Picture for Zhengjue Wang

Zhengjue Wang

HICEScore: A Hierarchical Metric for Image Captioning Evaluation

Add code
Jul 26, 2024
Figure 1 for HICEScore: A Hierarchical Metric for Image Captioning Evaluation
Figure 2 for HICEScore: A Hierarchical Metric for Image Captioning Evaluation
Figure 3 for HICEScore: A Hierarchical Metric for Image Captioning Evaluation
Figure 4 for HICEScore: A Hierarchical Metric for Image Captioning Evaluation
Viaarxiv icon

MeaCap: Memory-Augmented Zero-shot Image Captioning

Add code
Mar 06, 2024
Viaarxiv icon

SnapCap: Efficient Snapshot Compressive Video Captioning

Add code
Jan 10, 2024
Viaarxiv icon

ConZIC: Controllable Zero-shot Image Captioning by Sampling-Based Polishing

Add code
Mar 09, 2023
Viaarxiv icon

Block Modulating Video Compression: An Ultra Low Complexity Image Compression Encoder for Resource Limited Platforms

Add code
May 07, 2022
Figure 1 for Block Modulating Video Compression: An Ultra Low Complexity Image Compression Encoder for Resource Limited Platforms
Figure 2 for Block Modulating Video Compression: An Ultra Low Complexity Image Compression Encoder for Resource Limited Platforms
Figure 3 for Block Modulating Video Compression: An Ultra Low Complexity Image Compression Encoder for Resource Limited Platforms
Figure 4 for Block Modulating Video Compression: An Ultra Low Complexity Image Compression Encoder for Resource Limited Platforms
Viaarxiv icon

Memory-Efficient Network for Large-scale Video Compressive Sensing

Add code
Mar 05, 2021
Figure 1 for Memory-Efficient Network for Large-scale Video Compressive Sensing
Figure 2 for Memory-Efficient Network for Large-scale Video Compressive Sensing
Figure 3 for Memory-Efficient Network for Large-scale Video Compressive Sensing
Figure 4 for Memory-Efficient Network for Large-scale Video Compressive Sensing
Viaarxiv icon

MetaSCI: Scalable and Adaptive Reconstruction for Video Compressive Sensing

Add code
Mar 02, 2021
Figure 1 for MetaSCI: Scalable and Adaptive Reconstruction for Video Compressive Sensing
Figure 2 for MetaSCI: Scalable and Adaptive Reconstruction for Video Compressive Sensing
Figure 3 for MetaSCI: Scalable and Adaptive Reconstruction for Video Compressive Sensing
Figure 4 for MetaSCI: Scalable and Adaptive Reconstruction for Video Compressive Sensing
Viaarxiv icon

Variational Hetero-Encoder Randomized Generative Adversarial Networks for Joint Image-Text Modeling

Add code
May 18, 2019
Figure 1 for Variational Hetero-Encoder Randomized Generative Adversarial Networks for Joint Image-Text Modeling
Figure 2 for Variational Hetero-Encoder Randomized Generative Adversarial Networks for Joint Image-Text Modeling
Figure 3 for Variational Hetero-Encoder Randomized Generative Adversarial Networks for Joint Image-Text Modeling
Figure 4 for Variational Hetero-Encoder Randomized Generative Adversarial Networks for Joint Image-Text Modeling
Viaarxiv icon