Search Results for author: Li Song

Found 39 papers, 10 papers with code

Building a Chinese AMR Bank with Concept and Relation Alignments

no code implementations LILT 2019 Bin Li, Yuan Wen, Li Song, Weiguang Qu, Nianwen Xue

One significant change we have made to the AMR annotation methodology is the inclusion of the alignment between word tokens in the sentence and the concepts/relations in the CAMR annotation to make it easier for automatic parsers to model the correspondence between a sentence and its meaning representation.

Abstract Meaning Representation Relation +1

用计量风格学方法考察《水浒传》的作者争议问题——以罗贯中《平妖传》为参照(Quantitive Stylistics Based Research on the Controversy of the Author of “Tales of the Marshes”: Comparing with “Pingyaozhuan” of Luo Guanzhong)

no code implementations CCL 2020 Li Song, Ying Liu

《水浒传》是独著还是合著, 施耐庵和罗贯中是何关系一直存在争议。本文将其作者争议粗略归纳为施耐庵作、罗贯中作、施作罗续、罗作他续、施作罗改五种情况, 以罗贯中的《平妖传》为参照, 用假设检验、文本聚类、文本分类、波动风格计量等方法, 结合对文本内容的分析, 考察《水浒传》的写作风格, 试图为其作者身份认定提供参考。结果显示, 只有罗作他续的可能性大, 即前70回为罗贯中所作, 后由他人续写, 其他四种情况可能性都较小。

Dyn-Adapter: Towards Disentangled Representation for Efficient Visual Recognition

no code implementations19 Jul 2024 Yurong Zhang, Honghao Chen, Xinyu Zhang, Xiangxiang Chu, Li Song

Parameter-efficient transfer learning (PETL) is a promising task, aiming to adapt the large-scale pre-trained model to downstream tasks with a relatively modest cost.

HPC: Hierarchical Progressive Coding Framework for Volumetric Video

no code implementations12 Jul 2024 Zihan Zheng, Houqiang Zhong, Qiang Hu, Xiaoyun Zhang, Li Song, Ya zhang, Yanfeng Wang

Volumetric video based on Neural Radiance Field (NeRF) holds vast potential for various 3D applications, but its substantial data volume poses significant challenges for compression and transmission.

MRIR: Integrating Multimodal Insights for Diffusion-based Realistic Image Restoration

no code implementations4 Jul 2024 Yuhong Zhang, Hengsheng Zhang, Xinning Chai, Rong Xie, Li Song, Wenjun Zhang

In this work, we delve into the potential of utilizing pre-trained stable diffusion for image restoration and propose MRIR, a diffusion-based restoration method with multimodal insights.

Denoising Image Restoration +3

Diff-Restorer: Unleashing Visual Prompts for Diffusion-based Universal Image Restoration

no code implementations4 Jul 2024 Yuhong Zhang, Hengsheng Zhang, Xinning Chai, Zhengxue Cheng, Rong Xie, Li Song, Wenjun Zhang

Image restoration is a classic low-level problem aimed at recovering high-quality images from low-quality images with various degradations such as blur, noise, rain, haze, etc.

Decoder Image Restoration +1

JointRF: End-to-End Joint Optimization for Dynamic Neural Radiance Field Representation and Compression

no code implementations23 May 2024 Zihan Zheng, Houqiang Zhong, Qiang Hu, Xiaoyun Zhang, Li Song, Ya zhang, Yanfeng Wang

Neural Radiance Field (NeRF) excels in photo-realistically static scenes, inspiring numerous efforts to facilitate volumetric videos.

Feature Compression

Multimodal Semantic-Aware Automatic Colorization with Diffusion Prior

no code implementations25 Apr 2024 Han Wang, Xinning Chai, Yiwen Wang, Yuhong Zhang, Rong Xie, Li Song

Existing automatic colorization methods often fail to generate satisfactory results due to incorrect semantic colors and unsaturated colors.

Colorization Decoder +1

In-Context Translation: Towards Unifying Image Recognition, Processing, and Generation

no code implementations15 Apr 2024 Han Xue, Qianru Sun, Li Song, Wenjun Zhang, Zhiwu Huang

Secondly, it standardizes the training of different tasks into a general in-context learning, where "in-context" means the input comprises an example input-output pair of the target task and a query image.

Conditional Image Generation Denoising +5

Depth-Guided Robust and Fast Point Cloud Fusion NeRF for Sparse Input Views

no code implementations4 Mar 2024 Shuai Guo, Qiuwen Wang, Yijie Gao, Rong Xie, Li Song

A point cloud is constructed for each input view, characterized within the voxel grid using matrices and vectors.

Autonomous Driving Novel View Synthesis

Efficient Dynamic-NeRF Based Volumetric Video Coding with Rate Distortion Optimization

no code implementations2 Feb 2024 ZhiYu Zhang, Guo Lu, Huanxiong Liang, Anni Tang, Qiang Hu, Li Song

Volumetric videos, benefiting from immersive 3D realism and interactivity, hold vast potential for various applications, while the tremendous data volume poses significant challenges for compression.

Video Compression

Disentangled Clothed Avatar Generation from Text Descriptions

no code implementations8 Dec 2023 Jionghao Wang, YuAn Liu, Zhiyang Dou, Zhengming Yu, Yongqing Liang, Xin Li, Wenping Wang, Rong Xie, Li Song

In this paper, we introduced a novel text-to-avatar generation method that separately generates the human body and the clothes and allows high-quality animation on the generated avatar.

Virtual Try-on

Implicit-explicit Integrated Representations for Multi-view Video Compression

1 code implementation29 Nov 2023 Chen Zhu, Guo Lu, Bing He, Rong Xie, Li Song

To further enhance the reconstruction quality from the INR codec, we leverage the high-quality reconstructed frames from the explicit codec to achieve inter-view compensation.

Video Compression

Spatio-Temporal Contrastive Self-Supervised Learning for POI-level Crowd Flow Inference

no code implementations6 Sep 2023 Songyu Ke, Ting Li, Li Song, Yanping Sun, Qintian Sun, Junbo Zhang, Yu Zheng

To address these challenges, we recast the crowd flow inference problem as a self-supervised attributed graph representation learning task and introduce a novel Contrastive Self-learning framework for Spatio-Temporal data (CSST).

Contrastive Learning Graph Representation Learning +2

360-Degree Panorama Generation from Few Unregistered NFoV Images

1 code implementation28 Aug 2023 Jionghao Wang, Ziyu Chen, Jun Ling, Rong Xie, Li Song

360$^\circ$ panoramas are extensively utilized as environmental light sources in computer graphics.

On the use of deep learning for phase recovery

1 code implementation2 Aug 2023 Kaiqiang Wang, Li Song, Chutian Wang, Zhenbo Ren, Guangyuan Zhao, Jiazhen Dou, Jianglei Di, George Barbastathis, Renjie Zhou, Jianlin Zhao, Edmund Y. Lam

Then, we review how DL provides support for PR from the following three stages, namely, pre-processing, in-processing, and post-processing.

Learning Dense UV Completion for Human Mesh Recovery

no code implementations20 Jul 2023 Yanjun Wang, Qingping Sun, Wenjia Wang, Jun Ling, Zhongang Cai, Rong Xie, Li Song

Our method utilizes a dense correspondence map to separate visible human features and completes human features on a structured UV map dense human with an attention-based feature completion module.

Human Mesh Recovery

Boosting Video Object Segmentation via Space-time Correspondence Learning

1 code implementation CVPR 2023 Yurong Zhang, Liulei Li, Wenguan Wang, Rong Xie, Li Song, Wenjun Zhang

Current top-leading solutions for video object segmentation (VOS) typically follow a matching-based regime: for each query frame, the segmentation mask is inferred according to its correspondence to previously processed and the first annotated frames.

Object Segmentation +3

Freestyle Layout-to-Image Synthesis

1 code implementation CVPR 2023 Han Xue, Zhiwu Huang, Qianru Sun, Li Song, Wenjun Zhang

In this work, we explore the freestyle capability of the model, i. e., how far can it generate unseen semantics (e. g., classes, attributes, and styles) onto a given layout, and call the task Freestyle LIS (FLIS).

Image Classification Layout-to-Image Generation +2

Divide and Conquer: a Two-Step Method for High Quality Face De-identification with Model Explainability

no code implementations ICCV 2023 Yunqian Wen, Bo Liu, Jingyi Cao, Rong Xie, Li Song

To address these issues, we propose IDeudemon, which employs a "divide and conquer" strategy to protect identity and preserve utility step by step while maintaining good explainability.


Memories are One-to-Many Mapping Alleviators in Talking Face Generation

no code implementations9 Dec 2022 Anni Tang, Tianyu He, Xu Tan, Jun Ling, Li Song

More specifically, the implicit memory is employed in the audio-to-expression model to capture high-level semantics in the audio-expression shared space, while the explicit memory is employed in the neural-rendering model to help synthesize pixel-level details.

Neural Rendering Talking Face Generation

A Codec Information Assisted Framework for Efficient Compressed Video Super-Resolution

no code implementations15 Oct 2022 Hengsheng Zhang, Xueyi Zou, Jiaming Guo, Youliang Yan, Rong Xie, Li Song

In this paper, considering the characteristics of compressed videos, we propose a Codec Information Assisted Framework (CIAF) to boost and accelerate recurrent VSR models for compressed videos.

Motion Estimation Optical Flow Estimation +1

PTSEFormer: Progressive Temporal-Spatial Enhanced TransFormer Towards Video Object Detection

1 code implementation6 Sep 2022 Han Wang, Jun Tang, Xiaodong Liu, Shanyan Guan, Rong Xie, Li Song

The temporal information is introduced by the temporal feature aggregation model (TFAM), by conducting an attention mechanism between the context frames and the target frame (i. e., the frame to be detected).

object-detection Video Object Detection

StableFace: Analyzing and Improving Motion Stability for Talking Face Generation

no code implementations29 Aug 2022 Jun Ling, Xu Tan, Liyang Chen, Runnan Li, Yuchao Zhang, Sheng Zhao, Li Song

In this paper, we conduct systematic analyses on the motion jittering problem based on a state-of-the-art pipeline that uses 3D face representations to bridge the input audio and output video, and improve the motion stability with a series of effective designs.

Talking Face Generation Video Generation

Intra Encoding Complexity Control with a Time-Cost Model for Versatile Video Coding

no code implementations13 Jun 2022 Yan Huang, Jizheng Xu, Li Zhang, Yan Zhao, Li Song

Inspired by rate control algorithms, we propose a scheme to precisely control the intra encoding complexity of VVC.

Generative Compression for Face Video: A Hybrid Scheme

no code implementations21 Apr 2022 Anni Tang, Yan Huang, Jun Ling, ZhiYu Zhang, Yiwei Zhang, Rong Xie, Li Song

As the latest video coding standard, versatile video coding (VVC) has shown its ability in retaining pixel quality.

Complexity-Oriented Per-shot Video Coding Optimization

no code implementations23 Dec 2021 Hongcheng Zhong, Jun Xu, Chen Zhu, Donghui Feng, Li Song

Current per-shot encoding schemes aim to improve the compression efficiency by shot-level optimization.

A Multi-user Oriented Live Free-viewpoint Video Streaming System Based On View Interpolation

no code implementations20 Dec 2021 Jingchuan Hu, Shuai Guo, Kai Zhou, Yu Dong, Jun Xu, Li Song

As an important application form of immersive multimedia services, free-viewpoint video(FVV) enables users with great immersive experience by strong interaction.

Dual Attention Guided Gaze Target Detection in the Wild

1 code implementation CVPR 2021 Yi Fang, Jiapeng Tang, Wang Shen, Wei Shen, Xiao Gu, Li Song, Guangtao Zhai

In the third stage, we use the generated dual attention as guidance to perform two sub-tasks: (1) identifying whether the gaze target is inside or out of the image; (2) locating the target if inside.

Region-aware Adaptive Instance Normalization for Image Harmonization

1 code implementation CVPR 2021 Jun Ling, Han Xue, Li Song, Rong Xie, Xiao Gu

To ensure the visual style consistency between the foreground and the background, in this paper, we treat image harmonization as a style transfer problem.

Image Harmonization Style Transfer

DP-Image: Differential Privacy for Image Data in Feature Space

no code implementations12 Mar 2021 Hanyu Xue, Bo Liu, Ming Ding, Tianqing Zhu, Dayong Ye, Li Song, Wanlei Zhou

The excessive use of images in social networks, government databases, and industrial applications has posed great privacy risks and raised serious concerns from the public.

IdentityDP: Differential Private Identification Protection for Face Images

no code implementations2 Mar 2021 Yunqian Wen, Li Song, Bo Liu, Ming Ding, Rong Xie

We propose IdentityDP, a face anonymization framework that combines a data-driven deep neural network with a differential privacy (DP) mechanism.

De-identification Disentanglement +2

Personalized and Invertible Face De-Identification by Disentangled Identity Information Manipulation

no code implementations ICCV 2021 Jingyi Cao, Bo Liu, Yunqian Wen, Rong Xie, Li Song

The popularization of intelligent devices including smartphones and surveillance cameras results in more serious privacy issues.


Construct a Sense-Frame Aligned Predicate Lexicon for Chinese AMR Corpus

no code implementations LREC 2020 Li Song, Yuling Dai, Yihuan Liu, Bin Li, Weiguang Qu

The existing lexicons blur senses and frames of predicates, which needs to be refined to meet the tasks like word sense disambiguation and event extraction.

Abstract Meaning Representation Event Extraction +2

Toward Fine-grained Facial Expression Manipulation

1 code implementation ECCV 2020 Jun Ling, Han Xue, Li Song, Shuhui Yang, Rong Xie, Xiao Gu

Previous methods edit an input image under the guidance of a discrete emotion label or absolute condition (e. g., facial action units) to possess the desired expression.

Facial Expression Translation Image-to-Image Translation

Deep Collaborative Filtering with Multi-Aspect Information in Heterogeneous Networks

no code implementations14 Sep 2019 Chuan Shi, Xiaotian Han, Li Song, Xiao Wang, Senzhang Wang, Junping Du, Philip S. Yu

However, the characteristics of users and the properties of items may stem from different aspects, e. g., the brand-aspect and category-aspect of items.

Collaborative Filtering Recommendation Systems

Gated-GAN: Adversarial Gated Networks for Multi-Collection Style Transfer

2 code implementations4 Apr 2019 Xinyuan Chen, Chang Xu, Xiaokang Yang, Li Song, DaCheng Tao

We propose adversarial gated networks (Gated GAN) to transfer multiple styles in a single model.

Decoder Style Transfer

Learning an Inverse Tone Mapping Network with a Generative Adversarial Regularizer

no code implementations20 Apr 2018 Shiyu Ning, Hongteng Xu, Li Song, Rong Xie, Wenjun Zhang

Transferring a low-dynamic-range (LDR) image to a high-dynamic-range (HDR) image, which is the so-called inverse tone mapping (iTM), is an important imaging technique to improve visual effects of imaging devices.

inverse tone mapping Inverse-Tone-Mapping +1

Cannot find the paper you are looking for? You can Submit a new open access paper.