REVIEW 2 cited by
RareAct: A video dataset of unusual interactions
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
This paper introduces a manually annotated video dataset of unusual actions, namely RareAct, including actions such as "blend phone", "cut keyboard" and "microwave shoes". RareAct aims at evaluating the zero-shot and few-shot compositionality of action recognition models for unlikely compositions of common action verbs and object nouns. It contains 122 different actions which were obtained by combining verbs and nouns rarely co-occurring together in the large-scale textual corpus from HowTo100M, but that frequently appear separately. We provide benchmarks using a state-of-the-art HowTo100M pretrained video and text model and show that zero-shot and few-shot compositionality of actions remains a challenging and unsolved task.
Forward citations
Cited by 2 Pith papers
-
Can Vision Language Models Understand Mimed Actions?
Vision-language models identify real actions with context far better than they identify mimed actions performed by 3D avatars, while humans are equally accurate on both.
-
LEGO Co-builder: Exploring Fine-Grained Vision-Language Modeling for Multimodal LEGO Assembly Assistants
LEGO-VLM benchmark shows VLMs fail at fine-grained LEGO assembly state detection, but model-generated ground truth and a missing trivial baseline weaken the claim.
Discussion (0). Continue with ORCID to comment.