ﻻ يوجد ملخص باللغة العربية
Standard lossy image compression algorithms aim to preserve an images appearance, while minimizing the number of bits needed to transmit it. However, the amount of information actually needed by a user for downstream tasks -- e.g., deciding which product to click on in a shopping website -- is likely much lower. To achieve this lower bitrate, we would ideally only transmit the visual features that drive user behavior, while discarding details irrelevant to the users decisions. We approach this problem by training a compression model through human-in-the-loop learning as the user performs tasks with the compressed images. The key insight is to train the model to produce a compressed image that induces the user to take the same action that they would have taken had they seen the original image. To approximate the loss function for this model, we train a discriminator that tries to distinguish whether a users action was taken in response to the compressed image or the original. We evaluate our method through experiments with human participants on four tasks: reading handwritten digits, verifying photos of faces, browsing an online shopping catalogue, and playing a car racing video game. The results show that our method learns to match the users actions with and without compression at lower bitrates than baseline methods, and adapts the compression model to the users behavior: it preserves the digit number and randomizes handwriting style in the digit reading task, preserves hats and eyeglasses while randomizing faces in the photo verification task, preserves the perceived price of an item while randomizing its color and background in the online shopping task, and preserves upcoming bends in the road in the car racing game.
What happen in the brain when human beings play games with computers? Here a simple zero-sum game was conducted to investigate how people make decision via their brain even they know that their opponent is a computer. There are two choices (a low or
Convolutional Neural Networks (CNNs) are successful deep learning models in the field of computer vision. To get the maximum advantage of CNN model for Human Action Recognition (HAR) using inertial sensor data, in this paper, we use 4 types of spatia
The fundamental goal of business data analysis is to improve business decisions using data. Business users such as sales, marketing, product, or operations managers often make decisions to achieve key performance indicator (KPI) goals such as increas
The widespread use of deep neural networks has achieved substantial success in many tasks. However, there still exists a huge gap between the operating mechanism of deep learning models and human-understandable decision making, so that humans cannot
Action selection from many options with few constraints is crucial for improvisation and co-creativity. Our previous work proposed creative arc negotiation to solve this problem, i.e., selecting actions to follow an author-defined `creative arc or tr