Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks559 from public data
- Overview of the Versatile Video Coding (VVC) Standard and its Applications1,890
An overview of the novel technical features for new applications and the core compression technologies for achieving significant bit rate reductions in the neighborhood of 50% over its predecessor for equal video quality and 75% over the currently most-used format, the Advanced Video Coding (AVC) standard are provided.
- Graph Convolutional Label Noise Cleaner: Train a Plug-And-Play Action Classifier for Anomaly Detection587
A graph convolutional network is devised that propagates supervisory signals from high-confidence snippets to low-confidence ones and is capable of providing cleaned supervision for action classifiers.
- StructureFlow: Image Inpainting via Structure-Aware Appearance Flow396
A two-stage model which splits the inpainting task into two parts: structure reconstruction and texture generation is proposed, which shows superior performance on multiple publicly available datasets.
- PIRenderer: Controllable Portrait Image Generation via Semantic Neural Rendering300
The proposed Portrait Image Neural Renderer can generate photo-realistic portrait images with accurate movements according to intuitive modifications and is extended to tackle the audio-driven facial reenactment task by extracting sequential motions from audio inputs.
- Metabolic reprogramming and therapeutic resistance in primary and metastatic breast cancer245
By targeting distinct metabolic vulnerabilities at both the primary and metastatic stages, new strategies could improve the efficacy of existing therapies and provide better outcomes for breast cancer patients.
- OctAttention: Octree-Based Large-Scale Contexts Model for Point Cloud Compression216
A multiple-contexts deep learning framework called OctAttention employing the octree structure, a memory-efficient representation for point clouds that obtains a 10%-35% BD-Rate gain on the LiDAR benchmark, and saves 95% coding time compared to the voxel-based baseline.
- ROIMIX: Proposal-Fusion Among Multiple Images for Underwater Object Detection187
This work investigates augmentation policies to simulate overlapping, occluded and blurred objects, and builds a model capable of achieving better generalization, called RoIMix, which characterizes interactions among images.
- A digital construction framework integrating building information modeling and reverse engineering technologies for renovation projects163
A digital construction framework that integrates building information modeling (BIM) and reverse engineering (RE) to improve information utilization in different phases and thus reduce mistakes and reworks in renovation projects during urban renewal is proposed.
- 147
- Intra Prediction and Mode Coding in VVC144
The intra prediction and mode coding of the Versatile Video Coding (VVC) standard is presented and a bitrate saving of 25% on average is reported over H.265/HEVC using an objective metric.
- HQ-ISNet: High-Quality Instance Segmentation for Remote Sensing Imagery133
A novel instance segmentation approach of HR remote sensing imagery based on Cascade Mask R-CNN is proposed, which is called a high-quality instance segmentsation network (HQ-ISNet), which exploits a HR feature pyramid network (HRFPN) to fully utilize multi-level feature maps and maintain HR feature maps for remote sensing images’ instances segmentation.
- Coarse-To-Fine Deep Video Coding with Hyperprior-Guided Mode Prediction129
A coarse-to-fine (C2F) deep video compression framework equipped with the new hyperprior-guided mode prediction methods achieves the state-of-the-art performance on HEVC, UVG and MCL-JCV datasets.
- Transform Coding in the VVC Standard126
The experimental results on VVC reference software show that average 4.5% and 3.6% overall coding gain can be achieved by the VVC transform coding tools for All Intra and Random Access configurations, respectively.
- Neural Texture Extraction and Distribution for Controllable Person Image Synthesis100
A neural texture extraction and distribution operation based on double attention that extracts semantic neural textures from reference feature maps and distributes the extracted neural textures according to the spatial distributions learned from target poses to achieve controllable person image synthesis.
- GPA-Net:No-Reference Point Cloud Quality Assessment With Multi-Task Graph Convolutional Network89
To extract effective features for PCQA, a new graph convolution kernel is proposed, i.e., GPAConv, which attentively captures the perturbation of structure and texture, and a multi-task framework consisting of one main task (quality regression) and two auxiliary tasks (distortion type and degree predictions).
- Overview of the Screen Content Support in VVC: Applications, Coding Tools, and Performance87
This paper describes the screen content support and the five main low-level screen content coding tools in VVC: transform skip residual coding (TSRC), block-based differential pulse-code modulation (BDPCM), intra block copy (IBC), adaptive color transform (ACT), and the palette mode.
- 3DRIED: A High-Resolution 3-D Millimeter-Wave Radar Dataset Dedicated to Imaging and Evaluation86
Experimental results reveal that the dataset can be utilized to verify and evaluate the aforementioned algorithms, demonstrating the benefits of the proposed dataset.
- Different cardiorespiratory effects of indoor air pollution intervention with ionization air purifier: Findings from a randomized, double-blind crossover study among school children in Beijing83
Ionization air purifier could bring substantial respiratory benefits, however, the potential negative effects on HRV need further investigation.
- Deep Spatial Transformation for Pose-Guided Person Image Generation and Animation82
A differentiable global-flow local-attention framework to reassemble the inputs at the feature level and show that this framework can spatially transform the inputs in an efficient manner.
- 80
- VVC Complexity and Software Implementation Analysis80
A complexity analysis of VVC and its VTM reference software is provided, showing that most of the compression gains of V VC over HEVC can be obtained at a small fraction of the resources needed by the VTM encoder under common test conditions.
- 76
- R-PointHop: A Green, Accurate, and Unsupervised Point Cloud Registration Method74
R-PointHop’s model size and training time are an order of magnitude smaller than those of deep learning methods, and its registration errors are smaller, making it a green and accurate solution.
- Metabolic linkages between indoor negative air ions, particulate matter and cardiorespiratory function: A randomized, double-blind crossover study among children71
Investigating the molecular linkages between indoor NAI, decreased PM and the cardiorespiratory effect after purification found increased NAI and decreased PM improved respiratory function by increasing energy production, improving anti-inflammation and anti-oxidation capacity.
- General Video Coding Technology in Responses to the Joint Call for Proposals on Video Compression With Capability Beyond HEVC71
All technology proposed in the responses to the CfP was based on the classic block-based hybrid video coding design, extending it by new elements of partitioning, intra- and inter-picture prediction, prediction signal filtering, transforms, quantization/scaling, entropy coding, and in-loop filtering.
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-14. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.