Paper-Conference

Interact before Align: Leveraging Cross-Modal Knowledge for Domain Adaptive Action Recognition
Unsupervised domain adaptive video action recognition aims to recognize actions of a target domain using a model trained with only …
PDF 引用 DOI
Interact before Align: Leveraging Cross-Modal Knowledge for Domain Adaptive Action Recognition
Object Instance Identification in Dynamic Environments
We study the problem of identifying object instances in a dynamic environment where people interact with the objects. In such an …
PDF 引用
Object Instance Identification in Dynamic Environments
Precise Affordance Annotation for Egocentric Action Video Datasets
Object affordance is an important concept in human-object interaction, providing information on action possibilities based on human …
PDF 引用
Precise Affordance Annotation for Egocentric Action Video Datasets
Neural Routing by Memory
Recent Convolutional Neural Networks (CNNs) have achieved significant success by stacking multiple convolutional blocks, named …
PDF 引用
Neural Routing by Memory
Hand-Object Contact Prediction via Motion-Based Pseudo-Labeling and Guided Progressive Label Correction
Every hand-object interaction begins with contact. Despite predicting the contact state between hands and objects is useful in …
PDF 引用
Hand-Object Contact Prediction via Motion-Based Pseudo-Labeling and Guided Progressive Label Correction
Leveraging Human Selective Attention for Medical Image Analysis with Limited Training Data
The human gaze is a cost-efficient physiological data that reveals human underlying attentional patterns. The selective attention …
PDF 引用
Leveraging Human Selective Attention for Medical Image Analysis with Limited Training Data
Stacked Temporal Attention: Improving First-person Action Recognition by Emphasizing Discriminative Clips
First-person action recognition is a challenging task in video understanding. Because of strong ego-motion and a limited field of view, …
PDF 引用
Stacked Temporal Attention: Improving First-person Action Recognition by Emphasizing Discriminative Clips
Unsupervised Common Particular Object Discovery and Localization by Analyzing a Match Graph
Although the unsupervised discovery and localization of common objects from within a set of images has received considerable attention, …
PDF 引用 DOI
Unsupervised Common Particular Object Discovery and Localization by Analyzing a Match Graph
GO-Finder: A Registration-Free Wearable System for Assisting Users in Finding Lost Objects via Hand-Held Object Discovery
People spend an enormous amount of time and effort looking for lost objects. To help remind people of the location of lost objects, …
PDF 引用 DOI
GO-Finder: A Registration-Free Wearable System for Assisting Users in Finding Lost Objects via Hand-Held Object Discovery
Toward Visually Explaining Video Understanding Networks by Perturbation
‘‘Making black box models explainable’’ is a vital problem that accompanies the development of deep learning …
PDF 引用 DOI
Toward Visually Explaining Video Understanding Networks by Perturbation