2021 - ieeexplore.ieee.org
We use reinforcement learning to tackle the problem of untangling braids. We experiment
with braids with 2 and 3 strands. Two competing players learn to tangle and untangle a …

[PDF][PDF] Reinforcement learning algorithms for the untangling of braids

A Vernitski, A Lisitsa - The International FLAIRS Conference …, 2022 - journals.flvc.org
Insert Your Title Here Page 1 Reinforcement learning algorithms for the Untangling of Braids
Abdullah Khan ∗ , Alexei Lisitsa † , Alexei Vernitski ∗ ∗ University of Essex, Colchester CO4 …

Hyster: A hybrid spatio-temporal event reasoner

T Sautory, N Cingillioglu, A Russo - arXiv preprint arXiv:2101.06644, 2021 - arxiv.org
The task of Video Question Answering (VideoQA) consists in answering natural language
questions about a video and serves as a proxy to evaluate the performance of a model in …

Representation and processing of instantaneous and durative temporal phenomena

M Pitsikalis, A Lisitsa, S Luo - … on Logic-Based Program Synthesis and …, 2021 - Springer
Abstract Event definitions in Complex Event Processing systems are constrained by the
expressiveness of each system's language. Some systems allow the definition of …

Interval Logic Tensor Networks

S Badreddine, G Apriceno, A Passerini… - arXiv preprint arXiv …, 2023 - arxiv.org
In this paper, we introduce Interval Real Logic (IRL), a two-sorted logic that interprets
knowledge such as sequential properties (traces) and event properties using sequences of …

End-to-End Neuro-Symbolic Approaches for Event Recognition

G Apriceno - 2023 - iris.unitn.it
Event detection is a critical challenge in many fields like video surveillance, social graph
analysis, and multimedia processing. Furthermore, events are “structured” objects involv ing …