Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/Chained (RGB+Flow +Pose)

Chained (RGB+Flow +Pose)

Reported on 16 benchmarks across 8 tasks · 1 paper · 16 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision6 results

VideoonJ-HMDB
Accuracy (RGB+pose)· 2017-04-03
76.1
best: 90.4 (Potion)
SOTA
Chained Multi-stream Networks Exploiting Pose, Motion, and Appearance for Action Classification and Detection arXiv:1704.00616
VideoonJ-HMDB
Accuracy (pose)· 2017-04-03
56.8
best: 86.1 (HT-ConvNet)
SOTA
Chained Multi-stream Networks Exploiting Pose, Motion, and Appearance for Action Classification and Detection arXiv:1704.00616
Temporal Action LocalizationonJ-HMDB
Accuracy (RGB+pose)· 2017-04-03
76.1
best: 90.4 (Potion)
SOTA
Chained Multi-stream Networks Exploiting Pose, Motion, and Appearance for Action Classification and Detection arXiv:1704.00616
Temporal Action LocalizationonJ-HMDB
Accuracy (pose)· 2017-04-03
56.8
best: 86.1 (HT-ConvNet)
SOTA
Chained Multi-stream Networks Exploiting Pose, Motion, and Appearance for Action Classification and Detection arXiv:1704.00616
Action LocalizationonJ-HMDB
Accuracy (RGB+pose)· 2017-04-03
76.1
best: 90.4 (Potion)
SOTA
Chained Multi-stream Networks Exploiting Pose, Motion, and Appearance for Action Classification and Detection arXiv:1704.00616
Action LocalizationonJ-HMDB
Accuracy (pose)· 2017-04-03
56.8
best: 86.1 (HT-ConvNet)
SOTA
Chained Multi-stream Networks Exploiting Pose, Motion, and Appearance for Action Classification and Detection arXiv:1704.00616

Time Series4 results

Action DetectiononJ-HMDB
Accuracy (RGB+pose)· 2017-04-03
76.1
best: 90.4 (Potion)
SOTA
Chained Multi-stream Networks Exploiting Pose, Motion, and Appearance for Action Classification and Detection arXiv:1704.00616
Action DetectiononJ-HMDB
Accuracy (pose)· 2017-04-03
56.8
best: 86.1 (HT-ConvNet)
SOTA
Chained Multi-stream Networks Exploiting Pose, Motion, and Appearance for Action Classification and Detection arXiv:1704.00616
Action RecognitiononJ-HMDB
Accuracy (RGB+pose)· 2017-04-03
76.1
best: 90.4 (Potion)
SOTA
Chained Multi-stream Networks Exploiting Pose, Motion, and Appearance for Action Classification and Detection arXiv:1704.00616
Action RecognitiononJ-HMDB
Accuracy (pose)· 2017-04-03
56.8
best: 86.1 (HT-ConvNet)
SOTA
Chained Multi-stream Networks Exploiting Pose, Motion, and Appearance for Action Classification and Detection arXiv:1704.00616

Methodology2 results

Zero-Shot LearningonJ-HMDB
Accuracy (RGB+pose)· 2017-04-03
76.1
best: 90.4 (Potion)
SOTA
Chained Multi-stream Networks Exploiting Pose, Motion, and Appearance for Action Classification and Detection arXiv:1704.00616
Zero-Shot LearningonJ-HMDB
Accuracy (pose)· 2017-04-03
56.8
best: 86.1 (HT-ConvNet)
SOTA
Chained Multi-stream Networks Exploiting Pose, Motion, and Appearance for Action Classification and Detection arXiv:1704.00616

Robots2 results

Activity RecognitiononJ-HMDB
Accuracy (RGB+pose)· 2017-04-03
76.1
best: 90.4 (Potion)
SOTA
Chained Multi-stream Networks Exploiting Pose, Motion, and Appearance for Action Classification and Detection arXiv:1704.00616
Activity RecognitiononJ-HMDB
Accuracy (pose)· 2017-04-03
56.8
best: 86.1 (HT-ConvNet)
SOTA
Chained Multi-stream Networks Exploiting Pose, Motion, and Appearance for Action Classification and Detection arXiv:1704.00616

Natural Language Processing2 results

3D Action RecognitiononJ-HMDB
Accuracy (RGB+pose)· 2017-04-03
76.1
best: 90.4 (Potion)
SOTA
Chained Multi-stream Networks Exploiting Pose, Motion, and Appearance for Action Classification and Detection arXiv:1704.00616
3D Action RecognitiononJ-HMDB
Accuracy (pose)· 2017-04-03
56.8
best: 86.1 (HT-ConvNet)
SOTA
Chained Multi-stream Networks Exploiting Pose, Motion, and Appearance for Action Classification and Detection arXiv:1704.00616