Results 91 to 100 of about 739,829 (293)

Imitation from Observation: Learning to Imitate Behaviors from Raw Video via Context Translation

, 2018
Imitation learning is an effective approach for autonomous systems to acquire control policies when an explicit reward function is unavailable, using supervision provided as demonstrations from an expert, typically a human operator.
Abbeel, Pieter, Gupta, Abhishek, Levine, Sergey, Liu, YuXuan   +3 more
core   +1 more source

Transistor‐Level Activation Functions via Two‐Gate Designs: From Analog Sigmoid and Gaussian Control to Real‐Time Hardware Demonstrations

Advanced Materials, EarlyView.
Screen gate‐based transistors are presented, enabling tunable analog sigmoid and Gaussian activations. The SA‐transistor improves MRI classification accuracy, while the GA‐transistor supports precise Gaussian kernel tuning for forecasting. Both functions are implemented in a single device, offering compact, energy‐efficient analog AI processing ...
Junhyung Cho, Youngmin Han, Won Woo Lee, Youngwoo Yoo, Kannan Udaya Mohanan, Chang‐Hyun Kim, Junhwan Choi, Young‐Joon Kim, Wonjun Shin, Hocheon Yoo   +9 more
wiley   +1 more source

Intelligent Acousto‐Electrical Metamaterials (IAM) for Sound Source Detection

Advanced Materials, EarlyView.
Our proposed metamaterial concept enables sound source detection using a single material, in contrast to conventional arrays that require dozens or even hundreds of transducers. We show that the coupled acoustic–vibrational–electrical responses in piezoelectric metamaterials give rise to topology‐governed charge transport, producing distinct voltage ...
Victor Couëdel, Haotian Lu, Jiayan Zhang, Desheng Yao, Ananya Bhardwaj, Ramiro Contreras, Karim Sabra, Xiaoyu (Rayne) Zheng   +7 more
wiley   +1 more source

Unsupervised Learning of Visual Representations using Videos

, 2015
Is strong supervision necessary for learning a good visual representation? Do we really need millions of semantically-labeled images to train a Convolutional Neural Network (CNN)?
Gupta, Abhinav, Wang, Xiaolong
core   +1 more source

Label‐Free SERS Fingerprinting of Neuroprotein Conformational Dynamics in Human Saliva

Advanced Materials, EarlyView.
Galvanic molecular entrapment (GME) is a label‐free method for detecting and quantifying neuroprotein conformational states. This technique enables direct surface binding and in situ hotspot generation around molecules, effectively overcoming challenges related to target localization and mismatched hotspot geometries.
Muhammad Shalahuddin Al Ja'farawy, Jun‐Yeong Yang, Chaewon Mun, Seunghun Lee, Chul Bum Cho, Yoo Hyun Um, Min‐Young Lee, Sung‐Gyu Park, Dong‐Ho Kim, Seung Ho Yang, Ho Sang Jung   +10 more
wiley   +1 more source

Learning Single-Image Depth from Videos using Quality Assessment Networks

, 2019
Depth estimation from a single image in the wild remains a challenging problem. One main obstacle is the lack of high-quality training data for images in the wild.
Chen, Weifeng, Deng, Jia, Qian, Shengyi
core   +1 more source

Rewriting Polymer Fate via Chemomechanical Coupling

Advanced Materials, EarlyView.
This work introduces a life‐like “living” polymer platform that can grow, degrow, and reprogram its properties after fabrication. By integrating mass transport, reversible polymerization, and controlled catalysis, the material achieves on‐demand changes in size, shape, and mechanical properties.
Jiahe Huang, Haohui Zhang, Jiehao Chen, Xuelin Sui, Febby Krisnadi, Dongjing He, Huajian Ji, Will R. Gutekunst, Michael D. Dickey, Yuhang Hu   +9 more
wiley   +1 more source

Learning optimization: Video learning media creation training using the Canva platform for kindergarten teachers

Abdimas: Jurnal Pengabdian Masyarakat Universitas Merdeka Malang
The development of information and communication technology (ICT) has had a significant impact on education, including early childhood education (PAUD).
Etty Octaviani Manalu, Indrawati, Maya Pujowati, Tri Suwarningsih   +3 more
doaj   +1 more source

DAP3D-Net: Where, What and How Actions Occur in Videos?

, 2016
Action parsing in videos with complex scenes is an interesting but challenging task in computer vision. In this paper, we propose a generic 3D convolutional neural network in a multi-task learning manner for effective Deep Action Parsing (DAP3D-Net) in ...
Liu, Li, Shao, Ling, Zhou, Yi
core   +1 more source

Manifold Learning for Video-to-Video Face Recognition

, 2009
We look in this work at the problem of video-based face recognition in which both training and test sets are video sequences, and propose a novel approach based on manifold learning. The idea consists of first learning the intrinsic personal characteristics of each subject from the training video sequences by discovering the hidden low-dimensional ...
Hadid Abdenour, Pietikäinen Matti
openaire   +1 more source