Search Results for author:
Found 68 papers, 40 papers with code
UP-Person: Unified Parameter-Efficient Transfer Learning for Text-based Person Retrieval
Text-based Person Retrieval (TPR) as a multi-modal task, which aims to retrieve the target person from a pool of candidate images given a text description, has recently garnered considerable attention due to the progress of contrastive visual-language pre-trained model.
VISTA: Unsupervised 2D Temporal Dependency Representations for Time Series Anomaly Detection
Time Series Anomaly Detection (TSAD) is essential for uncovering rare and potentially harmful events in unlabeled time series data.
Decoupling Appearance Variations with 3D Consistent Features in Gaussian Splatting
We validate our method on several appearance-variant scenes, and demonstrate that it achieves state-of-the-art rendering quality with minimal training time and memory usage, without compromising rendering speeds.
DiffStereo: High-Frequency Aware Diffusion Model for Stereo Image Restoration
Specifically, DiffStereo first learns latent high-frequency representations (LHFR) of HQ images.
CATCH: Complementary Adaptive Token-level Contrastive Decoding to Mitigate Hallucinations in LVLMs
Large Vision-Language Model (LVLM) systems have demonstrated impressive vision-language reasoning capabilities but suffer from pervasive and severe hallucination issues, posing significant risks in critical domains such as healthcare and autonomous systems.
Efficient Feature Aggregation and Scale-Aware Regression for Monocular 3D Object Detection
Specifically, EH-FAM employs multi-head attention with a global receptive field to extract semantic features for small-scale objects and leverages lightweight convolutional modules to efficiently aggregate visual features across different scales.
Agent-Guided Gaze Estimation Network by Two-Eye Asymmetry Exploration
By exploring the appearance asymmetry and the consequent feature space asymmetry, we devise a main branch and two agent regression tasks.
Ranked #1 on
Gaze Estimation
on EYEDIAP
MonoDGP: Monocular 3D Object Detection with Decoupled-Query and Geometry-Error Priors
However, due to depth errors originating from the object's visual surface, the height of the bounding box often fails to represent the actual projected central height, which undermines the effectiveness of geometric depth.
Ranked #3 on
Monocular 3D Object Detection
on KITTI Cars Hard
ConsisSR: Delving Deep into Consistency in Diffusion-based Image Super-Resolution
To address this challenge, we introduce ConsisSR to handle both semantic and pixel-level consistency.
CONSULT: Contrastive Self-Supervised Learning for Few-shot Tumor Detection
The second stage of CONSULT uses PatchCore for conventional feature extraction via the fine-tuned weights from the first stage.
RICASSO: Reinforced Imbalance Learning with Class-Aware Self-Supervised Outliers Exposure
In contrast, our research shows that data mixing, a potent augmentation technique for long-tailed recognition, can generate pseudo-OOD data that exhibit the features of both in-distribution (ID) data and OOD data.
Alignment is All You Need: A Training-free Augmentation Strategy for Pose-guided Video Generation
Character animation is a transformative field in computer graphics and vision, enabling dynamic and realistic video animations from static images.
FFAA: Multimodal Large Language Model based Explainable Open-World Face Forgery Analysis Assistant
The rapid advancement of deepfake technologies has sparked widespread public concern, particularly as face forgery poses a serious threat to public information security.
Pose Magic: Efficient and Temporally Consistent Human Pose Estimation with a Hybrid Mamba-GCN Network
This architecture introduces local enhancement with GCN by capturing relationships between neighboring joints, thus producing new representations to complement Mamba's outputs.
GaussianSR: High Fidelity 2D Gaussian Splatting for Arbitrary-Scale Image Super-Resolution
Although these approaches have shown promising results, their performance is constrained by the limited representation ability of discrete latent codes in the encoded features.
LLM-Empowered State Representation for Reinforcement Learning
Conventional state representations in reinforcement learning often omit critical task-related details, presenting a significant challenge for value networks in establishing accurate mappings from states to task rewards.
Perspective+ Unet: Enhancing Segmentation with Bi-Path Fusion and Efficient Non-Local Attention for Superior Receptive Fields
Although Convolutional Neural Networks (CNNs) and non-local attention methods have achieved notable success in medical image segmentation, they either struggle to capture long-range spatial dependencies due to their reliance on local features, or face significant computational and feature integration challenges when attempting to address this issue with global attention mechanisms.
BDC-Occ: Binarized Deep Convolution Unit For Binarized Occupancy Network
To bridge these gaps, we propose a novel binarized deep convolution (BDC) unit that effectively enhances performance while increasing the number of binarized convolutional layers.
Bilateral Event Mining and Complementary for Event Stream Super-Resolution
In this paper, we propose a bilateral event mining and complementary network (BMCNet) to fully leverage the potential of each event and capture the shared information to complement each other simultaneously.
Motion-aware Latent Diffusion Models for Video Frame Interpolation
With the advancement of AIGC, video frame interpolation (VFI) has become a crucial component in existing video generation frameworks, attracting widespread research interest.
OccGaussian: 3D Gaussian Splatting for Occluded Human Rendering
OccGaussian initializes 3D Gaussian distributions in the canonical space, and we perform occlusion feature query at occluded regions, the aggregated pixel-align feature is extracted to compensate for the missing information.
Efficient Heatmap-Guided 6-Dof Grasp Detection in Cluttered Scenes
Specifically, Gaussian encoding and the grid-based strategy are applied to predict grasp heatmaps as guidance to aggregate local points into graspable regions and provide global semantic information.
Ranked #4 on
Robotic Grasping
on GraspNet-1Billion
Residual Dense Swin Transformer for Continuous Depth-Independent Ultrasound Imaging
Ultrasound imaging is crucial for evaluating organ morphology and function, yet depth adjustment can degrade image quality and field-of-view, presenting a depth-dependent dilemma.
Low-Trace Adaptation of Zero-shot Self-supervised Blind Image Denoising
Deep learning-based denoiser has been the focus of recent development on image denoising.
VmambaIR: Visual State Space Model for Image Restoration
To address these challenges, we propose VmambaIR, which introduces State Space Models (SSMs) with linear complexity into comprehensive image restoration tasks.
VastGaussian: Vast 3D Gaussians for Large Scene Reconstruction
Existing NeRF-based methods for large scene reconstruction often have limitations in visual quality and rendering speed.
DiffVein: A Unified Diffusion Network for Finger Vein Segmentation and Authentication
To fill this gap, we introduce DiffVein, a unified diffusion model-based framework which simultaneously addresses vein segmentation and authentication tasks.
LLMRA: Multi-modal Large Language Model based Restoration Assistant
By employing a pretrained multi-modal large language model and a vision language model, we generate text descriptions and encode them as context embedding with degradation information for the degraded image.
Binding-Adaptive Diffusion Models for Structure-Based Drug Design
Then the selected protein-ligand subcomplex is processed with SE(3)-equivariant neural networks, and transmitted back to each atom of the complex for augmenting the target-aware 3D molecule diffusion generation with binding interaction information.
Diffusion-based Pose Refinement and Muti-hypothesis Generation for 3D Human Pose Estimaiton
To address these two challenges, we propose a diffusion-based refinement framework called DRPose, which refines the output of deterministic models by reverse diffusion and achieves more suitable multi-hypothesis prediction for the current pose benchmark by multi-step refinement with multiple noises.
RTMO: Towards High-Performance One-Stage Real-Time Multi-Person Pose Estimation
Real-time multi-person pose estimation presents significant challenges in balancing speed and precision.
Ranked #1 on
Multi-Person Pose Estimation
on CrowdPose
(using extra training data)
DSR-Diff: Depth Map Super-Resolution with Diffusion Model
Color-guided depth map super-resolution (CDSR) improve the spatial resolution of a low-quality depth map with the corresponding high-quality color map, benefiting various applications such as 3D reconstruction, virtual reality, and augmented reality.
LAVSS: Location-Guided Audio-Visual Spatial Audio Separation
LAVSS is inspired by the correlation between spatial audio and visual location.
CLIP-based Synergistic Knowledge Transfer for Text-based Person Retrieval
Text-based Person Retrieval (TPR) aims to retrieve the target person images given a textual query.
Speech2Lip: High-fidelity Speech to Lip Generation by Learning from a Short Video
Therefore, directly learning a mapping function from speech to the entire head image is prone to ambiguity, particularly when using a short video for training.
DiffI2I: Efficient Diffusion Model for Image-to-Image Translation
Compared to traditional DMs, the compact IPR enables DiffI2I to obtain more accurate outcomes and employ a lighter denoising network and fewer iterations.
Dynamic Low-Rank Instance Adaptation for Universal Neural Image Compression
We thus introduce a dynamic gating network on top of the low-rank adaptation method, in order to decide which decoder layer should employ adaptation.
Double-chain Constraints for 3D Human Pose Estimation in Images and Videos
Notably, our model achieves state-of-the-art performance on all action categories in the Human3. 6M dataset using detected 2D poses from CPN, and our code is available at: https://github. com/KHB1698/DC-GCT.
Ranked #35 on
3D Human Pose Estimation
on MPI-INF-3DHP
(AUC metric)
Dual Arbitrary Scale Super-Resolution for Multi-Contrast MRI
Limited by imaging systems, the reconstruction of Magnetic Resonance Imaging (MRI) images from partial measurement is essential to medical imaging research.
Crafting Training Degradation Distribution for the Accuracy-Generalization Trade-off in Real-World Super-Resolution
In this work, we introduce a novel approach to craft training degradation distributions using a small set of reference images.
EgoVSR: Towards High-Quality Egocentric Video Super-Resolution
We explicitly tackle motion blurs in egocentric videos using a Dual Branch Deblur Network (DB$^2$Net) in the VSR framework.
DiffIR: Efficient Diffusion Model for Image Restoration
Diffusion model (DM) has achieved SOTA performance by modeling the image synthesis process into a sequential application of a denoising network.
Explicit3D: Graph Network with Spatial Inference for Single Image 3D Object Detection
Instead of using ground-truth labels as direct supervision, our relative and corner loss are derived from the homogeneous transformation, which renders the model to learn the geometric consistency between objects.
MVKT-ECG: Efficient Single-lead ECG Classification on Multi-Label Arrhythmia by Multi-View Knowledge Transferring
However, it is challenging to develop a single-lead-based ECG interpretation model for multiple diseases diagnosis due to the lack of some key disease information.
Local and Global Logit Adjustments for Long-Tailed Learning
LGLA consists of two core components: a Class-aware Logit Adjustment (CLA) strategy and an Adaptive Angular Weighted (AAW) loss.
Knowledge Distillation based Degradation Estimation for Blind Super-Resolution
It consists of a knowledge distillation based implicit degradation estimator network (KD-IDE) and an efficient SR network.
A Dual-scale Lead-seperated Transformer With Lead-orthogonal Attention And Meta-information For Ecg Classification
Auxiliary diagnosis of cardiac electrophysiological status can be obtained through the analysis of 12-lead electrocardiograms (ECGs).
Super-Resolution by Predicting Offsets: An Ultra-Efficient Super-Resolution Network for Rasterized Images
We finally use a guided fusion operation to integrate the sharp edges generated by the network and flat areas by the interpolation method to get the final SR image.
Basic Binary Convolution Unit for Binarized Image Restoration Network
In this study, we reconsider components in binary convolution, such as residual connection, BatchNorm, activation function, and structure, for IR tasks.
Meta-Learning based Degradation Representation for Blind Super-Resolution
The most of CNN based super-resolution (SR) methods assume that the degradation is known (\eg, bicubic).
Structured Sparsity Learning for Efficient Video Super-Resolution
In SSL, we design pruning schemes for several key components in VSR models, including residual blocks, recurrent networks, and upsampling networks.
SCS-Co: Self-Consistent Style Contrastive Learning for Image Harmonization
In addition, we propose a background-attentional adaptive instance normalization (BAIN) to achieve an attention-weighted background feature distribution according to the foreground-background feature similarity.
STDAN: Deformable Attention Network for Space-Time Video Super-Resolution
Second, we put forward a spatial-temporal deformable feature aggregation (STDFA) module, in which spatial and temporal contexts in dynamic video frames are adaptively captured and aggregated to enhance SR reconstruction.
Coarse-to-Fine Embedded PatchMatch and Multi-Scale Dynamic Aggregation for Reference-based Super-Resolution
To improve matching efficiency, we design a novel Embedded PatchMacth scheme with random samples propagation, which involves end-to-end training with asymptotic linear computational cost to the input size.
Efficient Non-Local Contrastive Attention for Image Super-Resolution
To demonstrate the effectiveness of ENLCA, we build an architecture called Efficient Non-Local Contrastive Network (ENLCN) by adding a few of our modules in a simple backbone.
Group Fisher Pruning for Practical Network Compression
Our method can be used to prune any structures including those with coupled channels.
Ranked #4 on
Network Pruning
on ImageNet
NTIRE 2021 Challenge on Perceptual Image Quality Assessment
This paper reports on the NTIRE 2021 challenge on perceptual image quality assessment (IQA), held in conjunction with the New Trends in Image Restoration and Enhancement workshop (NTIRE) workshop at CVPR 2021.
ER-IQA: Boosting Perceptual Quality Assessment Using External Reference Images
In this paper, we introduce a brand new scheme, namely external-reference image quality assessment (ER-IQA), by introducing external reference images to bridge the gap between FR and NR-IQA.
NTIRE 2021 Challenge on Quality Enhancement of Compressed Video: Methods and Results
This paper reviews the first NTIRE challenge on quality enhancement of compressed video, with a focus on the proposed methods and results.
Exploiting Temporal Contexts with Strided Transformer for 3D Human Pose Estimation
The modified VTE is termed as Strided Transformer Encoder (STE), which is built upon the outputs of VTE.
Ranked #2 on
3D Human Pose Estimation
on HumanEva-I
Towards Impartial Multi-task Learning
Multi-task learning (MTL) has been widely used in representation learning.
Attention Cube Network for Image Restoration
The adaptive spatial attention branch (ASAB) and the adaptive channel attention branch (ACAB) constitute the adaptive dual attention module (ADAM), which can capture the long-range spatial and channel-wise contextual information to expand the receptive field and distinguish different types of information for more effective feature representations.
Real-MFF: A Large Realistic Multi-focus Image Dataset with Ground Truth
In this letter, we introduce a large and realistic multi-focus dataset called Real-MFF, which contains 710 pairs of source images with corresponding ground truth images.
LCSCNet: Linear Compressing Based Skip-Connecting Network for Image Super-Resolution
In this paper, we develop a concise but efficient network architecture called linear compressing based skip-connecting network (LCSCNet) for image super-resolution.
Ranked #19 on
Image Super-Resolution
on BSD100 - 3x upscaling
CFSNet: Toward a Controllable Feature Space for Image Restoration
Deep learning methods have witnessed the great progress in image restoration with specific metrics (e. g., PSNR, SSIM).
Lightweight Feature Fusion Network for Single Image Super-Resolution
Specifically, a spindle block is composed of a dimension extension unit, a feature exploration unit and a feature refinement unit.
Ranked #17 on
Image Super-Resolution
on Manga109 - 3x upscaling
Domain-Aware SE Network for Sketch-based Image Retrieval with Multiplicative Euclidean Margin Softmax
This paper proposes a novel approach for Sketch-Based Image Retrieval (SBIR), for which the key is to bridge the gap between sketches and photos in terms of the data representation.
Deep Learning for Single Image Super-Resolution: A Brief Review
Single image super-resolution (SISR) is a notoriously challenging ill-posed problem, which aims to obtain a high-resolution (HR) output from one of its low-resolution (LR) versions.
