Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileAcademic lineage
Possible advisorsa guess from early papers, not confirmed
- Suggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works276 from public data
- Image and Video Compression With Neural Networks: A Review459
The evolution and development of neural network-based compression methodologies are introduced for images and video respectively and the joint compression on semantic and visual information is tentatively explored to formulate high efficiency signal representation structure for both human vision and machine vision.
- 192
- 186
- 185
- Diffusion-Based 3D Human Pose Estimation with Multi-Hypothesis Aggregation180
A novel Diffusion-based 3D Pose estimation method with Joint-wise reProjection-based Multi-hypothesis Aggregation (JPMA) proposed for probabilistic 3D human pose estimation and to assemble multiple hypotheses generated by D3DP into a single 3D pose for practical use.
- 117
- 117
- 109
- 106
- 104
- 100
- 86
- NTIRE 2024 Challenge on Image Super-Resolution (×4): Methods and Results83
This paper reviews the NTIRE 2024 challenge on image super-resolution (×4), highlighting the solutions proposed and the outcomes obtained, and offers a comprehensive overview of current trends in this field.
- Structure-CLIP: Towards Scene Graph Knowledge to Enhance Multi-Modal Structured Representations78
This paper presents an end-to-end framework Structure-CLIP, which integrates Scene Graph Knowledge (SGK) to enhance multi-modal structured representations and uses scene graphs to guide the construction of semantic negative examples, which results in an increased emphasis on learning structured representations.
- 78
- Towards Analysis-Friendly Face Representation With Scalable Feature and Texture Compression77
This work investigates the integration of feature and texture compression and shows that a universal and collaborative visual information representation can be achieved in a hierarchical way in a scalable coding framework.
- STRPM: A Spatiotemporal Residual Predictive Model for High-Resolution Video Prediction75
A Spatiotemporal Residual Predictive Model (STRPM) which can supervise the spatial encoder and temporal encoder to extract different features in the spatial domain and the temporal domain, respectively and is trained using generative adversarial networks with a learned perceptual loss to improve the perceptual quality of the predictions.
- 75
- No-reference quality assessment of deblocked images75
Experimental results conducted on the DBID database demonstrate that the proposed metric is effective in evaluating the quality of deblocked images, and it significantly outperforms the existing metrics.
- 74
- 68
- Predictive Generalized Graph Fourier Transform for Attribute Compression of Dynamic Point Clouds65
This work proposes a complete compression framework for attributes of 3D dynamic point clouds, focusing on optimal inter-coding and refined motion estimation via efficient registration prior to inter-prediction, which searches the temporal correspondence between adjacent frames of irregular point clouds.
- 65
- 65
- 65
- Video anomaly detection and localization using motion-field shape description and homogeneity testing59
A method to detect anomalies over time and space by judging whether the similarities between the testing sample and the retrieved K-NN samples follow the pattern distribution of homogeneous intra-class similarities, which is unsupervised one-class learning requiring no clustering nor prior assumption is proposed.
- 59
- 58
- Universal Adversarial Perturbations Generative Network For Speaker Recognition57
This paper demonstrated the existence of the universal adversarial perturbations (UAPs) for the speaker recognition systems, and proposed a generative network to learn the mapping from the low-dimensional normal distribution to the UAPs subspace, then synthesize the Uaps to perturbe any input signals to spoof the well-trained speaker recognition model with high probability.
- 57
- 56
- 56
- 56
- 51
- 50
- 48
- 46
- 46
- 44
- 44
- 43
- 43
- Towards Fine-Grained Human Pose Transfer With Detail Replenishing Network42
This work develops a more challenging yet practical HPT setting, termed as Fine-grained Human Pose Transfer (FHPT), with a higher focus on semantic fidelity and detail replenishment, and builds up a complete suite of fine- grained evaluation protocols to address the challenges of FHPT in a comprehensive manner.
- 42
- 41
- 40
- 40
- 40
- 38
- Direct Speech-to-Image Translation37
Experimental results on both synthesized and real data show that the proposed method is effective to translate the raw speech signals into images without the middle text representation.
- Scalable Facial Image Compression with Deep Feature Reconstruction36
A scalable image compression scheme, including the base layer for feature representation and enhancement layer for texture representation, which can feasibly inherit the advantages of both compress- then-analyze and analyze-then-compress schemes in surveillance applications.
- 35
- 35
- Blind quality index for tone-mapped images based on luminance partition35
A blind quality index based on luminance partition for tone-mapped images is presented and is shown to outperform those state-of-the-art metrics according to extensive experiments conducted on two publicly available databases.
- Visual attention analysis and prediction on human faces35
This work proposes to build visual attention models specifically for face images through combining low-level saliency calculated by traditional saliency models with high-level facial features, and efficiency of the built models is verified on the VAF database.
- 34
- User-Generated Video Quality Assessment: A Subjective and Objective Study34
A UGC video quality assessment (VQA) database is constructed and an objective quality assessment algorithm is developed that automatically evaluates the quality of the transcoded videos based on the corrupted reference, which is in accordance with the application scenarios of U GC video sharing in the hosting platforms.
- Nonlocal Edge-Directed Interpolation34
The new image interpolation approach preserves spatial coherence of the interpolated images better than the existing methods and it outperforms the other methods in terms of objective and subjective image quality.
- 31
- 30
- 30
- 30
- 30
- 29
- 29
- 29
- 29
- 27
- 27
- 27
- 26
- 26
- 26
- 25
- 24
- 22
- 22
- 22
- 22
- 21
- 21
- 21
- 21
- 21
- 21
- 19
- 19
- 18
- 18
- 18
- 18
- 17
- 17
- 17
- 16
- 16
- 16
- 16
- 16
- 15
- 14
- 14
- 14
- 13
- 13
- 13
- 12
- 12
- 12
- 11
- 11
- 11
- 11
- 11
- 10
- 10
- 10
- 10
- 10
- 10
- 10
- 10
- 10
- 9
- 9
- 9
- 9
- 9
- 9
- 9
- 8
- 8
- 8
- 8
- 8
- 8
- 8
- 8
- 8
- 7
- 7
- 7
- 7
- 7
- 7
- 7
- 7
- 6
- 6
- 6
- 6
- 6
- 6
- 6
- A Data-centric Approach to Unsupervised Texture Segmentation Using Principle Representative Patterns6
- 6
- 6
- 5
- 5
- 5
- 5
- 5
- 5
- 5
- 5
- 5
- 5
- 5
- 5
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- 3
- Remote Sensing Image Denoising with Iterative Adaptive Wiener Filter3
A novel Wiener filter strategy is proposed, which takes advantage of image self-similarity to estimate filter parameters adaptively and can significantly improve both the subjective and the objective quality of noisy remote sensing images.
- 3
- 3
- 3
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 1
- Joint Structure-Texture Scan-Order for Point Cloud Attribute Compression Using Affine Transformation1
- MoRLACS: A Monocular RGBD-based Locomotion Approach for CAVE Systems1
MoRLACS, a novel locomotion approach for CAVE systems that leverages a single RGBD camera, integrates small-scale physical walking with controller-based large-scale exploration through a tailored guidance method and supports extended interaction in larger virtual environments.
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- Fidelity or Quality? A Region-Aware Framework for Enhanced Image Decoding via Hybrid Neural Networks1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
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 2026-10-13. 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.