Search Results for author:
Found 60 papers, 34 papers with code
Learning Trailer Moments in Full-Length Movies with Co-Contrastive Attention
We introduce a novel ranking network that utilizes the Co-Attention between movies and trailers as guidance to generate the training pairs, where the moments highly corrected with trailers are expected to be scored higher than the uncorrelated moments.
Fill the K-Space and Refine the Image: Prompting for Dynamic and Multi-Contrast MRI Reconstruction
Then, we extend the baseline model to a prompt-based learning approach, PromptMR, for all-in-one MRI reconstruction from different views, contrasts, adjacent types, and acceleration factors.
DeFormer: Integrating Transformers with Deformable Models for 3D Shape Abstraction from a Single Image
Accurate 3D shape abstraction from a single 2D image is a long-standing problem in computer vision and graphics.
Deep Deformable Models: Learning 3D Shape Abstractions with Part Consistency
The task of shape abstraction with semantic part consistency is challenging due to the complex geometries of natural objects.
DMCVR: Morphology-Guided Diffusion Model for 3D Cardiac Volume Reconstruction
However, current cardiac MRI-based reconstruction technology used in clinical settings is 2D with limited through-plane resolution, resulting in low-quality reconstructed cardiac volumes.
Improving Pseudo Labels for Open-Vocabulary Object Detection
Second, a split-and-fusion (SAF) head is designed to remove the noise in localization of PLs, which is usually ignored in existing methods.
Classification of lung cancer subtypes on CT images with synthetic pathological priors
The accurate diagnosis on pathological subtypes for lung cancer is of significant importance for the follow-up treatments and prognosis managements.
Pathology-and-genomics Multimodal Transformer for Survival Outcome Prediction
Survival outcome assessment is challenging and inherently associated with multiple clinical factors (e. g., imaging and genomics biomarkers) in cancer.
Training Like a Medical Resident: Universal Medical Image Segmentation via Context Prior Learning
Inspired by the training of medical residents, we explore universal medical image segmentation, whose goal is to learn from diverse medical imaging sources covering a range of clinical targets, body regions, and image modalities.
A Critical Analysis of the Limitation of Deep Learning based 3D Dental Mesh Segmentation Methods in Segmenting Partial Scans
Tooth segmentation from intraoral scans is a crucial part of digital dentistry.
Revisiting Multimodal Representation in Contrastive Learning: From Patch and Token Embeddings to Finite Discrete Tokens
However, direct aligning cross-modal information using such representations is challenging, as visual patches and text tokens differ in semantic levels and granularities.
Dealing With Heterogeneous 3D MR Knee Images: A Federated Few-Shot Learning Method With Dual Knowledge Distillation
The supervised learning of the proposed method extracts features from limited labeled data in each client, while the unsupervised data is used to distill both feature and response-based knowledge from a national data repository to further improve the accuracy of the collaborative model and reduce the communication cost.
Steering Prototype with Prompt-tuning for Rehearsal-free Continual Learning
Prototype, as a representation of class embeddings, has been explored to reduce memory footprint or mitigate forgetting for continual learning scenarios.
3D Tooth Mesh Segmentation with Simplified Mesh Cell Representation
Summarizing of the mesh cell/triangle in this manner imposes an implicit structural constraint and makes it difficult to work with multiple resolutions which is done in many point cloud based deep learning algorithms.
CDDSA: Contrastive Domain Disentanglement and Style Augmentation for Generalizable Medical Image Segmentation
First, a disentangle network is proposed to decompose an image into a domain-invariant anatomical representation and a domain-specific style code, where the former is sent to a segmentation model that is not affected by the domain shift, and the disentangle network is regularized by a decoder that combines the anatomical and style codes to reconstruct the input image.
Visual Prompt Tuning for Test-time Domain Adaptation
First, DePT plugs visual prompts into the vision Transformer and only tunes these source-initialized prompts during adaptation.
Ranked #2 on
Domain Adaptation
on VisDA2017
Hierarchically Self-Supervised Transformer for Human Skeleton Representation Learning
Despite the success of fully-supervised human skeleton sequence modeling, utilizing self-supervised pre-training for skeleton sequence representation learning has been an active field because acquiring task-specific skeleton annotations at large scales is difficult.
Towards Self-supervised and Weight-preserving Neural Architecture Search
In this work, we propose the self-supervised and weight-preserving neural architecture search (SSWP-NAS) as an extension of the current NAS framework by allowing the self-supervision and retaining the concomitant weights discovered during the search stage.
A Data-scalable Transformer for Medical Image Segmentation: Architecture, Model Efficiency, and Benchmark
Transformers have demonstrated remarkable performance in natural language processing and computer vision.
Learning Transferable Reward for Query Object Localization with Policy Adaptation
We propose a reinforcement learning based approach to query object localization, for which an agent is trained to localize objects of interest specified by a small exemplary set.
Learned Half-Quadratic Splitting Network for MR Image Reconstruction
Magnetic Resonance (MR) image reconstruction from highly undersampled $k$-space data is critical in accelerated MR imaging (MRI) techniques.
WORD: A large scale dataset, benchmark and clinical applicable study for abdominal organ segmentation from CT image
Deep learning-based medical image segmentation has shown the potential to reduce manual delineation efforts, but it still requires a large-scale fine annotated dataset for training, and there is a lack of large-scale datasets covering the whole abdomen region with accurate and detailed annotations for the whole abdominal organ segmentation.
Stochastic Transformer Networks with Linear Competing Units: Application to end-to-end SL Translation
In this paper, we attenuate this need, by introducing an end-to-end SLT model that does not entail explicit use of glosses; the model only needs text groundtruth.
Hybrid Supervision Learning for Pathology Whole Slide Image Classification
To handle this problem, we propose a hybrid supervision learning framework for this kind of high resolution images with sufficient image-level coarse annotations and a few pixel-level fine labels.
Object-Guided Instance Segmentation With Auxiliary Feature Refinement for Biological Images
To deal with this problem, in this paper, we propose an object-guided instance segmentation method.
Improved Transformer for High-Resolution GANs
Attention-based models, exemplified by the Transformer, can effectively model long range dependency, but suffer from the quadratic complexity of self-attention operation, making them difficult to be adopted for high-resolution image generation based on Generative Adversarial Networks (GANs).
Ranked #2 on
Image Generation
on CelebA 256x256
(FID metric)
More Than Just Attention: Improving Cross-Modal Attentions with Contrastive Constraints for Image-Text Matching
Cross-modal attention mechanisms have been widely applied to the image-text matching task and have achieved remarkable improvements thanks to its capability of learning fine-grained relevance across different modalities.
A Good Image Generator Is What You Need for High-Resolution Video Synthesis
We introduce a motion generator that discovers the desired trajectory, in which content and motion are disentangled.
Ranked #21 on
Video Generation
on UCF-101
SCPM-Net: An Anchor-free 3D Lung Nodule Detection Network using Sphere Representation and Center Points Matching
To overcome these problems, we propose a 3D sphere representation-based center-points matching detection network that is anchor-free and automatically predicts the position, radius, and offset of nodules without the manual design of nodule/anchor parameters.
Deep Animation Video Interpolation in the Wild
In the animation industry, cartoon videos are usually produced at low frame rate since hand drawing of such frames is costly and time-consuming.
FocusNetv2: Imbalanced Large and Small Organ Segmentation with Adversarial Shape Constraint for Head and Neck CT Images
Radiotherapy is a treatment where radiation is used to eliminate cancer cells.
Variational Bayesian Sequence-to-Sequence Networks for Memory-Efficient Sign Language Translation
Memory-efficient continuous Sign Language Translation is a significant challenge for the development of assisted technologies with real-time applicability for the deaf.
Semantic Aware Data Augmentation for Cell Nuclei Microscopical Images With Artificial Neural Networks
The importance of this subject is nested in the amount of training data that artificial neural networks need to accurately identify and segment objects in images and the infeasibility of acquiring a sufficient dataset within the biomedical field.
Unity of Opposites: SelfNorm and CrossNorm for Model Robustness
CrossNorm exchanges styles between feature channels to perform style augmentation, diversifying the content and style mixtures.
Multi-modal AsynDGAN: Learn From Distributed Medical Image Data without Sharing Private Information
As deep learning technologies advance, increasingly more data is necessary to generate general and robust models for various tasks.
Learning Trailer Moments in Full-Length Movies
A movie's key moments stand out of the screenplay to grab an audience's attention and make movie browsing efficient.
Weakly Supervised Deep Nuclei Segmentation Using Partial Points Annotation in Histopathology Images
To alleviate such tedious and manual effort, in this paper we propose a novel weakly supervised segmentation framework based on partial points annotation, i. e., only a small portion of nuclei locations in each image are labeled.
Knowledge as Priors: Cross-Modal Knowledge Generalization for Datasets without Superior Knowledge
Our key idea is to generalize the distilled cross-modal knowledge learned from a Source dataset, which contains paired examples from both modalities, to the Target dataset by modeling knowledge as priors on parameters of the Student.
Vertebra-Focused Landmark Detection for Scoliosis Assessment
The comparison results demonstrate the merits of our method in both Cobb angle measurement and landmark detection on low-contrast and ambiguous X-ray images.
Object-Guided Instance Segmentation for Biological Images
Along with the instance normalization, the model is able to recover the target object distribution and suppress the distribution of neighboring attached objects.
Rethinking Kernel Methods for Node Representation Learning on Graphs
Graph kernels are kernel methods measuring graph similarity and serve as a standard tool for graph classification.
Ranked #7 on
Link Prediction
on Cora
ASSD: Attentive Single Shot Multibox Detector
This paper proposes a new deep neural network for object detection.
Collaborative Multi-agent Learning for MR Knee Articular Cartilage Segmentation
However, effective and efficient delineation of all the knee articular cartilages in large-sized and high-resolution 3D MR knee data is still an open challenge.
Greedy AutoAugment
This is a challenging problem and requires exploration for data augmentation policies to ensure their effectiveness in covering the search space.
Multi-scale Cell Instance Segmentation with Keypoint Graph based Bounding Boxes
In this paper, we propose a new box-based cell instance segmentation method.
Construct Dynamic Graphs for Hand Gesture Recognition via Spatial-Temporal Attention
We propose a Dynamic Graph-Based Spatial-Temporal Attention (DG-STA) method for hand gesture recognition.
Ranked #3 on
Hand Gesture Recognition
on SHREC 2017
2nd Place Solution to the GQA Challenge 2019
We present a simple method that achieves unexpectedly superior performance for Complex Reasoning involved Visual Question Answering.
Semantic Graph Convolutional Networks for 3D Human Pose Regression
In this paper, we study the problem of learning Graph Convolutional Networks (GCNs) for regression.
Ranked #21 on
Monocular 3D Human Pose Estimation
on Human3.6M
Sharpen Focus: Learning with Attention Separability and Consistency
Recent developments in gradient-based attention modeling have seen attention maps emerge as a powerful tool for interpreting convolutional neural networks.
CU-Net: Coupled U-Nets
We design a new connectivity pattern for the U-Net architecture.
Ranked #30 on
Pose Estimation
on MPII Human Pose
CR-GAN: Learning Complete Representations for Multi-view Generation
Generating multi-view images from a single-view input is an essential yet challenging problem.
Scenarios: A New Representation for Complex Scene Understanding
The ability for computational agents to reason about the high-level content of real world scene images is important for many applications.
RED-Net: A Recurrent Encoder-Decoder Network for Video-based Face Alignment
We propose a novel method for real-time face alignment in videos based on a recurrent encoder-decoder network model.
Cartoonish sketch-based face editing in videos using identity deformation transfer
We first recover the facial identity and expressions from the video by fitting a face morphable model for each frame.
Dual Iterative Hard Thresholding: From Non-convex Sparse Minimization to Non-smooth Concave Maximization
It remains open to explore duality theory and algorithms in such a non-convex and NP-hard problem setting.
Multispectral Deep Neural Networks for Pedestrian Detection
Multispectral pedestrian detection is essential for around-the-clock applications, e. g., surveillance and autonomous driving.
Track Facial Points in Unconstrained Videos
Our approach takes advantage of part-based representation and cascade regression for robust and efficient alignment on each frame.
A Recurrent Encoder-Decoder Network for Sequential Face Alignment
We propose a novel recurrent encoder-decoder network model for real-time video-based face alignment.
Visual Tracking via Reliable Memories
In this paper, we propose a novel visual tracking framework that intelligently discovers reliable patterns from a wide range of video to resist drift error for long-term tracking tasks.
PIEFA: Personalized Incremental and Ensemble Face Alignment
Face alignment, especially on real-time or large-scale sequential images, is a challenging task with broad applications.
