Search Results for author:
Found 26 papers, 12 papers with code
Key Mention Pairs Guided Document-Level Relation Extraction
To this end, we propose a novel DocRE model called Key Mention pairs Guided Relation Extractor (KMGRE) to directly model mention-level relations, containing two modules: a mention-level relation extractor and a key instance classifier.
CETA: A Consensus Enhanced Training Approach for Denoising in Distantly Supervised Relation Extraction
This paper proposes a sentence-level DSRE method beyond typical instance selection approaches by preventing samples from falling into the wrong classification space on the feature space.
Explore Better Relative Position Embeddings from Encoding Perspective for Transformer Models
Relative position embedding (RPE) is a successful method to explicitly and efficaciously encode position information into Transformer models.
Fine-grained Factual Consistency Assessment for Abstractive Summarization Models
Fact consistency assessment requires the reasoning capability to find subtle clues to identify whether a model-generated summary is consistent with the original document.
End-To-End Underwater Video Enhancement: Dataset and Model
To fill this gap, we construct the Synthetic Underwater Video Enhancement (SUVE) dataset, comprising 840 diverse underwater-style videos paired with ground-truth reference videos.
Joint Attention-Guided Feature Fusion Network for Saliency Detection of Surface Defects
To address these issues, we propose a joint attention-guided feature fusion network (JAFFNet) for saliency detection of surface defects based on the encoder-decoder network.
NID-SLAM: Neural Implicit Representation-based RGB-D SLAM in dynamic environments
In this paper we present NID-SLAM, which significantly improves the performance of neural SLAM in dynamic environments.
UIEDP:Underwater Image Enhancement with Diffusion Prior
To address this issue, we propose UIE with Diffusion Prior (UIEDP), a novel framework treating UIE as a posterior distribution sampling process of clear images conditioned on degraded underwater inputs.
Bold but Cautious: Unlocking the Potential of Personalized Federated Learning through Cautiously Aggressive Collaboration
The reasoning behind this approach is understandable, as localizing parameters that are easily influenced by non-IID data can prevent the potential negative effect of collaboration.
Take Your Pick: Enabling Effective Personalized Federated Learning within Low-dimensional Feature Space
FedPick achieves PFL in the low-dimensional feature space by selecting task-relevant features adaptively for each client from the features generated by the global encoder based on its local data distribution.
3Deformer: A Common Framework for Image-Guided Mesh Deformation
Unlike these studies, our 3Deformer is a non-training and common framework, which only requires supervision of readily-available semantic images, and is compatible with editing various objects unlimited by datasets.
Unlocking the Potential of Federated Learning for Deeper Models
Our further investigation shows that the decline is due to the continuous accumulation of dissimilarities among client models during the layer-by-layer back-propagation process, which we refer to as "divergence accumulation."
SentiStory: A Multi-Layered Sentiment-Aware Generative Model for Visual Storytelling
The visual storytelling (VIST) task aims at generating reasonable, human-like and coherent stories with the image streams as input.
Ranked #5 on
Visual Storytelling
on VIST
Convex Augmentation for Total Variation Based Phase Retrieval
Phase retrieval is an important problem with significant physical and industrial applications.
WeNet 2.0: More Productive End-to-End Speech Recognition Toolkit
Recently, we made available WeNet, a production-oriented end-to-end speech recognition toolkit, which introduces a unified two-pass (U2) framework and a built-in runtime to address the streaming and non-streaming decoding modes in a single model.
MARVEL: Raster Manga Vectorization via Primitive-wise Deep Reinforcement Learning
Manga is a fashionable Japanese-style comic form that is composed of black-and-white strokes and is generally displayed as raster images on digital devices.
ArtCoder: An End-to-End Method for Generating Scanning-Robust Stylized QR Codes
Quick Response (QR) code is one of the most worldwide used two-dimensional codes.
DAT: Training Deep Networks Robust To Label-Noise by Matching the Feature Distributions
Firstly, methods based on the noise probability modeling can only be applied to class-level noisy labels.
You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection
Can Transformer perform 2D object- and region-level recognition from a pure sequence-to-sequence perspective with minimal knowledge about the 2D spatial structure?
Ranked #30 on
Object Detection
on COCO-O
Visformer: The Vision-friendly Transformer
The past year has witnessed the rapid development of applying the Transformer module to vision problems.
Ranked #507 on
Image Classification
on ImageNet
SelectScale: Mining More Patterns from Images via Selective and Soft Dropout
Instead of randomly dropping units, SelectScale selects the important features in networks and adjusts them during training.
ACSC: Automatic Calibration for Non-repetitive Scanning Solid-State LiDAR and Camera Systems
Recently, the rapid development of Solid-State LiDAR (SSL) enables low-cost and efficient obtainment of 3D point clouds from the environment, which has inspired a large quantity of studies and applications.
An End-to-end Method for Producing Scanning-robust Stylized QR Codes
Quick Response (QR) code is one of the most worldwide used two-dimensional codes.~Traditional QR codes appear as random collections of black-and-white modules that lack visual semantics and aesthetic elements, which inspires the recent works to beautify the appearances of QR codes.
A Survey on Incorporating Domain Knowledge into Deep Learning for Medical Image Analysis
Although deep learning models like CNNs have achieved great success in medical image analysis, the small size of medical datasets remains a major bottleneck in this area.
MangaGAN: Unpaired Photo-to-Manga Translation Based on The Methodology of Manga Drawing
Manga is a world popular comic form originated in Japan, which typically employs black-and-white stroke lines and geometric exaggeration to describe humans' appearances, poses, and actions.
Network Adjustment: Channel Search Guided by FLOPs Utilization Ratio
Automatic designing computationally efficient neural networks has received much attention in recent years.
