8 papers
Zero-Shot Temporal Action Localization Through Textual Guidance
Benedetta Liberatori, Alessandro Conti, Lorenzo Vaquero +3
Zero-shot temporal action localization (ZS-TAL) consists of classifying and localizing actions in untrimmed videos, where action classes are unseen at training time. Existing work…
Training-Free Semantic Multi-Object Tracking with Vision-Language Models
Laurence Bonat, Francesco Tonini, Elisa Ricci +1
Semantic Multi-Object Tracking (SMOT) extends multi-object tracking with semantic outputs such as video summaries, instance-level captions, and interaction labels, aiming to move f…
Towards Unconstrained Human-Object Interaction
Francesco Tonini, Alessandro Conti, Lorenzo Vaquero +2
Human-Object Interaction (HOI) detection is a longstanding computer vision problem concerned with predicting the interaction between humans and objects. Current HOI models rely on…
From Weights to Concepts: Data-Free Interpretability of CLIP via Singular Vector Decomposition
Francesco Gentile, Nicola Dall'Asen, Francesco Tonini +3
As vision-language models are deployed at scale, understanding their internal mechanisms becomes increasingly critical. Existing interpretability methods predominantly rely on acti…
Superpowering Open-Vocabulary Object Detectors for X-ray Vision
Pablo Garcia-Fernandez, Lorenzo Vaquero, Mingxuan Liu +5
Open-vocabulary object detection (OvOD) is set to revolutionize security screening by enabling systems to recognize any item in X-ray scans. However, developing effective OvOD mode…
ConViS-Bench: Estimating Video Similarity Through Semantic Concepts
Benedetta Liberatori, Alessandro Conti, Lorenzo Vaquero +3
What does it mean for two videos to be similar? Videos may appear similar when judged by the actions they depict, yet entirely different if evaluated based on the locations where t…