natural-language-processing-9

Action Parsing

3260 papers • 126 benchmarks • 313 datasets

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.

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in action-parsing-9

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find action-parsing-9 models and implementations

Datasets

TAPOS

Home Action Genome

Subtasks

No subtasks available.

Most implemented papers

Local Temporal Bilinear Pooling for Fine-Grained Action Parsing

H. Neumann, Siyu Tang, Yan Zhang, Krikamol Muandet, Christian Jarvers•Tue Dec 04 2018

A novel bilinear pooling operation is proposed, which is used in intermediate layers of a temporal convolutional encoder-decoder net and is learnable and hence can capture more complex local statistics than the conventional counterpart.

23

Content

0

Paper Graph

Frontal Low-rank Random Tensors for Fine-grained Action Segmentation

Siyu Tang, Qianli Ma, Yan Zhang, Krikamol Muandet, Heiko Neumann•Sun Jun 02 2019

The proposed bilinear form outperforms the previous state-of-the-art methods on the challenging temporal action segmentation task, enabling to represent high-order information in complex deep models effectively and efficiently.

3 0

Paper Graph

Adding a benchmark result helps the community track progress.