Search

Your search keyword '"Ling, Nam"' showing total 96 results
Start Over Author "Ling, Nam" Publication Year Range Last 3 years
96 results on '"Ling, Nam"'

1. HAAP: Vision-context Hierarchical Attention Autoregressive with Adaptive Permutation for Scene Text Recognition

Author

Chen, Honghui, Qiu, Yuhang, Wang, Jiabao, Chen, Pingping, and Ling, Nam

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Artificial Intelligence, 68T01, I.2.10
Abstract

Internal Language Model (LM)-based methods use permutation language modeling (PLM) to solve the error correction caused by conditional independence in external LM-based methods. However, random permutations of human interference cause fit oscillations in the model training, and Iterative Refinement (IR) operation to improve multimodal information decoupling also introduces additional overhead. To address these issues, this paper proposes the Hierarchical Attention autoregressive Model with Adaptive Permutation (HAAP) to enhance the location-context-image interaction capability, improving autoregressive generalization with internal LM. First, we propose Implicit Permutation Neurons (IPN) to generate adaptive attention masks to dynamically exploit token dependencies. The adaptive masks increase the diversity of training data and prevent model dependency on a specific order. It reduces the training overhead of PLM while avoiding training fit oscillations. Second, we develop Cross-modal Hierarchical Attention mechanism (CHA) to couple context and image features. This processing establishes rich positional semantic dependencies between context and image while avoiding IR. Extensive experimental results show the proposed HAAP achieves state-of-the-art (SOTA) performance in terms of accuracy, complexity, and latency on several datasets., Comment: 12 pages, 10 figures

Published
2024

2. Novel View Synthesis from a Single Image via Unsupervised learning

Author

Liu, Bingzheng, Lei, Jianjun, Peng, Bo, Yu, Chuanbo, Li, Wanqing, and Ling, Nam

Subjects
Computer Science - Computer Vision and Pattern Recognition
Abstract

View synthesis aims to generate novel views from one or more given source views. Although existing methods have achieved promising performance, they usually require paired views of different poses to learn a pixel transformation. This paper proposes an unsupervised network to learn such a pixel transformation from a single source viewpoint. In particular, the network consists of a token transformation module (TTM) that facilities the transformation of the features extracted from a source viewpoint image into an intrinsic representation with respect to a pre-defined reference pose and a view generation module (VGM) that synthesizes an arbitrary view from the representation. The learned transformation allows us to synthesize a novel view from any single source viewpoint image of unknown pose. Experiments on the widely used view synthesis datasets have demonstrated that the proposed network is able to produce comparable results to the state-of-the-art methods despite the fact that learning is unsupervised and only a single source viewpoint image is required for generating a novel view. The code will be available soon., Comment: 9 pages, submitted to TCSVT

Published
2021

13. Graph Based Cross-Channel Transform for Color Image Compression.

Author

Wang, Lilong, Shi, Yunhui, Wang, Jin, Chen, Shujun, Yin, Baocai, and Ling, Nam

Subjects
IMAGE compression, DISCRETE cosine transforms, REPRESENTATIONS of graphs, JPEG (Image coding standard), CONTENT mining, WAVELET transforms, DISCRETE wavelet transforms
Abstract

Adaptive transform coding is gaining more and more attention for better mining of image content over fixed transforms such as discrete cosine transform (DCT). As a special case, graph transform learning establishes a novel paradigm for the graph-based transforms. However, there still exists a challenge for graph transform learning-based image codecs design on natural image compression, and graph representation cannot describe regular image samples well over graph-structured data. Therefore, in this article, we propose a cross-channel graph-based transform (CCGBT) for natural color image compression. We observe that neighboring pixels having similar intensities should have similar values in the chroma channels, which means that the prominent structure of the luminance channel is related to the contours of the chrominance channels. A collaborative design of the learned graphs and their corresponding distinctive transforms lies in the assumption that a sufficiently small block can be considered smooth, meanwhile, guaranteeing the compression of the luma and chroma signals at the cost of a small overhead for coding the description of the designed luma graph. In addition, a color image compression framework based on the CCGBT is designed for comparing DCT on the classic JPEG codec. The proposed method benefits from its flexible transform block design on arbitrary sizes to exploit image content better than the fixed transform. The experimental results show that the unified graph-based transform outperforms conventional DCT, while close to discrete wavelet transform on JPEG2000 at high bit-rates. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

21. MSF-Net: Multi-Scale Feedback Reconstruction for Guided Depth Map Super-Resolution

Author

Wang, Jin, Li, Chenyang, Shi, Yunhui, Wang, Dan, Wu, Mu-En, Ling, Nam, and Yin, Baocai

Abstract

Guided depth map super-resolution (GDSR) is one of the mainstream methods in depth map super-resolution, as high-resolution color images can guide the reconstruction of the depth maps and are often easy to obtain. However, how to make full use of extracted guidance information of the color image to improve the depth map reconstruction remains a challenging problem. In this paper, we first design a multi-scale feedback module (MF) that extracts multi-scale features and alleviates the information loss in network propagation. We further propose a novel multi-scale feedback network (MSF-Net) for guided depth map super-resolution, which can better extract and refine the features by sequentially joining MF blocks. Specifically, our MF block uses parallel sampling layers and feedback links between multiple time steps to better learn information at different scales. Moreover, an inter-scale attention module (IA) is proposed to adaptively select and fuse important features at different scales. Meanwhile, depth features and corresponding color features are interacted using cross-domain attention conciliation module (CAC) after each MF block. We evaluate the performance of our proposed method on both synthetic and real captured datasets. Extensive experimental results validate that the proposed method achieves state-of-the-art performance in both objective and subjective quality.

Published
2024
Full Text
View/download PDF

22. Unsupervised Single-View Synthesis Network via Style Guidance and Prior Distillation

Author

Liu, Bingzheng, Peng, Bo, Zhang, Zhe, Huang, Qingming, Ling, Nam, and Lei, Jianjun

Abstract

View synthesis aims to learn a view transformation and synthesize the target views from a single or multiple source views. Although previous view synthesis methods have obtained promising performance, they heavily rely on the supervision of the target view. In this paper, we propose an unsupervised single-view synthesis network (USVS-Net) to learn the view transformation without the supervision of the target view. Specifically, with the usage of only a single source view, a style-guidance view synthesis model is proposed to learn an intrinsic representation, which intends to describe the object from a reference pose. With the intrinsic representation, the view transformation is learned to boost the learning of the unsupervised single-view synthesis. Then, taking the style-guidance view synthesis model as the teacher, a prior-distillation view synthesis model is further presented as the student to learn a more direct view transformation. By utilizing the proposed method, high-quality target views are synthesized in a time-efficient manner. Experiments on both synthetic and real-scene datasets show that despite the lack of supervision of the target view, the proposed method achieves promising results compared with the existing view synthesis methods.

Published
2024
Full Text
View/download PDF

43. The Future of Video Coding

Author

Ling, Nam, primary, Kuo, C.-C. Jay, primary, Sullivan, Gary J., primary, Xu, Dong, primary, Liu, Shan, primary, Hang, Hsueh-Ming, primary, Peng, Wen-Hsiao, primary, and Liu, Jiaying, primary

Published
2022
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results