Improved deep unsupervised hashing via prototypical learning
Hashing has become increasingly popular in approximate nearest neighbor search in recent
years due to its storage and computational efficiency. While deep unsupervised hashing has …
years due to its storage and computational efficiency. While deep unsupervised hashing has …
Semi-supervised reference-based sketch extraction using a contrastive learning framework
Sketches reflect the drawing style of individual artists; therefore, it is important to consider
their unique styles when extracting sketches from color images for various applications …
their unique styles when extracting sketches from color images for various applications …
Data-efficient masked video modeling for self-supervised action recognition
Recently, self-supervised video representation learning based on Masked Video Modeling
(MVM) has demonstrated promising results for action recognition. However, existing …
(MVM) has demonstrated promising results for action recognition. However, existing …
[HTML][HTML] Recognizing affective states from the expressive behavior of tennis players using convolutional neural networks
This study describes an AI model by leveraging advanced Convolutional Neural Networks
(CNNs) to recognize affective states in real-world sports settings, particularly tennis matches …
(CNNs) to recognize affective states in real-world sports settings, particularly tennis matches …
Towards Privacy-Supporting Fall Detection via Deep Unsupervised RGB2Depth Adaptation
H Xiao, K Peng, X Huang, A Roitberg, H Li… - IEEE Sensors …, 2023 - ieeexplore.ieee.org
Fall detection is a vital task in health monitoring, as it allows the system to trigger an alert
and therefore enable faster interventions when a person experiences a fall. Although most …
and therefore enable faster interventions when a person experiences a fall. Although most …
View-agnostic Human Exercise Cataloging with Single MmWave Radar
A Liu, YT Lin, K Sundaresan - Proceedings of the ACM on Interactive …, 2024 - dl.acm.org
Advances in mmWave-based sensing have enabled a privacy-friendly approach to pose
and gesture recognition. Yet, providing robustness with the sparsity of reflected signals has …
and gesture recognition. Yet, providing robustness with the sparsity of reflected signals has …
[PDF][PDF] MuscleMap: Towards Video-based Activated Muscle Group Estimation
In this paper, we tackle the new task of video-based Activated Muscle Group Estimation
(AMGE) aiming at identifying active muscle regions during physical activity. To this intent, we …
(AMGE) aiming at identifying active muscle regions during physical activity. To this intent, we …
Collaboratively Self-supervised Video Representation Learning for Action Recognition
Considering the close connection between action recognition and human pose estimation,
we design a Collaboratively Self-supervised Video Representation (CSVR) learning …
we design a Collaboratively Self-supervised Video Representation (CSVR) learning …
SynthAct: Towards Generalizable Human Action Recognition based on Synthetic Data
Synthetic data generation is a proven method for augmenting training sets without the need
for extensive setups, yet its application in human activity recognition is underexplored. This …
for extensive setups, yet its application in human activity recognition is underexplored. This …
MetaCL: a semi-supervised meta learning architecture via contrastive learning
C Li, Y Xie, Z Li, L Zhu - International Journal of Machine Learning and …, 2024 - Springer
Meta learning aims to endow models with the ability to quickly learn new tasks based on
existing knowledge. However, recent works have relied on complex structures and prior …
existing knowledge. However, recent works have relied on complex structures and prior …