Search Results for author:
Found 4 papers, 0 papers with code
Unified Keypoint-based Action Recognition Framework via Structured Keypoint Pooling
A point cloud deep-learning paradigm is introduced to the action recognition, and a unified framework along with a novel deep neural network architecture called Structured Keypoint Pooling is proposed.
Ranked #1 on
Skeleton Based Action Recognition
on HMDB51
Prompt-Guided Zero-Shot Anomaly Action Recognition using Pretrained Deep Skeleton Features
Particularly, during the training phase using normal samples, the method models the distribution of skeleton features of the normal actions while freezing the weights of the DNNs and estimates the anomaly score using this distribution in the inference phase.
Pose Proposal Networks
We propose a novel method to detect an unknown number of articulated 2D poses in real time.
Robust, Real-Time 3D Tracking of Multiple Objects With Similar Appearances
A major limitation of previous techniques is foreground confusion, in which the shapes of objects and/or ghosting artifacts are ignored and are hence not appropriately specified in foreground regions.
