Accuracy and Performance Comparison of Video Action Recognition Approaches
Over the past few years, there has been significant interest in video action recognition systems and models. However, direct comparison of accuracy and computational performance results remain clouded by differing training environments, hardware specifications, hyperparameters, pipelines, and inference methods. This article provides a direct comparison between fourteen off-the-shelf and state-of-the-art models by ensuring consistency in these training characteristics in order to provide readers with a meaningful comparison across different types of video action recognition algorithms. Accuracy of the models is evaluated using standard Top-1 and Top-5 accuracy metrics in addition to a proposed new accuracy metric. Additionally, we compare computational performance of distributed training from two to sixty-four GPUs on a state-of-the-art HPC system.
Code (0)
등록된 구현이 없습니다.
Tasks
Action RecognitionTemporal Action LocalizationSimilar Papers 제목 키워드 기반
IndGIC: Supervised Action Recognition under Low Illumination
Technologies of human action recognition in the dark are gaining more and more attention as huge demand in surveillance, motion control and human-computer interaction. However, because of limitation in image enhancement …
Action RecognitionImage EnhancementTemporal Action LocalizationLightweight Network Architecture for Real-Time Action Recognition
In this work we present a new efficient approach to Human Action Recognition called Video Transformer Network (VTN). It leverages the latest advances in Computer Vision and Natural Language Processing and applies them to…
Action RecognitionCPUTemporal Action LocalizationVideo UnderstandingSemi-Supervised Few-Shot Atomic Action Recognition
Despite excellent progress has been made, the performance on action recognition still heavily relies on specific datasets, which are difficult to extend new action classes due to labor-intensive labeling. Moreover, the h…
Action RecognitionAtomic action recognitionDiversityDetection of Fights in Videos: A Comparison Study of Anomaly Detection and Action Recognition
Detection of fights is an important surveillance application in videos. Most existing methods use supervised binary action recognition. Since frame-level annotations are very hard to get for anomaly detection, weakly sup…
Action RecognitionAnomaly DetectionMultiple Instance LearningWeakly-supervised LearningVideo Action Recognition Collaborative Learning with Dynamics via PSO-ConvNet Transformer
Recognizing human actions in video sequences, known as Human Action Recognition (HAR), is a challenging task in pattern recognition. While Convolutional Neural Networks (ConvNets) have shown remarkable success in image r…
Action RecognitionAction Recognition In VideosTemporal Action Localization