← Search

Data · dataset · 2026

SPOT-Bench

Listed in Hugging Face Datasets

SPOT-Bench (NeurIPS 2026 E&D Track) A fully proactive benchmark for streaming video models and interaction models. ⚡ TL;DR: SPOT-Bench requires a streaming model to monitor a live video stream and proactively decide when to respond.

Description

Every prediction across the full video is evaluated using the Timeliness-F1 metric. [!IMPORTANT] Detection tasks (ABD, PNR) are released in full.

For Interaction (SQA, SPG) and Intervention (SI, UI) we release a representative validation set while… See the full description on the dataset page: huggingface.co/datasets/cvml-nus/spot-bench.

Links

Get the data

Documentation and papers

Catalogue records · 1

Topics

Inferred from text
Video 75%
Provenance · 1 source records, 9 field assertions
SourceKeyLast seenRaw
Hugging Face Datasetscvml-nus/spot-bench15 d agoJSON v1
FieldAssertionExtractorEvidence
access_levelsource · Hugging Faceconnector:huggingface@1.0.0/gated
concepts[field].local:field:computer-science-aimapping · Hugging Faceconnector:huggingface@1.0.0
concepts[modality].local:modality:videoenrichment · Hugging Facekeyword-concept-rules@1.0.0title+description (75%)
created_datesource · Hugging Faceconnector:huggingface@1.0.0
descriptionsource · Hugging Faceconnector:huggingface@1.0.0/description
licensesource · Hugging Faceconnector:huggingface@1.0.0/tags[license:*]
publication_datesource · Hugging Faceconnector:huggingface@1.0.0
titlesource · Hugging Faceconnector:huggingface@1.0.0/id
updated_datesource · Hugging Faceconnector:huggingface@1.0.0