Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks95 from public data
- Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels664
The proposed Q-Align achieves state-of-the-art performance on image quality assessment (IQA), image aesthetic assessment (IAA), as well as video quality assessment (VQA) tasks under the original LMM structure and unify the three tasks into one model, termed the OneAlign.
- Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectives463
The Disentangled Objective Video Quality Evaluator (DOVER) is proposed, the first approach to provide reliable clear-cut quality evaluations from a single aesthetic or technical perspective, and the first approach to provide reliable clear-cut quality evaluations from a single aesthetic or technical perspective.
- TOPIQ: A Top-Down Approach From Semantics to Distortions for Image Quality Assessment423
This work proposes a top-down approach that uses high-level semantics to guide the IQA network to focus on semantically important local distortion regions, named as TOPIQ, and designs a heuristic coarse-to-fine network that leverages multi-scale features and progressively propagates multi-level semantic information to low-level representations in a top-down manner.
- Q-Bench: A Benchmark for General-Purpose Foundation Models on Low-level Vision309
Q-Bench, a holistic benchmark crafted to systematically evaluate potential abilities of MLLMs on three realms: low-level visual perception, low-level visual description, and overall visual quality assessment, confirms that MLLMs possess preliminary low-level visual skills.
- STAR-Net: A SpaTial Attention Residue Network for Scene Text Recognition292
Experimental re-sults show that the STAR-Net can achieve a performance comparable to state-of-the-art methods for scene texts with little distortions, and outperform these methods for scene texts with considerable distortions.
- 239
- Blind Face Restoration via Deep Multi-scale Component Dictionaries230
A deep face dictionary network (termed as DFDNet) to guide the restoration process of degraded observations and can achieve plausible performance in both quantitative and qualitative evaluation, and can generate realistic and promising results on real degraded images without requiring an identity-belonging reference.
- Q-Instruct: Improving Low-Level Visual Abilities for Multi-Modality Foundation Models218
The first dataset consisting of human natural language feedback on low-level vision, and a GPT-participated transformation to convert these feedbacks into a rich set of 200K instruction-response pairs, termed Q-Instruct are collected.
- Progressive Semantic-Aware Style Transformation for Blind Face Restoration206
A new progressive semantic-aware style transformation framework, named PSFR-GAN, for face restoration, which makes full use of the semantic and pixel space information from different scales of input pairs and pretrain a face parsing network which can generate decent parsing maps from real-world LQ face images.
- Real-World Blind Super-Resolution via Feature Matching with Implicit High-Resolution Priors202
This work proposes Feature Matching SR (FeMaSR), which restores realistic HR images in a much more compact feature space by matching distorted LR image features to their distortion-free HR counterparts in the authors' pretrained HR priors, and decoding the matched features to obtain realisticHR images.
- Char-Net: A Character-Aware Neural Network for Distorted Scene Text Recognition183
This work introduces a novel hierarchical attention mechanism (HAM) which consists of a recurrent RoIWarp layer and a character-level attention layer which can handle different types of distortion that are hard, if not impossible, to be modelled by a single global transformation.
- Towards Open-ended Visual Quality Comparison121
This work demonstrates that Co-Instruct not only achieves in average 30% higher accuracy than state-of-the-art open-source LMMs, but also outperforms GPT-4V (its teacher), on both existing related benchmarks and the proposed MICBench.
- Neighbourhood Representative Sampling for Efficient End-to-End Video Quality Assessment99
This work proposes a unified scheme, spatial-temporal grid mini-cube sampling (St-GMS), and the resultant samples are named fragments, a network architecture tailored specifically for fragments that achieves up to 1612× efficiency than the existing state-of-the-art VQA benchmarks.
- DisCoVQA: Temporal Distortion-Content Transformers for Video Quality Assessment86
The proposed Temporal Distortion-Content Transformers for Video Quality Assessment (DisCoVQA) reaches state-of-the-art performance on several VQA benchmarks without any extra pre-training datasets and up to 10% better generalization ability than existing methods.
- 84
- A Novel Gait Pattern Recognition Method Based on LSTM-CNN for Lower Limb Exoskeleton81
A novel gait pattern recognition method based on Long Short-Term Memory (LSTM) and Convolutional Neural Network (CNN) for lower limb exoskeleton can identify the switching gait patterns in time, which shows that it has good real-time performance.
- Towards Explainable In-the-Wild Video Quality Assessment: A Database and a Language-Prompted Approach80
The MaxVQA is proposed, a language-prompted VQA approach that modifies vision-language foundation model CLIP to better capture important quality issues as observed in the authors' analyses.
- HDR Video Reconstruction: A Coarse-to-fine Network and A Real-world Benchmark Dataset78
This work introduces a coarse-to-fine deep learning framework for HDR video reconstruction, which outperforms previous state-of-the-art methods and conducts more sophisticated alignment and temporal fusion in the feature space of the coarse HDR video to produce better reconstruction.
- 75
- LMM-PCQA: Assisting Point Cloud Quality Assessment with LMM55
This study investigates the feasibility of imparting PCQA knowledge to LMMs through text supervision, and transforms quality labels into textual descriptions during the fine-tuning phase, enabling LMMs to derive quality rating logits from 2D projections of point clouds.
- 52
- S$^3$-NeRF: Neural Reflectance Field from Shading and Shadow under a Single Viewpoint48
This paper addresses the "dual problem" of multi-view scene reconstruction in which single-view images captured under different point lights are utilized to learn a neural scene representation, which is robust to depth discontinuities.
- MIMO Is All You Need：A Strong Multi-in-Multi-Out Baseline for Video Prediction44
Surprisingly, empirical studies reveal that a simple MIMO model can outperform the state-of-the-art work with a large margin much more than expected, especially in dealing with long-term error accumulation.
- Exploring the Effectiveness of Video Perceptual Representation in Blind Video Quality Assessment41
Experiments show that the perceptual representation in the HVS is an effective way of predicting subjective temporal quality, and thus TPQI can, for the first time, achieve comparable performance to the spatial quality metric and be even more effective in assessing videos with large temporal variations.
- Semi-supervised Learning for Face Sketch Synthesis in the Wild41
A semi-supervised deep learning architecture is proposed which extends face sketch synthesis to handle face photos in the wild by exploiting additional facePhotos in training by performing patch matching in feature space between the input photo and photos in a small reference set of photo-sketch pairs.
- MiR-193b-3p–ERBB4 axis regulates psoriasis pathogenesis via modulating cellular proliferation and inflammatory-mediator production of keratinocytes40
It is demonstrated that the miR-193b-3p–ERBB4 axis underlies the hyperproliferation and aberrant inflammatory-factor secretion of psoriatic keratinocytes, providing a novel, microRNA-related causal mechanism and a potential therapeutic target in psoriasis.
- Face Sketch Synthesis with Style Transfer Using Pyramid Column Feature39
A novel framework based on deep neural networks for face sketch synthesis from a photo that outperforms other state-of-the-arts methods, and can also generalize well to different test images.
- 32
- 31
- 26
- Deep Face Video Inpainting via UV Mapping22
This paper proposes a two-stage deep learning method for face video inpainting that can significantly outperform methods based merely on 2D information, especially for faces under large pose and expression variations.
- 22
- Semi-supervised Cycle-GAN for face photo-sketch translation in the wild21
A semi-supervised approach with a noise-injection strategy, named Semi-Cycle-GAN (SCG), to tackle face photo-sketch translation problems and shows that SCG achieves competitive performance on public benchmarks and superior results on photos in the wild.
- 21
- 20
- YAP1 facilitates the pathogenesis of psoriasis via modulating keratinocyte proliferation and inflammation19
The findings suggest that YAP1 plays a crucial role in psoriasis pathogenesis through modulating keratinocyte activation and may serve as a novel target for the treatment of psoriasis.
- Towards Robust Text-Prompted Semantic Criterion for In-the-Wild Video Quality Assessment19
An efficient fine-tuning scheme is devised for BVQI-Local that jointly optimizes text prompts and final fusion weights, resulting in state-of-the-art performance and superior generalization ability in comparison to prevalent opinion-driven VQA methods.
- Roles of AIM2 Gene and AIM2 Inflammasome in the Pathogenesis and Treatment of Psoriasis19
AIM2 gene has an essential role in the occurrence and development of Psoriasis, and the inhibitors of AIM2 inflammasome will be new therapeutic targets for psoriasis.
- 19
- 18
- 18
- 17
- 17
- 16
- 16
- 15
- 15
- Effect of the age of onset on epidemiology, clinical features, and comorbidity of geriatric psoriasis14
It is found that age of onset had no effect on disease characteristics or other comorbidities, except for toenail involvement, diabetes, and joint damage.
- T2I-Scorer: Quantitative Evaluation on Text-to-Image Generation via Fine-Tuned Large Multi-Modal Models12
The T2I-Scorer is introduced, a novel two-stage training methodology aimed at fine-tuning LMMs for T2I evaluation that has reached superior accuracy on T2I evaluation than all kinds of existing T2I metrics under zero-shot settings.
- 12
- G-Refine: A General Quality Refiner for Text-to-Image Generation11
G-Refine is introduced, a general image quality refiner designed to enhance low-quality images without compromising the integrity of high-quality ones, and significantly contributes to the practical application of contemporary T2I models, paving the way for their broader adoption.
- 10
- Local Distortion Aware Efficient Transformer Adaptation for Image Quality Assessment10
This paper demonstrates that with proper injection of local distortion features, a larger pretrained and fixed foundation model performs better in IQA tasks, indicating that IQA is not only a low-level problem but also benefits from stronger high-level features drawn from large-scale pretrained models.
- 10
- 10
- Beyond the Dirac Delta: Mitigating Diversity Collapse in Reinforcement Fine-Tuning for Versatile Image Generation9
DRIFT is an innovative framework that systematically incentivizes output diversity throughout the on-policy fine-tuning process, reconciling strong task alignment with high generation diversity to enhance versatility essential for applications that demand diverse candidate generations.
- Continual Learning of No-Reference Image Quality Assessment With Channel Modulation Kernel9
The Channel Modulation Kernel is introduced as a solution to enhance NR-IQA continual learning from two perspectives and dynamically weighting convolutional channels, the base model learns more equally from mixed datasets, enhancing its performance for subsequent incremental tasks.
- 9
- SAFE: Scale Aware Feature Encoder for Scene Text Recognition9
Experimental results demonstrate that S-SAN can achieve state-of-the-art performance without any post-processing, and a simple text recognizer named scale-spatial attention network (S-SAN) that employs SAFE as its feature encoder, and carry out experiments on six public benchmarks.
- 8
- 7
- A Unified Framework for Masked and Mask-Free Face Recognition Via Feature Rectification7
Experiments show that the unified framework, named Face Feature Rectification Network (FFR-Net), can learn a rectified feature space for recognizing both masked and mask-free faces effectively, achieving state-of-the-art results.
- 6
- 6
- 6
- MVQA: Mamba with Unified Sampling for Efficient Video Quality Assessment5
MVQA, a Mambabased model designed for efficient VQA along with a novel Unified Semantic and Distortion Sampling (USDS) approach is presented, enabling a unified sampling strategy that captures both semantic and quality information without additional computational burden.
- 5
- Combining Generative and Geometry Priors for Wide-Angle Portrait Correction5
This work proposes encapsulating the generative face prior as a guided natural manifold to facilitate the correction of facial regions, excelling not only in quantitative measures such as line straightness and shape consistency metrics but also in terms of perceptual visual quality.
- 5
- Costs and long-term outcomes following pulmonary vein isolation for atrial fibrillation in elderly patients using second-generation cryoballoon vs. open-irrigated radiofrequency in China5
CB-2 is associated with shorter procedure time, left atrial dwell time, and length of stay after ablation, as well as lower ERAA, but its costs and fluoroscopy time are greater than the RF group, and the rate of complications and long-term success is similar between two groups.
- 2D Gaussian Splatting with Semantic Alignment for Image Inpainting4
This paper proposes the first image inpainting framework based on 2D Gaussian Splatting, which encodes incomplete images into a continuous field of 2D Gaussian splat coefficients and reconstructs the final image via a differentiable rasterization process and incorporates features from a pretrained DINO model for global semantic consistency.
- 4
- 3
- 3
- 2
- 2
- 2
- 2
- 1
- 1
- 1
- 1
- 1
- –
- –
- –
- –
- –
- –
- –
- –
- –
- Establishment of a culture method for primary human nail matrix cells in serum-free media–
Human primary nails matrix cells could be successfully cultured by using the tissue culture method with serum-free culture media, and the nail matrix cells cultured in vitro can express both K5 and K10.
- A new video surveillance system based on AVS–
This paper analyzed the key technology of current video surveillance systems, compared the performances, prices, and the prospects between the H.264 and AVS codec technologies, and proposed a new video surveillance system based on AVS.
- –
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 2026-10-12. 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.