Search Results for author:
Found 48 papers, 12 papers with code
Federated Semi-supervised Learning for Medical Image Segmentation with intra-client and inter-client Consistency
The intra-client and inter-client consistency learning are introduced to smooth predictions at the data level and avoid confirmation bias of local models.
A Medical Data-Effective Learning Benchmark for Highly Efficient Pre-training of Foundation Models
This paper introduces data-effective learning, aiming to use data in the most impactful way to pre-train foundation models.
Low-latency Space-time Supersampling for Real-time Rendering
With the rise of real-time rendering and the evolution of display devices, there is a growing demand for post-processing methods that offer high-resolution content in a high frame rate.
Context-Aware Iteration Policy Network for Efficient Optical Flow Estimation
In this paper, we develop a Context-Aware Iteration Policy Network for efficient optical flow estimation, which determines the optimal number of iterations per sample.
Federated Heterogeneous Graph Neural Network for Privacy-preserving Recommendation
Existing HIN-based recommender systems operate under the assumption of centralized storage and model training.
Unsupervised Disentangling of Facial Representations with 3D-aware Latent Diffusion Models
Second, we propose a novel representation diffusion model (RDM) to disentangle 3D latent into facial identity and expression.
MVFlow: Deep Optical Flow Estimation of Compressed Videos with Motion Vector Prior
Motion vectors, one of the compression information, record the motion of the video frames.
Uncertainty-Guided Spatial Pruning Architecture for Efficient Frame Interpolation
We can use dynamic spatial pruning method to skip redundant computation, but this method cannot properly identify easy regions in VFI tasks without supervision.
SAMFlow: Eliminating Any Fragmentation in Optical Flow with Segment Anything Model
Optical Flow Estimation aims to find the 2D dense motion field between two frames.
DifFSS: Diffusion Model for Few-Shot Semantic Segmentation
Although various few-shot semantic segmentation (FSS) models with different network structures have been proposed, performance improvement has reached a bottleneck.
Ranked #5 on
Few-Shot Semantic Segmentation
on PASCAL-5i (1-Shot)
Instruct-NeuralTalker: Editing Audio-Driven Talking Radiance Fields with Instructions
Given a short speech video, we first build an efficient talking radiance field, and then apply the latest conditional diffusion model for image editing based on the given instructions and guiding implicit representation optimization towards the editing target.
Learning Survival Distribution with Implicit Survival Function
Survival analysis aims at modeling the relationship between covariates and event occurrence with some untracked (censored) samples.
Multi-Modality Deep Network for JPEG Artifacts Reduction
In recent years, many convolutional neural network-based models are designed for JPEG artifacts reduction, and have achieved notable progress.
Multi-Modality Deep Network for Extreme Learned Image Compression
Image-based single-modality compression learning approaches have demonstrated exceptionally powerful encoding and decoding capabilities in the past few years , but suffer from blur and severe semantics loss at extremely low bitrates.
Graph Mining for Cybersecurity: A Survey
In recent years, with the proliferation of graph mining techniques, many researchers investigated these techniques for capturing correlations between cyber entities and achieving high performance.
Abnormal Event Detection via Hypergraph Contrastive Learning
AEHCL designs the intra-event and inter-event contrastive modules to exploit self-supervised AHIN information.
Task-Specific Data Augmentation and Inference Processing for VIPriors Instance Segmentation Challenge
And in order to make the most of visual inductive priors, we designed a task-specific inference processing strategy.
Strong Instance Segmentation Pipeline for MMSports Challenge
The goal of ACM MMSports2022 DeepSportRadar Instance Segmentation Challenge is to tackle the segmentation of individual humans including players, coaches and referees on a basketball court.
Geometry-Aware Reference Synthesis for Multi-View Image Super-Resolution
To address these problems, we propose the MVSRnet, which uses geometry information to extract sharp details from all LR multi-view to support the SR of the LR input view.
Learning Parallax Transformer Network for Stereo Image JPEG Artifacts Removal
Under stereo settings, the performance of image JPEG artifacts removal can be further improved by exploiting the additional information provided by a second view.
Perception-Oriented Stereo Image Super-Resolution
Recent studies of deep learning based stereo image super-resolution (StereoSR) have promoted the development of StereoSR.
Rethinking Super-Resolution as Text-Guided Details Generation
To enhance the semantic accuracy and the visual quality of the reconstructed image, we explore the multi-modal fusion learning in SISR by proposing a Text-Guided Super-Resolution (TGSR) framework, which can effectively utilize the information from the text and image modalities.
The Third Place Solution for CVPR2022 AVA Accessibility Vision and Autonomy Challenge
Finally, our approach achieves 63. 008\%AP@0. 50:0. 95 on the test set of CVPR2022 AVA Challenge.
The Second Place Solution for The 4th Large-scale Video Object Segmentation Challenge--Track 3: Referring Video Object Segmentation
The referring video object segmentation task (RVOS) aims to segment object instances in a given video referred by a language expression in all video frames.
Bilateral Network with Channel Splitting Network and Transformer for Thermal Image Super-Resolution
Firstly, we designed a context branch based on channel splitting network with transformer to obtain sufficient context information.
Learning Robust Image-Based Rendering on Sparse Scene Geometry via Depth Completion
Specifically, GR stage takes sparse depth map and RGB as input to predict dense depth map by exploiting the correlation between two modals.
Stronger Baseline for Person Re-Identification
Person re-identification (re-ID) aims to identify the same person of interest across non-overlapping capturing cameras, which plays an important role in visual surveillance applications and computer vision research areas.
The Second Place Solution for ICCV2021 VIPriors Instance Segmentation Challenge
Finally, our approach can achieve 40. 2\%AP@0. 50:0. 95 on the test set of ICCV2021 VIPriors instance segmentation challenge.
TBN-ViT: Temporal Bilateral Network with Vision Transformer for Video Scene Parsing
Based on VSPW, we design a Temporal Bilateral Network with Vision Transformer.
Time in a Box: Advancing Knowledge Graph Completion with Temporal Scopes
Hence, knowledge base completion (KBC) on temporal knowledge bases (TKB), where each statement \textit{may} be associated with a temporal scope, has attracted growing attention.
A Review of Location Encoding for GeoAI: Methods and Applications
A common need for artificial intelligence models in the broader geoscience is to represent and encode various types of spatial data, such as points (e. g., points of interest), polylines (e. g., trajectories), polygons (e. g., administrative regions), graphs (e. g., transportation networks), or rasters (e. g., remote sensing images), in a hidden embedding space so that they can be readily incorporated into deep learning models.
GACAN: Graph Attention-Convolution-Attention Networks for Traffic Forecasting Based on Multi-granularity Time Series
The main novelty of the model is the integration of time series of four different time granularities: the original time series, together with hourly, daily, and weekly time series.
Feature Pyramid Network for Multi-task Affective Analysis
Affective Analysis is not a single task, and the valence-arousal value, expression class, and action unit can be predicted at the same time.
DeepAVO: Efficient Pose Refining with Feature Distilling for Deep Visual Odometry
The technology for Visual Odometry (VO) that estimates the position and orientation of the moving object through analyzing the image sequences captured by on-board cameras, has been well investigated with the rising interest in autonomous driving.
Perceptual Variousness Motion Deblurring With Light Global Context Refinement
Deep learning algorithms have made significant progress in dynamic scene deblurring.
Generator Pyramid for High-Resolution Image Inpainting
Thus, our model consists of a pyramid of fully convolutional GANs, wherein the content GAN is responsible for completing contents in the lowest-resolution masked image, and each texture GAN is responsible for synthesizing textures in a higher-resolution image.
Isometric Graph Neural Networks
Many tasks that rely on representations of nodes in graphs would benefit if those representations were faithful to distances between nodes in the graph.
Traffic transformer: Capturing the continuity and periodicity of time series for traffic forecasting
In this work we propose a novel deep learning architecture called Traffic Transformer to capture the continuity and periodicity of time series and to model spatial dependency.
Ranked #1 on
Time Series Forecasting
on US Economy
Assessing Eye Aesthetics for Automatic Multi-Reference Eye In-Painting
With the wide use of artistic images, aesthetic quality assessment has been widely concerned.
Disparity-Aware Domain Adaptation in Stereo Image Restoration
Under stereo settings, the problems of disparity estimation, stereo magnification and stereo-view synthesis have gathered wide attention.
SE-KGE: A Location-Aware Knowledge Graph Embedding Model for Geographic Question Answering and Spatial Semantic Lifting
We also construct a geographic knowledge graph as well as a set of geographic query-answer pairs called DBGeo to evaluate the performance of SE-KGE in comparison to multiple baselines.
Multi-Scale Representation Learning for Spatial Feature Distributions using Grid Cells
The key idea is to use neural networks to convert words in texts to vector space representations based on word positions in a sentence and their contexts, which are suitable for end-to-end training of downstream tasks.
TransGCN:Coupling Transformation Assumptions with Graph Convolutional Networks for Link Prediction
Link prediction is an important and frequently studied task that contributes to an understanding of the structure of knowledge graphs (KGs) in statistical relational learning.
Contextual Graph Attention for Answering Logical Queries over Incomplete Knowledge Graphs
Recently, several studies have explored methods for using KG embedding to answer logical queries.
Frame and Feature-Context Video Super-Resolution
For video super-resolution, current state-of-the-art approaches either process multiple low-resolution (LR) frames to produce each output high-resolution (HR) frame separately in a sliding window fashion or recurrently exploit the previously estimated HR frames to super-resolve the following frame.
Cycle-IR: Deep Cyclic Image Retargeting
Our idea is built on the reverse mapping from the retargeted images to the given input images.
Feature Super-Resolution: Make Machine See More Clearly
In this paper, different from image super-resolution (ISR), we propose a novel super-resolution technique called feature super-resolution (FSR), which aims at enhancing the discriminatory power of small size image in order to provide high recognition precision for machine.
From the Periphery to the Center: Information Brokerage in an Evolving Network
We model integration as the interplay between the newcomer and the dynamics network and capture information brokerage using a process of relationship building.
