MétaCan
Menu
Back to cohort
Record W4323527314 · doi:10.23977/jaip.2023.060105

A survey of Few-Shot Action Recognition

2023· article· en· W4323527314 on OpenAlexvenueno aff
Congmin Wang, Yancong Zhou

Bibliographic record

VenueJournal of Artificial Intelligence Practice · 2023
Typearticle
Languageen
FieldComputer Science
TopicHuman Pose and Action Recognition
Canadian institutionsnot available
Fundersnot available
KeywordsFeature (linguistics)Computer scienceShot (pellet)Action (physics)Field (mathematics)Artificial intelligenceMetric (unit)Process (computing)EmbeddingMachine learningOne shotPattern recognition (psychology)EngineeringMathematics

Abstract

fetched live from OpenAlex

In recent years, with the development of network technology, countless videos are produced every day. Many achievements have also been made in the field of action recognition in computer vision. Training action recognition models requires a large number of labeled samples, but in reality, the amount of data is scarce, and it is extremely difficult to obtain a large amount of data due to costs and other reasons. The few-shot learning aims to solve the problem of using several samples to learn new categories. This paper combs the relevant research in recent years of few-shot action recognition technology. According to the classification of training process, this paper summarizes the research progress and typical models of few-shot action recognition from the perspectives of data processing, feature embedding, feature augmentation, and metric learning; finally points out the challenges faced by current research and the future development directions.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.003
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Not applicable · Consensus signal: none
GenreCandidate signal: Review · Consensus signal: none
Teacher disagreement score0.006
Threshold uncertainty score0.014

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0010.003
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0020.001
Bibliometrics0.0030.004
Science and technology studies0.0000.001
Scholarly communication0.0020.003
Open science0.0020.001
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0040.003

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.342
GPT teacher head0.420
Teacher spread0.078 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designNot applicable
Domainnot available
GenreReview

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations1
Published2023
Admission routes1
Has abstractyes

Explore more

Same venueJournal of Artificial Intelligence PracticeSame topicHuman Pose and Action RecognitionFrench-language works237,207