Explainable action prediction through self-supervision on scene graphs
P Kochakarn, D De Martini, D Omeiza… - … on Robotics and …, 2023 - ieeexplore.ieee.org
This work explores scene graphs as a distilled representation of high-level information for
autonomous driving, applied to future driver-action prediction. Given the scarcity and strong …
autonomous driving, applied to future driver-action prediction. Given the scarcity and strong …
Don't explain without verifying veracity: an evaluation of explainable ai with video activity recognition
Explainable machine learning and artificial intelligence models have been used to justify a
model's decision-making process. This added transparency aims to help improve user …
model's decision-making process. This added transparency aims to help improve user …
Data-level information enhancement: Motion-patch-based Siamese Convolutional Neural Networks for human activity recognition in videos
Data augmentation is critical for deep learning-based human activity recognition (HAR)
systems. However, conventional data augmentation methods, such as random-cropping …
systems. However, conventional data augmentation methods, such as random-cropping …
Adversarial attacks against LipNet: End-to-end sentence level lipreading
M Jethanandani, D Tang - 2020 IEEE Security and Privacy …, 2020 - ieeexplore.ieee.org
Visual adversarial attacks inspired by Carlini-Wagner targeted audiovisual attacks can fool
the state-of-the-art Google DeepMind LipNet model to subtitle anything with over 99 …
the state-of-the-art Google DeepMind LipNet model to subtitle anything with over 99 …
Human action recognition in unconstrained trimmed videos using residual attention network and joints path signature
Action recognition has been achieved great progress in recent years because of better
feature representation learning and classification technology like convolutional neural …
feature representation learning and classification technology like convolutional neural …
Visual Attention Assisted Games
In this work, we propose a committee of attention models developed for improving the deep
reinforcement learning frequently used for games. The game environment is manifested with …
reinforcement learning frequently used for games. The game environment is manifested with …
Spatio-temporal attention deep recurrent q-network for pomdps
One of the long-standing challenges for reinforcement learning agents is to deal with noisy
environments. Although progress has been made in producing an agent capable of …
environments. Although progress has been made in producing an agent capable of …
[图书][B] Shadows of the Past: The Effects of User's Differences and Past Experiences on Human-AI Partnership
M Nourani - 2023 - search.proquest.com
Abstract Recent advancements in Artificial Intelligence (AI) necessitate designing systems
wary of users and stakeholders. People from different backgrounds encounter intelligent …
wary of users and stakeholders. People from different backgrounds encounter intelligent …
Multi-Group Multi-Attention: Towards Discriminative Spatiotemporal Representation
Z Shi, L Cao, C Guan, J Liang, Q Li, Z Gu… - Proceedings of the 28th …, 2020 - dl.acm.org
Learning spatiotemporal features is very effective but challenging for video understanding
especially action recognition. In this paper, we propose Multi-Group Multi-Attention, dubbed …
especially action recognition. In this paper, we propose Multi-Group Multi-Attention, dubbed …
CNN–LSTM con mecanismo de atención suave para el reconocimiento de acciones humanas en videos
CI Orozco, ME Buemi, JJ Berlles - Elektron, 2021 - elektron.fi.uba.ar
El reconocimiento de acciones en videos es actualmente un tema de interés en el área de
la visión por computador, debido a potenciales aplicaciones como: indexación multimedia …
la visión por computador, debido a potenciales aplicaciones como: indexación multimedia …