New RGB-only action recognition model for edge devices unveiled

Researchers have developed a new, resource-efficient RGB-only action recognition network designed for deployment on edge devices. This model, which incorporates several architectural innovations like temporal shift and Ghost pointwise convolutions, achieves high accuracy on benchmark datasets such as NTU RGB+D 60 and 120. The research also investigates the model's performance under various visual degradations, finding that occlusion significantly impacts recall. When deployed on an NVIDIA Jetson Orin Nano, the model demonstrates strong static compactness. AI

IMPACT Enables more efficient and capable AI-powered monitoring systems on resource-constrained edge devices.

RANK_REASON The cluster describes a new academic paper detailing a novel model architecture and its performance evaluation. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

• Dongsik Yoon
• Hugging Face
• NTU RGB+D 60
• NVIDIA Jetson Orin Nano
• TensorRT FP16
• X3D

• paper
• model release
• infra

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →