REVIEW 2 cited by
Knowledge Prompting for Few-shot Action Recognition
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
Few-shot action recognition in videos is challenging for its lack of supervision and difficulty in generalizing to unseen actions. To address this task, we propose a simple yet effective method, called knowledge prompting, which leverages commonsense knowledge of actions from external resources to prompt a powerful pre-trained vision-language model for few-shot classification. We first collect large-scale language descriptions of actions, defined as text proposals, to build an action knowledge base. The collection of text proposals is done by filling in handcraft sentence templates with external action-related corpus or by extracting action-related phrases from captions of Web instruction videos.Then we feed these text proposals into the pre-trained vision-language model along with video frames to generate matching scores of the proposals to each frame, and the scores can be treated as action semantics with strong generalization. Finally, we design a lightweight temporal modeling network to capture the temporal evolution of action semantics for classification.Extensive experiments on six benchmark datasets demonstrate that our method generally achieves the state-of-the-art performance while reducing the training overhead to 0.001 of existing methods.
Forward citations
Cited by 2 Pith papers
-
A Baseline Study and Benchmark for Few-Shot Open-Set Action Recognition with Feature Residual Discrimination
A feature-residual discriminator adapted from skeleton-based recognition improves unknown-action rejection over standard baselines on a new five-dataset benchmark for few-shot open-set action recognition.
-
Few-Shot Optimization for Sensor Data Using Large Language Models: A Case Study on Fatigue Detection
A hybrid Euclidean-distance and LLM-relevance example selector for few-shot sensor classification reports a small, statistically fragile gain over distance-only selection on a fatigue detection dataset.
Discussion (0). Sign in to comment.