Advances in Human Action Recognition: A Survey

Abstract

Human action recognition has been an important topic in computer vision due to its many applications such as video surveillance, human machine interaction and video retrieval. One core problem behind these applications is automatically recognizing low-level actions and high-level activities of interest. The former is usually the basis for the latter. This survey gives an overview of the most recent advances in human action recognition during the past several years, following a well-formed taxonomy proposed by a previous survey. From this state-of-the-art survey, researchers can view a panorama of progress in this area for future research.

References in corpus (1)

• Grounding the Lexical Semantics of Verbs in Visual Perception using Force Dynamics and Event Logic

Cited by in corpus (14)

• Levels of explainable artificial intelligence for human-aligned conversational explanations
• Analyzing Human-Human Interactions: A Survey
• Video Action Understanding
• STAIR Actions: A Video Dataset of Everyday Home Actions
• Video-based Human Action Recognition using Deep Learning: A Review
• Towards Understanding the Adversarial Vulnerability of Skeleton-based Action Recognition
• Towards Train-Test Consistency for Semi-supervised Temporal Action Localization
• Attention Transfer from Web Images for Video Recognition
• Direct Network Transfer: Transfer Learning of Sentence Embeddings for Semantic Similarity
• AutoLoc: Weakly-supervised Temporal Action Localization
• Online Detection of Action Start in Untrimmed, Streaming Videos
• Predicting Human Activities from User-Generated Content
• Convolutional Architecture Exploration for Action Recognition and Image Classification
• Multi-Level Network for High-Speed Multi-Person Pose Estimation