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
- Max Q.‐H. MengSuggested from co-authorship
Is this you? Claim this profile to confirm or dismiss it.
Works171 from public data
- Cross-Modality Person Re-Identification With Shared-Specific Feature Transfer417
This paper proposes a novel cross-modality shared-specific feature transfer algorithm (termed cm-SSFT) to explore the potential of both the modality-shared information and themodality-specific characteristics to boost the reidentification performance.
- 231
- 192
- Texture analysis for ulcer detection in capsule endoscopy images188
A new idea of curvelet based local binary pattern is proposed as textural features to distinguish ulcer regions from normal regions, which makes full use of Curvelet transformation and local binary patterns.
- 170
- ViTCoD: Vision Transformer Acceleration via Dedicated Algorithm and Accelerator Co-Design167
A dedicated algorithm and accelerator co-design framework dubbed ViTCoD for accelerating ViTs and develops a dedicated accelerator to simultaneously coordinate the aforementioned enforced denser and sparser workloads for boosted hardware utilization, while integrating on-chip encoder and decoder engines to leverage ViTCs algorithm pipeline for much reduced data movements.
- Computer-based detection of bleeding and ulcer in wireless capsule endoscopy images by chromaticity moments160
Experimental results on the present image data of bleeding and ulcer show that it is feasible to exploit the proposed chromaticity moments to detect bleeding and Ulcer for WCE images.
- $\beta$-DARTS: Beta-Decay Regularization for Differentiable Architecture Search155
A simple-but-efficient regularization method, termed as Beta-Decay, is proposed to regularize the DARTS-based NAS searching process and can impose constraints to keep the value and variance of activated architecture parameters from too large.
- Action Segmentation With Joint Self-Supervised Temporal Domain Adaptation146
SelfSupervised Temporal Domain Adaptation (SSTDA), which contains two self-supervised auxiliary tasks (binary and sequential domain prediction) to jointly align cross-domain feature spaces embedded with local and global temporal dynamics, achieving better performance than other Domainadaptation (DA) approaches.
- Kinematic Constrained Bi-directional RRT with Efficient Branch Pruning for robot path planning145
The results of numerical simulations reveal that the proposed Kinematic Constrained Bi-directional Rapidly-exploring Random Tree with Efficient Branch Pruning (KB-RRT*) can achieve better performance compared with the conventional path planning algorithms.
- 136
- 125
- 122
- 120
- 113
- A novel license plate location method based on wavelet transform and EMD analysis110
A robust method based on wavelet transform and empirical mode decomposition (EMD) analysis to search for the location of a license plate in an image to deal with some challenging problems in practice such as illumination changes, complex background and perspective change.
- 108
- GLiT: Neural Architecture Search for Global and Local Image Transformer107
This work introduces the first Neural Architecture Search (NAS) method to find a better transformer architecture for image recognition and introduces a locality module that models the local correlations in images explicitly with fewer computational cost.
- NTIRE 2020 Challenge on Real Image Denoising: Dataset, Methods and Results106
This paper reviews the NTIRE 2020 challenge on real image denoising with focus on the newly introduced dataset, the proposed methods and their results, based on the SIDD benchmark.
- Automatic polyp detection for wireless capsule endoscopy images106
This work attempts to design a computerized scheme aiming for polyp WCE image recognition though polyp in WCE images show great variations in appearance, which integrates advantages of wavelet transform and uniform local binary pattern.
- 101
- AIM 2020 Challenge on Learned Image Signal Processing Pipeline90
This paper reviews the second AIM learned ISP challenge and provides the description of the proposed solutions and results, defining the state-of-the-art for practical image signal processing pipeline modeling.
- MetaCorrection: Domain-aware Meta Loss Correction for Unsupervised Domain Adaptation in Semantic Segmentation87
A MetaCorrection framework is advanced, where a Domain-aware Meta-learning strategy is devised to benefit Loss Correction (DMLC) for UDA semantic segmentation and the proposed DMLC strategy is employed to provide matched and compatible supervision signals for different level features, thereby ensuring deep adaptation.
- 84
- Computer-aided small bowel tumor detection for capsule endoscopy77
A new computer-aided detection scheme using color texture features and classifier ensemble is promising for small bowel tumor detection in capsule endoscopy images.
- 73
- 69
- 67
- Learning Scene Structure Guidance via Cross-Task Knowledge Transfer for Single Depth Super-Resolution62
A cross-task distillation scheme is designed that encourages DSR and DE networks to learn from each other in a teacher-student role-exchanging fashion and achieves superior performance in comparison with other DSR methods.
- 62
- Wireless capsule endoscopy images enhancement via adaptive contrast diffusion54
This work proposes an adaptive contrast diffusion to enhance WCE images with an adaptive choice of the conductance parameter, which plays an important role in diffusion.
- DEAL: An Unsupervised Domain Adaptive Framework for Graph-level Classification52
A novel GNN framework named DEAL is presented by incorporating both source graphs and target graphs, which is featured by two modules, i.e., adversarial perturbation and pseudo-label distilling, which improves the performance of graph classification.
- Learning Cross-Image Object Semantic Relation in Transformer for Few-Shot Fine-Grained Image Classification52
Extensive experiments demonstrate that HelixFormer can effectively enhance the cross-image object semantic relation matching for recognizing fine-grained objects, achieving much better performance over most state-of-the-art methods under 1-shot and 5-shot scenarios.
- Towards Robust Adaptive Object Detection under Noisy Annotations47
This paper represents the first effort to formulate noisy DAOD and proposes a Noise Latent Transferability Exploration (NLTE) framework to address this issue and a thorough evaluation on benchmark DAOD datasets with noisy source annotations validates the effectiveness of NLTE.
- 44
- AIM 2020 Challenge on Real Image Super-Resolution: Methods and Results43
This paper introduces the real image Super-Resolution challenge that was part of the Advances in Image Manipulation (AIM) workshop, held in conjunction with ECCV 2020, and gauges the state-of-the-art approaches for real image SR in terms of PSNR and SSIM.
- Towards Bidirectional Arbitrary Image Rescaling: Joint Optimization and Cycle Idempotence42
The proposed method is the first to treat arbitrary rescaling, both upscaling and downscaling, as one unified process, and is able to learn up Scaling and Downscaling simultaneously and achieve bidirectional arbitrary image rescaling.
- 42
- 40
- UDC 2020 Challenge on Image Restoration of Under-Display Camera: Methods and Results38
The results in the paper are state-of-the-art restoration performance of Under-Display Camera Restoration.
- 37
- BN-NAS: Neural Architecture Search with Batch Normalization37
BN-NAS can significantly reduce the time required by model training and evaluation in NAS and a BN-based indicator for predicting subnet performance at a very early training stage is proposed for fast evaluation.
- 36
- 33
- 33
- 31
- 29
- 28
- 27
- 27
- 27
- 27
- 26
- 24
- 24
- 23
- 3D Multi-frame Fusion for Video Stabilization21
A novel framework for video stabilization that integrates 3D multi-frame fusion through volume rendering, and introduces the Adaptive Ray Range (ARR) module to integrate depth priors, adaptively defining the sampling range for the projection process.
- Rethinking Cross-Domain Pedestrian Detection: A Background-Focused Distribution Alignment Framework for Instance-Free One-Stage Detectors21
This paper proposes a novel framework, namely, background-focused distribution alignment (BFDA), to train domain adaptive one-stage pedestrian detectors that first decouples the background features from the whole image feature maps and then aligns them via a novel long-short-range discriminator.
- BridgeNet: Comprehensive and Effective Feature Interactions via Bridge Feature for Multi-Task Dense Predictions20
This work proposes a novel BridgeNet framework, which extracts comprehensive and discriminative intermediate Bridge Features, and conducts interactions based on them, and is the first work considering the completeness and quality of feature participants in cross-task interactions.
- 20
- 20
- 19
- 18
- 18
- 17
- 17
- 15
- 15
- 15
- 14
- 14
- 14
- 12
- Efficient Joint-Dimensional Search with Solution Space Regularization for Real-Time Semantic Segmentation12
A novel Solution Space Regularization (SSR) loss is first proposed to effectively encourage the supernet to converge to its discrete one and a new Hierarchical and Progressive Solution Space Shrinking method is presented to further achieve high efficiency of searching.
- 12
- 12
- 12
- 12
- 11
- 11
- 10
- 10
- 10
- 10
- 9
- 9
- 9
- 9
- 8
- 8
- 8
- 8
- 8
- 8
- 8
- 8
- Efficient Architecture Search via Bi-Level Data Pruning7
This work introduces a progressive bi-level data pruning strategy that utilizes supernet prediction dynamics as the metric to gradually prune unsuitable samples for DARTS during the search, and proposes a novel Bi-level Data Pruning (BDP) paradigm that targets the weights and architecture levels of DARTS to enhance efficiency from a data perspective.
- 7
- 7
- 7
- 7
- 7
- 6
- 6
- 6
- 5
- 5
- 5
- 5
- 5
- 5
- 5
- 5
- 5
- 5
- 5
- 4
- Instance-aware Model Ensemble With Distillation For Unsupervised Domain Adaptation4
A novel framework, namely Instance aware Model Ensemble With Distillation, IMED, which fuses multiple UDA component models adaptively according to different instances and distills these components into a small model is proposed.
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- 4
- Rethinking Pseudo-Label-Based Unsupervised Person Re-ID with Hierarchical Prototype-based Graph3
This work proposes a novel hierarchical prototype-based graph network (HPG-Net) for unsupervised person Re-ID that outperforms state-of-the-art (SOTA) works and achieves promising performance on an occluded dataset.
- 3
- 3
- 3
- 3
- 3
- 3
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 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.