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
Most implemented papers
Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition
yysijie/st-gcn
•
•
Dynamics of human body skeletons convey significant information for human action recognition.
Temporal Segment Networks: Towards Good Practices for Deep Action Recognition
yjxiong/temporal-segment-networks
•
•
The other contribution is our study on a series of good practices in learning ConvNets on video data with the help of temporal segment network.
Moments in Time Dataset: one million videos for event understanding
We present the Moments in Time Dataset, a large-scale human-annotated collection of one million short videos corresponding to dynamic events unfolding within three seconds.
AssembleNet: Searching for Multi-Stream Neural Connectivity in Video Architectures
tensorflow/models
•
•
ICLR 2020
Learning to represent videos is a very challenging task both algorithmically and computationally.
Gimme Signals: Discriminative signal encoding for multimodal activity recognition
airglow/gimme_signals_action_recognition
•
•
We present a simple, yet effective and flexible method for action recognition supporting multiple sensor modalities.
Interpretable 3D Human Action Analysis with Temporal Convolutional Networks
In this work, we propose to use a new class of models known as Temporal Convolutional Neural Networks (TCN) for 3D human action recognition.
Cross-modal Learning by Hallucinating Missing Modalities in RGB-D Vision
ncgarcia/modality-distillation
•
•
Multimodal Scene Understanding Algorithms, Applications and Deep Learning 2019
We report state-of-the-art or comparable results on video action recognition on the largest multimodal dataset available for this task, the NTU RGB+D, as well as on the UWA3DII and Northwestern-UCLA.
EV-Action: Electromyography-Vision Multi-Modal Action Dataset
To make up this, we introduce a new, large-scale EV-Action dataset in this work, which consists of RGB, depth, electromyography (EMG), and two skeleton modalities.
Bayesian Hierarchical Dynamic Model for Human Action Recognition
Human action recognition remains as a challenging task partially due to the presence of large variations in the execution of action.
Distilling Audio-Visual Knowledge by Compositional Contrastive Learning
yanbeic/CCL
•
•
CVPR 2021
Having access to multi-modal cues (e. g. vision and audio) empowers some cognitive tasks to be done faster compared to learning from a single modality.
