Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks55 from public data
- Generalized cross entropy loss for training deep neural networks with noisy labels3,376
A theoretically grounded set of noise-robust loss functions that can be seen as a generalization of MAE and CCE are presented and can be readily applied with any existing DNN architecture and algorithm, while yielding good performance in a wide range of noisy label scenarios.
- 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.
- Spatially Adaptive Self-Supervised Learning for Real-World Image Denoising85
A novel perspective to solve the problem of spatially adaptive supervision for real-world sRGB image denoising, taking into account the respective characteristics of flat and textured regions in noisy images, and constructing supervisions for them separately.
- Learning RAW-to-sRGB Mappings with Inaccurately Aligned Supervision66
A joint learning model for image alignment and RAW-to-sRGB mapping is presented and it is shown that a light-weight backbone can achieve better quantitative and qualitative performance on ZRR dataset and SR-RAW datasets.
- Utilization of Iron Tailings Sand as an Environmentally Friendly Alternative to Natural River Sand in High-Strength Concrete: Shrinkage Characterization and Mitigation Strategies65
Theshrinkage reducing agent (SRA) was the most effective shrinkage reducing method for river sand concrete, while for iron tailings sandcrete, super absorbent polymer (SAP) and controlled permeable formwork liner (CPFL) it worked best on autogenous shrinkage and drying shrinkage, respectively.
- 61
- 59
- Rethinking Transformer-Based Blind-Spot Network for Self-Supervised Image Denoising56
A Transformer-based Blind-Spot Network (TBSN) is built that largely extends the receptive field and exhibits favorable performance against state-of-the-art SSID methods, and a knowledge distillation strategy is introduced that distills TBSN into smaller denoisers to improve computational efficiency while maintaining performance.
- Nonnegative matrix factorization with local similarity learning53
A new type of nonnegative matrix factorization method is proposed, which learns local similarity and clustering in a mutually enhancing way, which is more representative in that it better reveals inherent geometric property of the data.
- 47
- NTIRE 2022 Challenge on Super-Resolution and Quality Enhancement of Compressed Video: Dataset, Methods and Results41
This paper reviews the NTIRE 2022 Challenge on Super-Resolution and Quality Enhancement of Compressed Video and proposed the LDV 2.0 dataset, which includes theLDV dataset (240 videos) and 95 additional videos.
- 41
- NTIRE 2022 Challenge on Stereo Image Super-Resolution: Methods and Results35
The 1st NTIRE challenge on stereo image super-resolution (restoration of rich details in a pair of low-resolution stereo images) with a focus on new solutions and results establishes a new benchmark for stereo image SR.
- 35
- 34
- 33
- Benchmark Dataset and Effective Inter-Frame Alignment for Real-World Video Super-Resolution29
A real-world ×4 VSR dataset is built, namely MVSR4×, where low- and high-resolution videos are captured with different focal length lenses of a smartphone, respectively, and an effective alignment method is proposed, namely EAVSR, which takes the proposed multi-layer adaptive spatial transform network to refine the offsets provided by the pre-trained optical flow estimation network.
- 29
- 28
- 28
- 27
- 26
- 24
- 18
- 16
- 14
- 10
- 10
- 9
- 7
- 6
- 4
- 2
- 2
- 2
- 2
- 2
- 1
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
Publication data from OpenAlex; 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.