Multimodal Activity Recognition
12 papers with code • 10 benchmarks • 7 datasets
Benchmarks
These leaderboards are used to track progress in Multimodal Activity Recognition
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
MiT
UCSD Ped2
UT-Kinect
UTD-MHAD
MSRDailyActivity3D
MMAct
Home Action Genome
Latest papers with no code
Uncertainty aware audiovisual activity recognition using deep Bayesian variational inference
In the multimodal setting, the proposed framework improved precision-recall AUC by 10. 2% on the subset of MiT dataset as compared to non-Bayesian baseline.
Recognizing Human Actions as the Evolution of Pose Estimation Maps
Specifically, the evolution of pose estimation maps can be decomposed as an evolution of heatmaps, e. g., probabilistic maps, and an evolution of estimated 2D human poses, which denote the changes of body shape and body pose, respectively.
Deep Multimodal Feature Analysis for Action Recognition in RGB+D Videos
Single modality action recognition on RGB or depth sequences has been extensively explored recently.
Moving poselets: A discriminative and interpretable skeletal motion representation for action recognition
While automatic feature learning methods such as supervised sparse dictionary learning or neural networks can be applied to learn feature representation and action classifiers jointly, the resulting features are usually uninterpretable.
Action recognition from depth maps using deep convolutional neural networks
In addition, the method was evaluated on the large dataset constructed from the above datasets.
Multimodal Multipart Learning for Action Recognition in Depth Videos
We propose a joint sparse regression based learning method which utilizes the structured sparsity to model each action as a combination of multimodal features from a sparse set of body parts.
Fusing multiple features for depth-based action recognition
The experiments are conducted on four challenging depth action databases, in order to evaluate and find the best fusion methods generally.
Group sparsity and geometry constrained dictionary learning for action recognition from depth maps.
Human action recognition based on the depth information provided by commodity depth sensors is an important yet challenging task.
