Picture for James Z. Wang

James Z. Wang

Context-driven self-supervised visual learning: Harnessing the environment as a data source

Add code
Jan 26, 2024
Viaarxiv icon

AI-SAM: Automatic and Interactive Segment Anything Model

Add code
Dec 05, 2023
Viaarxiv icon

Unlocking the Emotional World of Visual Media: An Overview of the Science, Research, and Impact of Understanding Emotion

Add code
Jul 25, 2023
Figure 1 for Unlocking the Emotional World of Visual Media: An Overview of the Science, Research, and Impact of Understanding Emotion
Figure 2 for Unlocking the Emotional World of Visual Media: An Overview of the Science, Research, and Impact of Understanding Emotion
Figure 3 for Unlocking the Emotional World of Visual Media: An Overview of the Science, Research, and Impact of Understanding Emotion
Figure 4 for Unlocking the Emotional World of Visual Media: An Overview of the Science, Research, and Impact of Understanding Emotion
Viaarxiv icon

Learning Emotion Representations from Verbal and Nonverbal Communication

Add code
May 22, 2023
Figure 1 for Learning Emotion Representations from Verbal and Nonverbal Communication
Figure 2 for Learning Emotion Representations from Verbal and Nonverbal Communication
Figure 3 for Learning Emotion Representations from Verbal and Nonverbal Communication
Figure 4 for Learning Emotion Representations from Verbal and Nonverbal Communication
Viaarxiv icon

Bodily expressed emotion understanding through integrating Laban movement analysis

Add code
Apr 05, 2023
Figure 1 for Bodily expressed emotion understanding through integrating Laban movement analysis
Figure 2 for Bodily expressed emotion understanding through integrating Laban movement analysis
Figure 3 for Bodily expressed emotion understanding through integrating Laban movement analysis
Figure 4 for Bodily expressed emotion understanding through integrating Laban movement analysis
Viaarxiv icon

Learning to Adapt to Online Streams with Distribution Shifts

Add code
Mar 02, 2023
Figure 1 for Learning to Adapt to Online Streams with Distribution Shifts
Figure 2 for Learning to Adapt to Online Streams with Distribution Shifts
Figure 3 for Learning to Adapt to Online Streams with Distribution Shifts
Figure 4 for Learning to Adapt to Online Streams with Distribution Shifts
Viaarxiv icon

Asymmetry Disentanglement Network for Interpretable Acute Ischemic Stroke Infarct Segmentation in Non-Contrast CT Scans

Add code
Jun 30, 2022
Figure 1 for Asymmetry Disentanglement Network for Interpretable Acute Ischemic Stroke Infarct Segmentation in Non-Contrast CT Scans
Figure 2 for Asymmetry Disentanglement Network for Interpretable Acute Ischemic Stroke Infarct Segmentation in Non-Contrast CT Scans
Figure 3 for Asymmetry Disentanglement Network for Interpretable Acute Ischemic Stroke Infarct Segmentation in Non-Contrast CT Scans
Figure 4 for Asymmetry Disentanglement Network for Interpretable Acute Ischemic Stroke Infarct Segmentation in Non-Contrast CT Scans
Viaarxiv icon

HICEM: A High-Coverage Emotion Model for Artificial Emotional Intelligence

Add code
Jun 15, 2022
Figure 1 for HICEM: A High-Coverage Emotion Model for Artificial Emotional Intelligence
Figure 2 for HICEM: A High-Coverage Emotion Model for Artificial Emotional Intelligence
Figure 3 for HICEM: A High-Coverage Emotion Model for Artificial Emotional Intelligence
Figure 4 for HICEM: A High-Coverage Emotion Model for Artificial Emotional Intelligence
Viaarxiv icon

Patcher: Patch Transformers with Mixture of Experts for Precise Medical Image Segmentation

Add code
Jun 03, 2022
Figure 1 for Patcher: Patch Transformers with Mixture of Experts for Precise Medical Image Segmentation
Figure 2 for Patcher: Patch Transformers with Mixture of Experts for Precise Medical Image Segmentation
Figure 3 for Patcher: Patch Transformers with Mixture of Experts for Precise Medical Image Segmentation
Figure 4 for Patcher: Patch Transformers with Mixture of Experts for Precise Medical Image Segmentation
Viaarxiv icon

Forget Less, Count Better: A Domain-Incremental Self-Distillation Learning Benchmark for Lifelong Crowd Counting

Add code
May 06, 2022
Figure 1 for Forget Less, Count Better: A Domain-Incremental Self-Distillation Learning Benchmark for Lifelong Crowd Counting
Figure 2 for Forget Less, Count Better: A Domain-Incremental Self-Distillation Learning Benchmark for Lifelong Crowd Counting
Figure 3 for Forget Less, Count Better: A Domain-Incremental Self-Distillation Learning Benchmark for Lifelong Crowd Counting
Figure 4 for Forget Less, Count Better: A Domain-Incremental Self-Distillation Learning Benchmark for Lifelong Crowd Counting
Viaarxiv icon