Search Results for author:
Found 54 papers, 31 papers with code
Lagrange Duality and Compound Multi-Attention Transformer for Semi-Supervised Medical Image Segmentation
Overall, our results indicate that CMAformer, combined with the feature fusion framework and the new consistency loss, demonstrates strong complementarity in semi-supervised learning ensembles.
ASSNet: Adaptive Semantic Segmentation Network for Microtumors and Multi-Organ Segmentation
To address this limitation, we propose the Adaptive Semantic Segmentation Network (ASSNet), a transformer architecture that effectively integrates local and global features for precise medical image segmentation.
Spatial-Aware Conformal Prediction for Trustworthy Hyperspectral Image Classification
Hyperspectral image (HSI) classification involves assigning specific labels to each pixel to identify various land cover categories.
SMAFormer: Synergistic Multi-Attention Transformer for Medical Image Segmentation
First, a Synergistic Multi-Attention (SMA) Transformer block is proposed, which has the benefits of Pixel Attention, Channel Attention, and Spatial Attention for feature enrichment.
UIE-UnFold: Deep Unfolding Network with Color Priors and Vision Transformer for Underwater Image Enhancement
By explicitly incorporating color priors and modeling the physical characteristics of underwater image formation, the proposed DUN model achieves more accurate and reliable enhancement results.
Dual-Hybrid Attention Network for Specular Highlight Removal
Specular highlight removal plays a pivotal role in multimedia applications, as it enhances the quality and interpretability of images and videos, ultimately improving the performance of downstream tasks such as content-based retrieval, object recognition, and scene understanding.
MFDNet: Multi-Frequency Deflare Network for Efficient Nighttime Flare Removal
The low-frequency part typically contains illumination information, while the high-frequency part contains detailed content information.
IMDL-BenCo: A Comprehensive Benchmark and Codebase for Image Manipulation Detection & Localization
A comprehensive benchmark is yet to be established in the Image Manipulation Detection \& Localization (IMDL) field.
ZeroPur: Succinct Training-Free Adversarial Purification
In this work, we suppose that adversarial images are outliers of the natural image manifold and the purification process can be considered as returning them to this manifold.
PVALane: Prior-Guided 3D Lane Detection with View-Agnostic Feature Alignment
Monocular 3D lane detection is essential for a reliable autonomous driving system and has recently been rapidly developing.
Ranked #1 on
3D Lane Detection
on OpenLane
Depth-aware Test-Time Training for Zero-shot Video Object Segmentation
In this work, we introduce a test-time training (TTT) strategy to address the problem.
EmoSpeaker: One-shot Fine-grained Emotion-Controlled Talking Face Generation
Additionally, we propose an emotion intensity control method using a fine-grained emotion matrix.
COMMA: Co-Articulated Multi-Modal Learning
First, the prompts of the vision and language branches in these methods are usually separated or uni-directionally correlated.
GaussianHead: High-fidelity Head Avatars with Learnable Gaussian Derivation
Constructing vivid 3D head avatars for given subjects and realizing a series of animations on them is valuable yet challenging.
Sketch Video Synthesis
Understanding semantic intricacies and high-level concepts is essential in image sketch generation, and this challenge becomes even more formidable when applied to the domain of videos.
ELF: An End-to-end Local and Global Multimodal Fusion Framework for Glaucoma Grading
Glaucoma is a chronic neurodegenerative condition that can lead to blindness.
UWFormer: Underwater Image Enhancement via a Semi-Supervised Multi-Scale Transformer
Underwater images often exhibit poor quality, distorted color balance and low contrast due to the complex and intricate interplay of light, water, and objects.
Perceptual MAE for Image Manipulation Localization: A High-level Vision Learner Focusing on Low-level Features
While MAE has demonstrated an impressive understanding of object semantics, PMAE can also compensate for low-level semantics with our proposed enhancements.
MedPrompt: Cross-Modal Prompting for Multi-Task Medical Image Translation
Within this framework, we introduce the Prompt Extraction Block and the Prompt Fusion Block to efficiently encode the cross-modal prompt.
ShaDocFormer: A Shadow-Attentive Threshold Detector With Cascaded Fusion Refiner for Document Shadow Removal
The STD module employs a traditional thresholding technique and leverages the attention mechanism of the Transformer to gather global information, thereby enabling precise detection of shadow masks.
High-Resolution Document Shadow Removal via A Large-Scale Real-World Dataset and A Frequency-Aware Shadow Erasing Net
We handle high-resolution document shadow removal directly via a larger-scale real-world dataset and a carefully designed frequency-aware network.
Devignet: High-Resolution Vignetting Removal via a Dual Aggregated Fusion Transformer With Adaptive Channel Expansion
Vignetting commonly occurs as a degradation in images resulting from factors such as lens design, improper lens hood usage, and limitations in camera sensors.
RBA-GCN: Relational Bilevel Aggregation Graph Convolutional Network for Emotion Recognition
This module can construct the interaction between different modalities and capture long-range contextual information based on similarity clusters.
AdaBrowse: Adaptive Video Browser for Efficient Continuous Sign Language Recognition
Then these features are fed into a policy network to intelligently select a subsequence to process.
Ranked #8 on
Sign Language Recognition
on CSL-Daily
DocDeshadower: Frequency-Aware Transformer for Document Shadow Removal
Shadows in scanned documents pose significant challenges for document analysis and recognition tasks due to their negative impact on visual quality and readability.
Explicit Visual Prompting for Universal Foreground Segmentations
We take inspiration from the widely-used pre-training and then prompt tuning protocols in NLP and propose a new visual prompting model, named Explicit Visual Prompting (EVP).
Ranked #2 on
Salient Object Detection
on DUT-OMRON
Brain Imaging-to-Graph Generation using Adversarial Hierarchical Diffusion Models for MCI Causality Analysis
To be specific, the proposed BIGG framework is based on the diffusion denoising probabilistic models (DDPM), where each denoising step is modeled as a generative adversarial network (GAN) to progressively translate the noise and conditional fMRI to effective connectivity.
Quaternion-valued Correlation Learning for Few-Shot Semantic Segmentation
In this paper, we introduce a quaternion perspective on correlation learning and propose a novel Quaternion-valued Correlation Learning Network (QCLNet), with the aim to alleviate the computational burden of high-dimensional correlation tensor and explore internal latent interaction between query and support images by leveraging operations defined by the established quaternion algebra.
Ranked #20 on
Few-Shot Semantic Segmentation
on COCO-20i (5-shot)
Locality Preserving Multiview Graph Hashing for Large Scale Remote Sensing Image Search
This article proposes a multiview hashing with learnable parameters to retrieve the queried images for a large-scale remote sensing dataset.
Explicit Visual Prompting for Low-Level Structure Segmentations
Different from the previous visual prompting which is typically a dataset-level implicit embedding, our key insight is to enforce the tunable parameters focusing on the explicit visual content from each individual image, i. e., the features from frozen patch embeddings and the input's high-frequency components.
Ranked #3 on
Salient Object Detection
on HKU-IS
CoordFill: Efficient High-Resolution Image Inpainting via Parameterized Coordinate Querying
Thanks to the proposed structure, we only encode the high-resolution image in a relatively low resolution for larger reception field capturing.
Brain Diffuser: An End-to-End Brain Image to Brain Network Pipeline
Brain network analysis is essential for diagnosing and intervention for Alzheimer's disease (AD).
A Large-scale Film Style Dataset for Learning Multi-frequency Driven Film Enhancement
In order to facilitate film-based image stylization research, we construct FilmSet, a large-scale and high-quality film style dataset.
WavEnhancer: Unifying Wavelet and Transformer for Image Enhancement
Image enhancement is a technique that frequently utilized in digital image processing.
ShaDocNet: Learning Spatial-Aware Tokens in Transformer for Document Shadow Removal
Shadow removal improves the visual quality and legibility of digital copies of documents.
Asymmetric Scalable Cross-modal Hashing
In addition, most of the existing methods choose to use an $n\times n$ similarity matrix for optimization, which makes the memory and computation unaffordable.
Arbitrary Style Transfer with Structure Enhancement by Combining the Global and Local Loss
To solve this problem, we introduce a novel arbitrary style transfer method with structure enhancement by combining the global and local loss.
Image Harmonization with Region-wise Contrastive Learning
Our method attempts to bring together corresponding positive and negative samples by maximizing the mutual information between the foreground and background styles, which desirably makes our harmonization network more robust to discriminate the foreground and background style features when harmonizing composite images.
Learning Enriched Illuminants for Cross and Single Sensor Color Constancy
Color constancy aims to restore the constant colors of a scene under different illuminants.
Spatial-Separated Curve Rendering Network for Efficient and High-Resolution Image Harmonization
To this end, we propose a novel spatial-separated curve rendering network(S$^2$CRNet) for efficient and high-resolution image harmonization for the first time.
Ranked #12 on
Image Harmonization
on iHarmony4
Deep Collaborative Multi-Modal Learning for Unsupervised Kinship Estimation
To this end, we propose a novel deep collaborative multi-modal learning (DCML) to integrate the underlying information presented in facial properties in an adaptive manner to strengthen the facial details for effective unsupervised kinship verification.
Kinship Verification Based on Cross-Generation Feature Interaction Learning
Specifically, we take parents and children as a whole to extract the expressive local and non-local features.
Personal Privacy Protection via Irrelevant Faces Tracking and Pixelation in Video Live Streaming
On the video live streaming dataset we collected, FPVLS obtains satisfying accuracy, real-time efficiency, and contains the over-pixelation problems.
Privacy-sensitive Objects Pixelation for Live Video Streaming
With the prevailing of live video streaming, establishing an online pixelation method for privacy-sensitive objects is an urgency.
News Image Steganography: A Novel Architecture Facilitates the Fake News Identification
A larger portion of fake news quotes untampered images from other sources with ulterior motives rather than conducting image forgery.
Split then Refine: Stacked Attention-guided ResUNets for Blind Single Image Visible Watermark Removal
Simultaneously, to increase the robustness of watermark, attacking technique, such as watermark removal, also gets the attention from the community.
Defocus Blur Detection via Depth Distillation
In detail, we learn the defocus blur from ground truth and the depth distilled from a well-trained depth estimation network at the same time.
Towards Ghost-free Shadow Removal via Dual Hierarchical Aggregation Network and Shadow Matting GAN
With the help of novel masks or scenes, we enhance the current datasets using synthesized shadow images.
Ranked #4 on
Shadow Removal
on ISTD
Improving the Harmony of the Composite Image by Spatial-Separated Attention Module
Thus, we address the problem of Image Harmonization: Given a spliced image and the mask of the spliced region, we try to harmonize the "style" of the pasted region with the background (non-spliced region).
Ranked #5 on
Image Harmonization
on HAdobe5k(1024$\times$1024)
Generating Minimal Adversarial Perturbations with Integrated Adaptive Gradients
Deep neural networks are easily fooled high confidence predictions for adversarial samples
Pixelation is NOT Done in Videos Yet
This paper introduces an algorithm to protect the privacy of individuals in streaming video data by blurring faces such that face cannot be reliably recognized.
Adaptive Gradient for Adversarial Perturbations Generation
Deep Neural Networks have achieved remarkable success in computer vision, natural language processing, and audio tasks.
Generating Adversarial Perturbation with Root Mean Square Gradient
We focus our attention on the problem of generating adversarial perturbations based on the gradient in image classification domain
Depth Assisted Full Resolution Network for Single Image-based View Synthesis
In this paper, we focus on a more challenging and ill-posed problem that is to synthesize novel viewpoints from one single input image.
