This leads to a viewpoint that provides a more accurate prediction to distinguish such an object from other objects better.
In this paper, we present Fusion-GCN, an approach for multimodal action recognition using Graph Convolutional Networks (GCNs).
One-shot action recognition allows the recognition of human-performed actions with only a single training example.
Ranked #1 on One-Shot 3D Action Recognition on NTU RGB+D 120
Further, we show that our approach generalizes well in experiments on the UTD-MHAD dataset for inertial, skeleton and fused data and the Simitate dataset for motion capturing data.
Ranked #2 on One-Shot 3D Action Recognition on NTU RGB+D 120
We present a simple, yet effective and flexible method for action recognition supporting multiple sensor modalities.
Ranked #5 on Multimodal Activity Recognition on UTD-MHAD
This paper presents a method for gesture recognition in RGB videos using OpenPose to extract the pose of a person and Dynamic Time Warping (DTW) in conjunction with One-Nearest-Neighbor (1NN) for time-series classification.
We present Simitate --- a hybrid benchmarking suite targeting the evaluation of approaches for imitation learning.
We present Scratchy---a modular, lightweight robot built for low budget competition attendances.
We analyze a set of spatial constraints on human pose data extracted using convolutional pose machines and object informations extracted from 2D image sequences.
Simple Online and Realtime Tracking (SORT) is a pragmatic approach to multiple object tracking with a focus on simple, effective algorithms.
Ranked #33 on Video Instance Segmentation on YouTube-VIS validation