Saved in:
Bibliographic Details
Main Authors: Knab, Patrick, Xhelili, Orgest, Buzi, Inis, Nilo, Drago Andres Guggiana, Khan, Mohd Saquib, Kolb, Lorenz, Scherzer, Manuel, Yildirir, Kerem, Bartelt, Christian, Schubert, Philipp Johannes
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.12074
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913117096640512
author Knab, Patrick
Xhelili, Orgest
Buzi, Inis
Nilo, Drago Andres Guggiana
Khan, Mohd Saquib
Kolb, Lorenz
Scherzer, Manuel
Yildirir, Kerem
Bartelt, Christian
Schubert, Philipp Johannes
author_facet Knab, Patrick
Xhelili, Orgest
Buzi, Inis
Nilo, Drago Andres Guggiana
Khan, Mohd Saquib
Kolb, Lorenz
Scherzer, Manuel
Yildirir, Kerem
Bartelt, Christian
Schubert, Philipp Johannes
contents Scene understanding is central to general physical intelligence, and video is a primary modality for capturing both state and temporal dynamics of a scene. Yet understanding physical processes remains difficult, as models must combine object localization, hand-object interactions, relational parsing, temporal reasoning, and step-level procedural inference. Existing benchmarks usually evaluate these capabilities separately, limiting diagnosis of why models fail on procedural tasks. We introduce BARISTA, a densely annotated egocentric dataset and benchmark of 185 real-world coffee-preparation videos covering fully automatic, portafilter-based, and capsule-based workflows. BARISTA provides verified per-frame scene graphs linking persistent object identities to masks, tracks, boxes, attributes, typed relations, hand-object interactions, activities, and process steps. From these graphs, we derive zero-shot language-based tasks spanning phrase grounding, hand-object interaction recognition, referring, activity recognition, relation extraction, and temporal visual question answering. Experiments reveal strong variation across task families and no consistently dominant model family, positioning BARISTA as a challenging diagnostic benchmark for procedural video understanding. Code and dataset available at https://huggingface.co/datasets/ramblr/BARISTA.
format Preprint
id arxiv_https___arxiv_org_abs_2605_12074
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle BARISTA: A Multi-Task Egocentric Benchmark for Compositional Visual Understanding
Knab, Patrick
Xhelili, Orgest
Buzi, Inis
Nilo, Drago Andres Guggiana
Khan, Mohd Saquib
Kolb, Lorenz
Scherzer, Manuel
Yildirir, Kerem
Bartelt, Christian
Schubert, Philipp Johannes
Computer Vision and Pattern Recognition
Scene understanding is central to general physical intelligence, and video is a primary modality for capturing both state and temporal dynamics of a scene. Yet understanding physical processes remains difficult, as models must combine object localization, hand-object interactions, relational parsing, temporal reasoning, and step-level procedural inference. Existing benchmarks usually evaluate these capabilities separately, limiting diagnosis of why models fail on procedural tasks. We introduce BARISTA, a densely annotated egocentric dataset and benchmark of 185 real-world coffee-preparation videos covering fully automatic, portafilter-based, and capsule-based workflows. BARISTA provides verified per-frame scene graphs linking persistent object identities to masks, tracks, boxes, attributes, typed relations, hand-object interactions, activities, and process steps. From these graphs, we derive zero-shot language-based tasks spanning phrase grounding, hand-object interaction recognition, referring, activity recognition, relation extraction, and temporal visual question answering. Experiments reveal strong variation across task families and no consistently dominant model family, positioning BARISTA as a challenging diagnostic benchmark for procedural video understanding. Code and dataset available at https://huggingface.co/datasets/ramblr/BARISTA.
title BARISTA: A Multi-Task Egocentric Benchmark for Compositional Visual Understanding
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.12074