Picture for Yu-Siang Wang

Yu-Siang Wang

OCID-Ref: A 3D Robotic Dataset with Embodied Language for Clutter Scene Grounding

Add code
Mar 13, 2021
Figure 1 for OCID-Ref: A 3D Robotic Dataset with Embodied Language for Clutter Scene Grounding
Figure 2 for OCID-Ref: A 3D Robotic Dataset with Embodied Language for Clutter Scene Grounding
Figure 3 for OCID-Ref: A 3D Robotic Dataset with Embodied Language for Clutter Scene Grounding
Figure 4 for OCID-Ref: A 3D Robotic Dataset with Embodied Language for Clutter Scene Grounding
Viaarxiv icon

Situation and Behavior Understanding by Trope Detection on Films

Add code
Jan 19, 2021
Figure 1 for Situation and Behavior Understanding by Trope Detection on Films
Figure 2 for Situation and Behavior Understanding by Trope Detection on Films
Figure 3 for Situation and Behavior Understanding by Trope Detection on Films
Figure 4 for Situation and Behavior Understanding by Trope Detection on Films
Viaarxiv icon

End-to-End Video Question-Answer Generation with Generator-Pretester Network

Add code
Jan 05, 2021
Figure 1 for End-to-End Video Question-Answer Generation with Generator-Pretester Network
Figure 2 for End-to-End Video Question-Answer Generation with Generator-Pretester Network
Figure 3 for End-to-End Video Question-Answer Generation with Generator-Pretester Network
Figure 4 for End-to-End Video Question-Answer Generation with Generator-Pretester Network
Viaarxiv icon

xCos: An Explainable Cosine Metric for Face Verification Task

Add code
Mar 11, 2020
Figure 1 for xCos: An Explainable Cosine Metric for Face Verification Task
Figure 2 for xCos: An Explainable Cosine Metric for Face Verification Task
Figure 3 for xCos: An Explainable Cosine Metric for Face Verification Task
Figure 4 for xCos: An Explainable Cosine Metric for Face Verification Task
Viaarxiv icon

Investigating the Decoders of Maximum Likelihood Sequence Models: A Look-ahead Approach

Mar 08, 2020
Figure 1 for Investigating the Decoders of Maximum Likelihood Sequence Models: A Look-ahead Approach
Figure 2 for Investigating the Decoders of Maximum Likelihood Sequence Models: A Look-ahead Approach
Figure 3 for Investigating the Decoders of Maximum Likelihood Sequence Models: A Look-ahead Approach
Figure 4 for Investigating the Decoders of Maximum Likelihood Sequence Models: A Look-ahead Approach
Viaarxiv icon

Video Question Generation via Cross-Modal Self-Attention Networks Learning

Jul 05, 2019
Figure 1 for Video Question Generation via Cross-Modal Self-Attention Networks Learning
Figure 2 for Video Question Generation via Cross-Modal Self-Attention Networks Learning
Figure 3 for Video Question Generation via Cross-Modal Self-Attention Networks Learning
Figure 4 for Video Question Generation via Cross-Modal Self-Attention Networks Learning
Viaarxiv icon

Adversarial Attacks Beyond the Image Space

Sep 10, 2018
Figure 1 for Adversarial Attacks Beyond the Image Space
Figure 2 for Adversarial Attacks Beyond the Image Space
Figure 3 for Adversarial Attacks Beyond the Image Space
Figure 4 for Adversarial Attacks Beyond the Image Space
Viaarxiv icon

Scene Graph Parsing as Dependency Parsing

Add code
Mar 25, 2018
Figure 1 for Scene Graph Parsing as Dependency Parsing
Figure 2 for Scene Graph Parsing as Dependency Parsing
Figure 3 for Scene Graph Parsing as Dependency Parsing
Figure 4 for Scene Graph Parsing as Dependency Parsing
Viaarxiv icon