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.
Works321 from public data
- 496
- PHASEN: A Phase-and-Harmonics-Aware Speech Enhancement Network412
This paper proposes a phase-and-harmonics-aware deep neural network (DNN), named PHASEN, which has the ability to handle detailed phase patterns and to utilize harmonic patterns, and outperforms previous methods by a large margin on four metrics.
- 339
- 278
- SPM-Tracker: Series-Parallel Matching for Real-Time Visual Object Tracking263
The greatest challenge facing visual object tracking is the simultaneous requirements on robustness and discrimination power, and a SiamFC-based tracker, named SPM-Tracker, is proposed, to address the two requirements in two separate matching stages.
- Deep Fourier-Based Exposure Correction Network with Spatial-Frequency Interaction247
A deep Fourier-based Exposure Correction Network (FECNet) consisting of an amplitude subnetwork and a phase sub-network to progressively reconstruct the representation of lightness and structure components is proposed.
- Dual-camera design for coded aperture snapshot spectral imaging209
A beam splitter is placed in front of the objective lens of CASSI, which allows the same scene to be simultaneously captured by a grayscale camera, which greatly eases the reconstruction problem and yields high-quality 3D spectral data.
- 204
- Tracking by Instance Detection: A Meta-Learning Approach193
This work proposes a principled three-step approach to build a high-performance tracker based on two modern detectors RetinaNet and FCOS, and finds that model-agnostic meta-learning (MAML) offers a strategy to initialize the detector that satisfies the authors' needs.
- Camera Lens Super-Resolution170
This paper investigates SR from the perspective of camera lenses, named as CameraSR, which aims to alleviate the intrinsic tradeoff between resolution (R) and field-of-view (V) in realistic imaging systems and quantitatively analyzes the performance of commonly-used synthetic degradation models.
- 160
- 159
- 155
- NTIRE 2018 Challenge on Spectral Reconstruction from RGB Images135
This paper reviews the first challenge on spectral image reconstruction from RGB images, i.e., the recovery of whole-scene hyperspectral (HS) information from a 3-channel RGB image.
- Progressive Retinex125
A novel progressive Retinex framework is presented, in which illumination and noise of low-light image are perceived in a mutually reinforced manner, leading to noise reduction low- light enhancement results.
- GET: Group Event Transformer for Event-Based Vision117
A novel Group-based vision Transformer backbone for Event-based vision, called Group Event Transformer (GET), which decouples temporal-polarity information from spatial information throughout the feature extraction process, and demonstrates that GET outperforms other state-of-the-art methods.
- 110
- Deep Boosting for Image Denoising110
A novel deep boosting framework (DBF) for denoising, which integrates several convolutional networks in a feed-forward fashion, and introduces the concept of dense connection that overcomes the vanishing of gradients during training.
- 107
- 105
- 105
- 103
- Neural Degradation Representation Learning for All-in-One Image Restoration98
This paper proposes to learn a neural degradation representation (NDR) that captures the underlying characteristics of various degradations that adaptively decomposes different types of degradations, similar to a neural dictionary that represents basic degradation components.
- Recurrent Dynamic Embedding for Video Object Segmentation91
This paper proposes a Recurrent Dynamic Embedding (RDE) to build a memory bank of constant size, explicitly generated and update by the proposed Spatio-temporal Aggregation Module (SAM), which exploits the cue of historical information.
- Towards Generalizable Tumor Synthesis88
It is ascertained that generative AI models, e.g., Diffusion Models, can create realistic tumors generalized to a range of organs even when trained on a limited number of tumor examples from only one organ, and it is shown that AI models trained on these synthetic tumors can be generalized to detect and segment real tumors from CT volumes.
- Unambiguous 3D measurement from speckle-embedded fringe84
A novel phase-shifting method for fast, accurate, and unambiguous 3D shape measurement by embedding a speckle-like signal in three sinusoidal fringe patterns to eliminate the phase ambiguity, but without reducing the fringe amplitude or frequency.
- 79
- 78
- Scalable volumetric imaging for ultrahigh-speed brain mapping at synaptic resolution76
A new light-sheet microscopy method for fast, large-scale volumetric imaging that achieves high-speed 3D image acquisition of an entire mouse brain within 2 hours, at a resolution capable of resolving synaptic spines is described.
- High-speed structured light based 3D scanning using an event camera74
This paper presents an event-based structured light system for high-speed 3D scanning, which is composed of an event camera (CeleX-V) and a high- speed digital light projector (TI-DLP6500), triggered by blinking a single pseudo-random pattern by controlling the projector.
- Temporal Hierarchical Attention at Category- and Item-Level for Micro-Video Click-Through Prediction74
This paper investigates how to model user's historical behaviors so as to predict the user's click-through of micro-videos, and proposes a Temporal Hierarchical Attention at Category- and Item-Level (THACIL) network for user behavior modeling.
- 73
- 72
- 71
- 71
- Dual Path Interaction Network for Video Moment Localization70
A unified top-down and bottom-up approach to moment localization called Dual Path Interaction Network (DPIN), where the alignment and discrimination information are closely connected to jointly make the prediction.
- 70
- 70
- 66
- Training Spiking Neural Networks with Accumulated Spiking Flow65
This paper proposes a new backpropagation method for SNNs based on the accumulated spiking flow (ASF), i.e. ASF-BP, and presents an adaptive linear estimation model to approach the dynamic characteristics of spiking neurons statistically.
- Learning and Fusing Multiple User Interest Representations for Micro-Video and Movie Recommendations65
- 63
- 61
- 61
- 61
- Photon-Efficient 3D Imaging with A Non-local Neural Network59
A non-local neural network trained on simulated data that achieves decent reconstruction fidelity even under photon counts (and signal-to-background ratio, SBR) as low as 1 photon/pixel (and 0.01 SBR), which significantly surpasses the state-of-the-art.
- Deep Residual Attention Network for Spectral Image Super-Resolution59
A novel deep residual attention network is proposed for the spatial super-resolution (SR) of spectral images and is one of the winning solutions in the PIRM 2018 Spectral Super-resolution Challenge.
- 59
- 57
- 56
- 54
- 54
- 54
- Space-Time Video Super-Resolution Using Temporal Profiles54
A novel space-time video super-resolution method, which aims to recover a high-frame-rate and high-resolution video from its low- frame- rate and low-resolution observation, followed by a refining module for artifacts alleviation and detail enhancement, which does not require any explicit or implicit motion estimation.
- 53
- Exposure-Consistency Representation Learning for Exposure Correction53
A proposed ECP module to consistently learn the representation of both underexposure and overexposure in the feature space and an Exposure-Consistency Constraining strategy that augments the various local region exposures and then constrains the feature representation change between the exposure augmented image and the original one are developed.
- 53
- NTIRE 2023 Challenge on Light Field Image Super-Resolution: Dataset, Methods and Results52
The first NTIRE challenge on light field (LF) image super-resolution (SR), which aims at super-resolving LF images under the standard bicubic degradation with a magnification factor of 4, develops a new LF dataset called NTIRE-2023 for validation and test, and provides a toolbox called BasicLFSR to facilitate model development.
- 52
- 52
- 3D-Printing Damage-Tolerant Architected Metallic Materials with Shape Recoverability via Special Deformation Design of Constituent Material51
A novel constituent material deformation design strategy has been skillfully proposed, where the low load resistance of yielded regions of the architecture can be effectively compensated by the significant self-strengthening behavior of constituent material, thus avoiding the formation of localized deformation bands and collapse of strength.
- 48
- Attribute Artifacts Removal for Geometry-Based Point Cloud Compression48
This paper proposes a Multi-Scale Graph Attention Network (MS-GAT) to remove the artifacts of point cloud attributes compressed by G-PCC, and is the first attribute artifacts removal method for G- PCC.
- Stimulating Diffusion Model for Image Denoising via Adaptive Embedding and Ensembling45
This work presents a novel strategy called the Diffusion Model for Image Denoising (DMID) by understanding and rethinking the diffusion model from a denoising perspective, which achieves state-of-the-art performance on both distortion-based and perception-based metrics, for both Gaussian and real-world image denoising.
- MuLUT: Cooperating Multiple Look-Up Tables for Efficient Image Super-Resolution45
MuLUT achieves a significant improvement over SR-LUT, up to 1.1dB PSNR, while preserving its efficiency, and is extended to address demosaicing of Bayer-patterned images, surpassing SR-LUT on two benchmarks by a large margin.
- 45
- 44
- 43
- 43
- 41
- 41
- BERT4SessRec41
This paper describes the solution for the Content-Based Video Relevance Prediction (CBVRP) challenge, where the task is to predict user click-through behavior on new TV series or new movies according to the user's historical behavior and uses the Bidirectional Encoder Representations from Transformer methodology.
- CNN-Based DCT-Like Transform for Image Compression40
This paper presents a block transform for image compression, where the transform is inspired by discrete cosine transform (DCT) but achieved by training convolutional neural network (CNN) models to achieve the overall rate-distortion optimization.
- Can SAM Boost Video Super-Resolution?39
This paper investigates a more robust and semantic-aware prior for enhanced VSR by utilizing the Segment Anything Model (SAM), a powerful foundational model that is less susceptible to image degradation.
- aiWave: Volumetric Image Compression With 3-D Trained Affine Wavelet-Like Transform39
A 3-D trained wavelet-like transform is designed to enable signal-dependent and non-separable transform and an affine wavelet basis is introduced to capture the various local correlations in different regions of volumetric images to enable an adaptive compression scheme for various datasets.
- 36
- NTIRE 2021 Challenge on Video Super-Resolution36
This paper presents evaluation results from two competition tracks as well as the proposed solutions to the NTIRE 2021 Challenge on Video Super-Resolution, and develops conventional video SR methods focusing on the restoration quality.
- 35
- Why is the Winner the Best?34
A multicenter study with all 80 benchmarking competitions that were conducted in the scope of IEEE ISBI 2021 and MICCAI 2021 revealed common characteristics of winning solutions: the reflection of the metrics in the method design and the focus on analyzing and handling failure cases.
- 34
- 34
- EDPN: Enhanced Deep Pyramid Network for Blurry Image Restoration34
Experimental results demonstrate that the proposed Enhanced Deep Pyramid Network (EDPN) significantly outperforms existing solutions for blurry image super-resolution and blurry image deblocking.
- 33
- 32
- A Dive into SAM Prior in Image Restoration32
This paper uses the prior knowledge of the state-of-the-art segment anything model (SAM) to boost the performance of existing IR networks in an parameter-efficient tuning manner and proposes a lightweight SAM prior tuning (SPT) unit, which allows us to effectively integrate semantic priors into existingIR networks, resulting in significant improvements in restoration quality.
- Spectral-depth imaging with deep learning based reconstruction30
This is the first attempt to capture 5D information (3D space + 1D spectrum +1D time) with a miniaturized apparatus and without active illumination.
- 30
- 29
- 28
- 28
- 28
- 28
- 27
- 27
- 27
- 26
- 26
- 25
- 25
- 25
- 25
- 25
- 24
- 24
- 24
- 24
- 24
- 23
- 23
- 23
- 23
- 22
- 22
- 22
- 21
- 21
- 21
- TAR3D: Creating High-Quality 3D Assets Via Next-Part Prediction20
TAR3D is presented, a novel framework that consists of a 3D-aware Vector Quantized-Variational AutoEncoder and a Generative Pre-trained Transformer to generate high-quality 3D assets to migrate the multimodal unification and promising learning capabilities of the next-token prediction paradigm to conditional 3D object generation.
- 20
- 20
- Appearance Prompt Vision Transformer for Connectome Reconstruction19
A coherent and unified Appearance Prompt Vision Transformer is proposed to integrate affinity and metric learning to exploit the complementarity by learning long-range spatial dependencies and achieves consistent improvements with huge flexibility under the same post-processing strategy.
- 18
- 18
- 18
- 18
- 18
- 18
- 18
- 17
- 17
- 17
- 17
- 17
- 17
- 17
- 17
- 16
- 16
- 16
- 16
- 16
- 16
- 16
- 16
- 16
- 16
- 15
- 15
- 15
- 15
- 14
- 14
- 14
- 14
- 13
- 13
- 13
- 13
- 12
- 12
- 12
- 12
- 12
- 12
- 12
- 11
- 11
- 11
- 11
- 11
- Image Aesthetics Assessment Via Learnable Queries10
The IAA-LQ approach adapts learnable queries to extract aesthetic features from pre-trained image features obtained from a frozen image encoder, beating the best state-of-the-art method by 2.2% and 2.1% in terms of SRCC and PLCC, respectively.
- 10
- 10
- 10
- 10
- 10
- 9
- 9
- 9
- 9
- 9
- 9
- 9
- 9
- 9
- 9
- 9
- 9
- 8
- 8
- 8
- Unraveling Motion Uncertainty for Local Motion Deblurring8
This work proposes a novel method named Motion-Uncertainty-Guided Network (MUGNet), which harnesses a probabilistic representational model to explicitly address the intricacies stemming from motion uncertainties and demonstrates the superiority of the MUGNet with extensive experiments.
- 8
- 8
- 8
- 8
- 7
- 7
- 7
- 7
- 7
- 7
- 7
- 7
- 7
- 7
- 7
- 7
- 6
- 6
- 6
- 6
- 6
- 6
- 6
- 6
- 6
- 6
- 6
- 6
- 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
- MIPI 2023 Challenge on RGBW Fusion: Methods and Results3
This paper summarizes and reviews the RGBW Joint Fusion and Denoise track on MIPI 2023 and describes the models developed in this challenge, including PSNR, SSIM, LPIPS, and KLD.
- 3
- 3
- 3
- 2
- 2
- 2
- 2
- 2
- Test-Time Adaptation via Style and Structure Guidance for Histological Image Registration2
This paper proposes a novel test-time adaptation method for histological image registration, aiming to improve the generalization ability of learning-based methods, and introduces a smoothing strategy to leverage historical models for better generalization.
- 2
- 2
- 2
- 2
- 2
- 1
- 1
- 1
- 1
- 1
- 1
- Multi-modal Learnable Queries for Image Aesthetics Assessment1
This paper proposes MMLQ, which utilizes multi-modal learnable queries to extract aesthetics-related features from multi-modal pre-trained features, and achieves new state-of-the-art performance on multimodal IAA.
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- Spatial synaptic regularization stabilizes learning across biological and artificial neural networks–
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
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.