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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–15 of 15 papers

TitleStatusHype
Local Temporal Bilinear Pooling for Fine-grained Action ParsingCode1
Modeling Worlds in TextCode1
Action Recognition by Hierarchical Mid-level Action Elements—0
An Expressive Deep Model for Human Action Parsing from A Single Image—0
DAP3D-Net: Where, What and How Actions Occur in Videos?—0
IncSQL: Training Incremental Text-to-SQL Parsers with Non-Deterministic Oracles—0
Intra- and Inter-Action Understanding via Temporal Action Parsing—0
Learning Knowledge Graph-based World Models of Textual Environments—0
SSCAP: Self-supervised Co-occurrence Action Parsing for Unsupervised Temporal Action Segmentation—0
Action parsing using context features—0
A Baseline Framework for Part-level Action Parsing and Action Recognition—0
Part-level Action Parsing via a Pose-guided Coarse-to-Fine Framework—0
PIVOT-R: Primitive-Driven Waypoint-Aware World Model for Robotic Manipulation—0
Technical Report: Disentangled Action Parsing Networks for Accurate Part-level Action Parsing—0
Frontal Low-rank Random Tensors for Fine-grained Action SegmentationCode0
Show:102550

Benchmark Results

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