Efficient Shape Coding for Object-Based 3D Video Applications

Zhu, Zhongkui; Wang, Yuer; Jiang, Gangyi; Yang, Yueping

doi:10.1109/tcsvt.2018.2881469

Cited by 3 publications

(1 citation statement)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The techniques of voltage clamping, synchronous rectification and soft switching are manipulated thus providing high efficiency bidirectional power conversion for power sources with large voltage diversity. [3] 2 Proposed topology…”

Section: Introductionmentioning

confidence: 99%

Analysis of Solar PV Application Based on Bidirectional Inverter

Jeylani¹,

Kanakaraj

Subahani

et al. 2018

MATEC Web Conf.

View full text Add to dashboard Cite

Building a DC-DC converter with high step-up, low cost and high efficiency from low DC voltage is the requirement in many applications. It is achieved by employing a front end boost converter based full bridge inverter on bidirectional inverter. In conventional boost converter during device turn-off, voltage overshoot occurs across the semiconductor devices. So, an additional snubber or voltage clamping is required to limit the overshot voltage. It upturns the component’s count and losses making the converter less efficient. The above problem can be avoided by operate the converter with soft-switching method by using secondary modulation technique. Hence, it avoids the need of additional snubber or auxiliary circuit. Soft switching operation is proposed in the bidirectional inverter. Soft switching operation is achieved through the auxiliary circuit, which consist of two auxiliary switches, Front end converter and full bridge inverter. Bidirectional inverter allows current flow in both direction and therefore permits energy flow from the grid to storage when solar energy is not available. The theoretical analysis of the proposed converter is verified using simulation results.

show abstract

Section: Introductionmentioning

confidence: 99%

Analysis of Solar PV Application Based on Bidirectional Inverter

Jeylani¹,

Kanakaraj

Subahani

et al. 2018

MATEC Web Conf.

View full text Add to dashboard Cite

show abstract

Multi-Level View Associative Convolution Network for View-Based 3D Model Retrieval

Gao

Zhang

et al. 2022

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

MMFN

Nie

Wang

et al. 2020

ACM Trans. Multimedia Comput. Commun. Appl.

View full text Add to dashboard Cite

In recent years, research into 3D shape recognition in the field of multimedia and computer vision has attracted wide attention. With the rapid development of deep learning, various deep models have achieved state-of-the-art performance based on different representations. There are many modalities for representing a 3D model, such as point cloud, multiview, and panorama view. Deep learning models based on these different modalities have different concerns, and all of them have achieved high performance for 3D shape recognition. However, all of these methods ignore the multimodality information in conditions where the same 3D model is represented by different modalities. Thus, we can obtain a better descriptor by guiding the training to consider these multiple representations. In this article, we propose MMFN, a novel multimodal fusion network for 3D shape recognition that employs correlations between the different modalities to generate a fused descriptor, which is more robust. In particular, we design two novel loss functions to help the model learn the correlation information during training. The first is correlation loss, which focuses on the correlations among different descriptors generated from different structures. This approach reduces the training time and improves the robustness of the fused descriptor of the 3D model. The second is instance loss, which preserves the independence of each modality and utilizes feature differentiation to guide model learning during the training process. More specifically, we use the weighted fusion method, which applies statistical methods to obtain robust descriptors that maximize the advantages of the information from the different modalities. We evaluated the proposed method on the ModelNet40 and ShapeNetCore55 datasets for 3D shape classification and retrieval tasks. The experimental results and comparisons with state-of-the-art methods demonstrate the superiority of our approach.

show abstract

Efficient Shape Coding for Object-Based 3D Video Applications

Cited by 3 publications

References 19 publications

Analysis of Solar PV Application Based on Bidirectional Inverter

Analysis of Solar PV Application Based on Bidirectional Inverter

Multi-Level View Associative Convolution Network for View-Based 3D Model Retrieval

MMFN

Contact Info

Product

Resources

About