Towards Real-Time Action Recognition on Mobile Devices Using Deep Models
원문 초록
Action recognition is a vital task in computer vision, and many methods are developed to push it to the limit. However, current action recognition models have huge computational costs, which cannot be deployed to real-world tasks on mobile devices. In this paper, we first illustrate the setting of real-time action recognition, which is different from current action recognition inference settings. Under the new inference setting, we investigate state-of-the-art action recognition models on the Kinetics dataset empirically. Our results show that designing efficient real-time action recognition models is different from designing efficient ImageNet models, especially in weight initialization. We show that pre-trained weights on ImageNet improve the accuracy under the real-time action recognition setting. Finally, we use the hand gesture recognition task as a case study to evaluate our compact real-time action recognition models in real-world applications on mobile phones. Results show that our action recognition models, being 6x faster and with similar accuracy as state-of-the-art, can roughly meet the real-time requirements on mobile devices. To our best knowledge, this is the first paper that deploys current deep learning action recognition models on mobile devices.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Online hand gesture recognition using Continual Graph Transformers
EgoHand: Ego-centric Hand Pose Estimation and Gesture Recognition with Head-mounted Millimeter-wave Radar and IMUs
DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling
HaGRIDv2: 1M Images for Static and Dynamic Hand Gesture Recognition
ConvMixFormer- A Resource-efficient Convolution Mixer for Transformer-based Dynamic Hand Gesture Recognition
MVTN: A Multiscale Video Transformer Network for Hand Gesture Recognition
토론
이 논문과 연결된 포럼 글이 아직 없습니다.