Article-Journal

Matching Compound Prototypes for Few-Shot Action Recognition
The task of few-shot action recognition aims to recognize novel action classes using only a small number of labeled training samples. …
PDF Cite Code DOI
Matching Compound Prototypes for Few-Shot Action Recognition
Image-to-Text Translation for Interactive Image Recognition: A Comparative User Study with Non-Expert Users
Interactive machine learning (IML) allows users to build their custom machine learning models without expert knowledge. While most …
PDF Cite DOI
Image-to-Text Translation for Interactive Image Recognition: A Comparative User Study with Non-Expert Users
Technical Understanding from Interactive Machine Learning Experience: A Study through a Public Event for Science Museum Visitors
While AI technology is becoming increasingly prevalent in our daily lives, the comprehension of machine learning (ML) among non-experts …
PDF Cite DOI
Technical Understanding from Interactive Machine Learning Experience: A Study through a Public Event for Science Museum Visitors
Simultaneous control of head pose and expressions in 3D facial keypoint-based GAN
In this work, we present a novel method for simultaneously controlling the head pose and the facial expressions of a given input image …
PDF Cite DOI
Simultaneous control of head pose and expressions in 3D facial keypoint-based GAN
Efficient Annotation and Learning for 3D Hand Pose Estimation: A Survey
In this survey, we present a systematic review of 3D hand pose estimation from the perspective of efficient annotation and learning. 3D …
PDF Cite
Efficient Annotation and Learning for 3D Hand Pose Estimation: A Survey
Interactive Machine Learning on Edge Devices With User-in-the-Loop Sample Recommendation
Interactive machine learning (IML) aims to make machine learning an easy-to-use tool for novice users to solve personalized tasks. …
PDF Cite DOI
Interactive Machine Learning on Edge Devices With User-in-the-Loop Sample Recommendation
Self-Supervised Learning for Audio-Visual Relationships of Videos with Stereo Sounds
Learning cross-modal features is an essential task for many multimedia applications such as sound localization, audio-visual alignment, …
PDF Cite DOI
Self-Supervised Learning for Audio-Visual Relationships of Videos with Stereo Sounds
Semantic Image Segmentation by Dynamic Discriminative Prototypes
Semantic segmentation achieves significant success through large-scale training data. Meanwhile, few-shot semantic segmentation was …
Cite
Semantic Image Segmentation by Dynamic Discriminative Prototypes
Go-Finder: A Registration-Free Wearable System for Assisting Users in Finding Lost Hand-Held Objects
People spend an enormous amount of time and effort looking for lost objects. To help remind people of the location of lost objects, …
PDF Cite DOI
Go-Finder: A Registration-Free Wearable System for Assisting Users in Finding Lost Hand-Held Objects
Spatio-Temporal Perturbations for Video Attribution
The attribution method provides a direction for interpreting opaque neural networks in a visual way by identifying and visualizing the …
PDF Cite DOI
Spatio-Temporal Perturbations for Video Attribution