SMART-Vision: Survey of Modern Action Recognition Techniques in Vision
arXiv:2501.13066 · doi:10.1007/s11042-024-20484-5
Abstract
Human Action Recognition (HAR) is a challenging domain in computer vision, involving recognizing complex patterns by analyzing the spatiotemporal dynamics of individuals' movements in videos. These patterns arise in sequential data, such as video frames, which are often essential to accurately distinguish actions that would be ambiguous in a single image. HAR has garnered considerable interest due to its broad applicability, ranging from robotics and surveillance systems to sports motion analysis, healthcare, and the burgeoning field of autonomous vehicles. While several taxonomies have been proposed to categorize HAR approaches in surveys, they often overlook hybrid methodologies and fail to demonstrate how different models incorporate various architectures and modalities. In this comprehensive survey, we present the novel SMART-Vision taxonomy, which illustrates how innovations in deep learning for HAR complement one another, leading to hybrid approaches beyond traditional categories. Our survey provides a clear roadmap from foundational HAR works to current state-of-the-art systems, highlighting emerging research directions and addressing unresolved challenges in discussion sections for architectures within the HAR domain. We provide details of the research datasets that various approaches used to measure and compare goodness HAR approaches. We also explore the rapidly emerging field of Open-HAR systems, which challenges HAR systems by presenting samples from unknown, novel classes during test time.
References in corpus (14)
- NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding
- Action Recognition with Trajectory-Pooled Deep-Convolutional Descriptors
- Towards Open World Recognition
- Skeleton-based Action Recognition via Spatial and Temporal Transformer Networks
- Stronger, Faster and More Explainable: A Graph Convolutional Baseline for Skeleton-based Action Recognition
- The Extreme Value Machine
- Rank Pooling for Action Recognition
- Action Transformer: A Self-Attention Model for Short-Time Pose-Based Human Action Recognition
- Spatial Temporal Transformer Network for Skeleton-based Action Recognition
- Audio-Based Activities of Daily Living (ADL) Recognition with Large-Scale Acoustic Embeddings from Online Videos
- Human in Events: A Large-Scale Benchmark for Human-centric Video Analysis in Complex Events
- 3D VSG: Long-term Semantic Scene Change Prediction through 3D Variable Scene Graphs
- Pose2Trajectory: Using Transformers on Body Pose to Predict Tennis Player's Trajectory
- Towards Accurate Human Pose Estimation in Videos of Crowded Scenes