Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Lou, Zhenyu"'
Predicting future human pose is a fundamental application for machine intelligence, which drives robots to plan their behavior and paths ahead of time to seamlessly accomplish human-robot collaboration in real-world 3D scenarios. Despite encouraging
Externí odkaz:
http://arxiv.org/abs/2405.02911
Model reparameterization is a widely accepted technique for improving inference speed without compromising performance. However, current Post-training Quantization (PTQ) methods often lead to significant accuracy degradation when applied to reparamet
Externí odkaz:
http://arxiv.org/abs/2402.16121
Publikováno v:
Pattern Recognition 2023/2024
Recently, video text detection, tracking, and recognition in natural scenes are becoming very popular in the computer vision community. However, most existing algorithms and benchmarks focus on common text cases (e.g., normal size, density) and singl
Externí odkaz:
http://arxiv.org/abs/2312.01938
Large Language Models (LLMs) pose significant hardware challenges related to memory requirements and computational ability. There are two mainstream quantization schemes for LLMs: coarse-grained ($\textit{e.g.,}$ channel-wise) quantization and fine-g
Externí odkaz:
http://arxiv.org/abs/2310.04836
Model binarization can significantly compress model size, reduce energy consumption, and accelerate inference through efficient bit-wise operations. Although binarizing convolutional neural networks have been extensively studied, there is little work
Externí odkaz:
http://arxiv.org/abs/2211.07091
Publikováno v:
In Pattern Recognition May 2024 149
Publikováno v:
Neural Processing Letters; Dec2023, Vol. 55 Issue 7, p9085-9100, 16p
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Publikováno v:
Applied Intelligence; Mar2023, Vol. 53 Issue 6, p6266-6275, 10p
Publikováno v:
Transportation Research Record; January 2000, Vol. 1699 Issue: 1 p95-100, 6p