Search Results for author: Xinyue Hao

Found 4 papers, 1 papers with code

Principles of Visual Tokens for Efficient Video Understanding

no code implementations20 Nov 2024 Xinyue Hao, Gen Li, Shreyank N Gowda, Robert B Fisher, Jonathan Huang, Anurag Arnab, Laura Sevilla-Lara

First, we develop an oracle for the value of tokens which exposes a clear Pareto distribution where most tokens have remarkably low value, and just a few carry most of the perceptual information.

Video Understanding

Watt For What: Rethinking Deep Learning's Energy-Performance Relationship

no code implementations10 Oct 2023 Shreyank N Gowda, Xinyue Hao, Gen Li, Shashank Narayana Gowda, Xiaobo Jin, Laura Sevilla-Lara

Deep learning models have revolutionized various fields, from image recognition to natural language processing, by achieving unprecedented levels of accuracy.

Deep Learning

OpenLORIS-Object: A Robotic Vision Dataset and Benchmark for Lifelong Deep Learning

2 code implementations15 Nov 2019 Qi She, Fan Feng, Xinyue Hao, Qihan Yang, Chuanlin Lan, Vincenzo Lomonaco, Xuesong Shi, Zhengwei Wang, Yao Guo, Yimin Zhang, Fei Qiao, Rosa H. M. Chan

Yet, robotic vision poses unique challenges for applying visual algorithms developed from these standard computer vision datasets due to their implicit assumption over non-varying distributions for a fixed set of tasks.

Lifelong learning Object +1

Cannot find the paper you are looking for? You can Submit a new open access paper.