Picture for Yin Zhao

Yin Zhao

Bit Rate Matching Algorithm Optimization in JPEG-AI Verification Model

Feb 27, 2024
Viaarxiv icon

Bit Distribution Study and Implementation of Spatial Quality Map in the JPEG-AI Standardization

Feb 27, 2024
Viaarxiv icon

Triple Disentangled Representation Learning for Multimodal Affective Analysis

Jan 29, 2024
Viaarxiv icon

Learning Subjective Time-Series Data via Utopia Label Distribution Approximation

Add code
Jul 15, 2023
Figure 1 for Learning Subjective Time-Series Data via Utopia Label Distribution Approximation
Figure 2 for Learning Subjective Time-Series Data via Utopia Label Distribution Approximation
Figure 3 for Learning Subjective Time-Series Data via Utopia Label Distribution Approximation
Figure 4 for Learning Subjective Time-Series Data via Utopia Label Distribution Approximation
Viaarxiv icon

Reducing the Covariate Shift by Mirror Samples in Cross Domain Alignment

Add code
Oct 13, 2021
Figure 1 for Reducing the Covariate Shift by Mirror Samples in Cross Domain Alignment
Figure 2 for Reducing the Covariate Shift by Mirror Samples in Cross Domain Alignment
Figure 3 for Reducing the Covariate Shift by Mirror Samples in Cross Domain Alignment
Figure 4 for Reducing the Covariate Shift by Mirror Samples in Cross Domain Alignment
Viaarxiv icon

Pairwise Emotional Relationship Recognition in Drama Videos: Dataset and Benchmark

Add code
Sep 23, 2021
Figure 1 for Pairwise Emotional Relationship Recognition in Drama Videos: Dataset and Benchmark
Figure 2 for Pairwise Emotional Relationship Recognition in Drama Videos: Dataset and Benchmark
Figure 3 for Pairwise Emotional Relationship Recognition in Drama Videos: Dataset and Benchmark
Figure 4 for Pairwise Emotional Relationship Recognition in Drama Videos: Dataset and Benchmark
Viaarxiv icon

Subjective evaluation of traditional and learning-based image coding methods

Add code
Jul 28, 2021
Figure 1 for Subjective evaluation of traditional and learning-based image coding methods
Figure 2 for Subjective evaluation of traditional and learning-based image coding methods
Figure 3 for Subjective evaluation of traditional and learning-based image coding methods
Figure 4 for Subjective evaluation of traditional and learning-based image coding methods
Viaarxiv icon

ESA-ReID: Entropy-Based Semantic Feature Alignment for Person re-ID

Jul 09, 2020
Figure 1 for ESA-ReID: Entropy-Based Semantic Feature Alignment for Person re-ID
Figure 2 for ESA-ReID: Entropy-Based Semantic Feature Alignment for Person re-ID
Figure 3 for ESA-ReID: Entropy-Based Semantic Feature Alignment for Person re-ID
Figure 4 for ESA-ReID: Entropy-Based Semantic Feature Alignment for Person re-ID
Viaarxiv icon

RNE: A Scalable Network Embedding for Billion-scale Recommendation

Apr 09, 2020
Figure 1 for RNE: A Scalable Network Embedding for Billion-scale Recommendation
Figure 2 for RNE: A Scalable Network Embedding for Billion-scale Recommendation
Figure 3 for RNE: A Scalable Network Embedding for Billion-scale Recommendation
Figure 4 for RNE: A Scalable Network Embedding for Billion-scale Recommendation
Viaarxiv icon

Video Affective Effects Prediction with Multi-modal Fusion and Shot-Long Temporal Context

Sep 01, 2019
Figure 1 for Video Affective Effects Prediction with Multi-modal Fusion and Shot-Long Temporal Context
Figure 2 for Video Affective Effects Prediction with Multi-modal Fusion and Shot-Long Temporal Context
Figure 3 for Video Affective Effects Prediction with Multi-modal Fusion and Shot-Long Temporal Context
Figure 4 for Video Affective Effects Prediction with Multi-modal Fusion and Shot-Long Temporal Context
Viaarxiv icon