SOTAVerified

Action Parsing

Action parsing is the task of, given a video or still image, assigning each frame or image a label describing the action in that frame or image.

Papers

Showing 1115 of 15 papers

TitleStatusHype
Frontal Low-rank Random Tensors for Fine-grained Action SegmentationCode0
IncSQL: Training Incremental Text-to-SQL Parsers with Non-Deterministic Oracles0
DAP3D-Net: Where, What and How Actions Occur in Videos?0
Action Recognition by Hierarchical Mid-level Action Elements0
An Expressive Deep Model for Human Action Parsing from A Single Image0
Show:102550
← PrevPage 2 of 2Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Seq2SeqSet accuracy18.1Unverified
2CALMSet accuracy13.79Unverified