[图书][B] Synthetic data for deep learning
SI Nikolenko - 2021 - Springer
You are holding in your hands… oh, come on, who holds books like this in their hands
anymore? Anyway, you are reading this, and it means that I have managed to release one of …
anymore? Anyway, you are reading this, and it means that I have managed to release one of …
MMTM: Multimodal transfer module for CNN fusion
In late fusion, each modality is processed in a separate unimodal Convolutional Neural
Network (CNN) stream and the scores of each modality are fused at the end. Due to its …
Network (CNN) stream and the scores of each modality are fused at the end. Due to its …
A robust learning approach to domain adaptive object detection
M Khodabandeh, A Vahdat… - Proceedings of the …, 2019 - openaccess.thecvf.com
Abstract Domain shift is unavoidable in real-world applications of object detection. For
example, in self-driving cars, the target domain consists of unconstrained road environments …
example, in self-driving cars, the target domain consists of unconstrained road environments …
Eldersim: A synthetic data generation platform for human action recognition in eldercare applications
To train deep learning models for vision-based action recognition of elders' daily activities,
we need large-scale activity datasets acquired under various daily living environments and …
we need large-scale activity datasets acquired under various daily living environments and …
Take an emotion walk: Perceiving emotions from gaits using hierarchical attention pooling and affective mapping
We present an autoencoder-based semi-supervised approach to classify perceived human
emotions from walking styles obtained from videos or motion-captured data and represented …
emotions from walking styles obtained from videos or motion-captured data and represented …
Exploring human pose estimation and the usage of synthetic data for elderly fall detection in real-world surveillance
The world's elderly population continues to grow at an unprecedented rate, creating a need
to monitor the safety of an aging population. One of the current problems is accurately …
to monitor the safety of an aging population. One of the current problems is accurately …
Simple yet efficient real-time pose-based action recognition
D Ludl, T Gulde, C Curio - 2019 IEEE Intelligent Transportation …, 2019 - ieeexplore.ieee.org
Recognizing human actions is a core challenge for autonomous systems as they directly
share the same space with humans. Systems must be able to recognize and assess human …
share the same space with humans. Systems must be able to recognize and assess human …
Attacking gait recognition systems via silhouette guided GANs
This paper investigates a new attack method to gait recognition systems. Different from
typical spoofing attacks that require impostors to mimic certain clothing or walking styles, it …
typical spoofing attacks that require impostors to mimic certain clothing or walking styles, it …
The liar's walk: Detecting deception with gait and gesture
We present a data-driven deep neural algorithm for detecting deceptive walking behavior
using nonverbal cues like gaits and gestures. We conducted an elaborate user study, where …
using nonverbal cues like gaits and gestures. We conducted an elaborate user study, where …
Bent & Broken Bicycles: Leveraging synthetic data for damaged object re-identification
Instance-level object re-identification is a fundamental computer vision task, with
applications from image retrieval to intelligent monitoring and fraud detection. In this work …
applications from image retrieval to intelligent monitoring and fraud detection. In this work …