Search Results for author:
Found 78 papers, 21 papers with code
Read Extensively, Focus Smartly: A Cross-document Semantic Enhancement Method for Visual Documents NER
To deal with this problem, this work proposes a cross-document semantic enhancement method, which consists of two modules: 1) To prevent distractions from irrelevant regions in the current document, we design a learnable attention mask mechanism, which is used to adaptively filter redundant information in the current document.
Continual Pre-training of Language Models for Math Problem Understanding with Syntax-Aware Memory Network
In this paper, we study how to continually pre-train language models for improving the understanding of math problems.
Great~Truths~are ~Always ~Simple: A Rather Simple Knowledge Encoder for Enhancing the Commonsense Reasoning Capacity of Pre-Trained Models
Commonsense reasoning in natural language is a desired ability of artificial intelligent systems.
CipherDM: Secure Three-Party Inference for Diffusion Model Sampling
Diffusion Models (DMs) achieve state-of-the-art synthesis results in image generation and have been applied to various fields.
AResNet-ViT: A Hybrid CNN-Transformer Network for Benign and Malignant Breast Nodule Classification in Ultrasound Images
To address the challenges of similarity between lesions and surrounding tissues, overlapping appearances of partially benign and malignant nodules, and difficulty in classification, a deep learning network that integrates CNN and Transformer is proposed for the classification of benign and malignant breast lesions in ultrasound images.
What Matters in Learning Facts in Language Models? Multifaceted Knowledge Probing with Diverse Multi-Prompt Datasets
Large language models (LLMs) face issues in handling factual knowledge, making it vital to evaluate their true ability to understand facts.
Video Coding with Cross-Component Sample Offset
The input to the mapping is a group of reconstructed luma samples, and the output is an offset value applied on the center luma or co-located chroma sample.
MetaRM: Shifted Distributions Alignment via Meta-Learning
These two issues can be united as a challenge posed by the shifted distribution of the environment.
EulerFormer: Sequential User Behavior Modeling with Complex Vector Attention
The core of transformer architecture lies in the self-attention mechanism, which computes the pairwise attention scores in a sequence.
UAlign: Pushing the Limit of Template-free Retrosynthesis Prediction with Unsupervised SMILES Alignment
Single-step retrosynthesis prediction, a crucial step in the planning process, has witnessed a surge in interest in recent years due to advancements in AI for science.
PeLK: Parameter-efficient Large Kernel ConvNets with Peripheral Convolution
Due to these issues, current CNNs compromise to scale up to 51x51 in the form of stripe convolution (i. e., 51x5 + 5x51) and start to saturate as the kernel size continues growing.
Tracing the Roots of Facts in Multilingual Language Models: Independent, Shared, and Transferred Knowledge
Acquiring factual knowledge for language models (LMs) in low-resource languages poses a serious challenge, thus resorting to cross-lingual transfer in multilingual LMs (ML-LMs).
Language-Specific Neurons: The Key to Multilingual Capabilities in Large Language Models
Large language models (LLMs) demonstrate remarkable multilingual capabilities without being pre-trained on specially curated multilingual parallel corpora.
Adaptive Online Learning of Separable Path Graph Transforms for Intra-prediction
Current video coding standards, including H. 264/AVC, HEVC, and VVC, employ discrete cosine transform (DCT), discrete sine transform (DST), and secondary to Karhunen-Loeve transforms (KLTs) decorrelate the intra-prediction residuals.
IRConStyle: Image Restoration Framework Using Contrastive Learning and Style Transfer
By leveraging the flexibility of ConStyle, we develop a \textbf{general restoration network} for image restoration.
RA-Rec: An Efficient ID Representation Alignment Framework for LLM-based Recommendation
To address this limitation, we propose a new paradigm, ID representation, which incorporates pre-trained ID embeddings into LLMs in a complementary manner.
BioDrone: A Bionic Drone-based Single Object Tracking Benchmark for Robust Vision
These challenges are especially manifested in videos captured by unmanned aerial vehicles (UAV), where the target is usually far away from the camera and often with significant motion relative to the camera.
LIR: A Lightweight Baseline for Image Restoration
Recently, there have been significant advancements in Image Restoration based on CNN and transformer.
Robust single-particle cryo-EM image denoising and restoration
Cryo-electron microscopy (cryo-EM) has achieved near-atomic level resolution of biomolecules by reconstructing 2D micrographs.
UFIN: Universal Feature Interaction Network for Multi-Domain Click-Through Rate Prediction
To address the above issue, we propose the Universal Feature Interaction Network (UFIN) approach for CTR prediction.
Efficient-VQGAN: Towards High-Resolution Image Generation with Efficient Vision Transformers
Vector-quantized image modeling has shown great potential in synthesizing high-quality images.
Open Set Relation Extraction via Unknown-Aware Training
Inspired by text adversarial attacks, we adaptively apply small but critical perturbations to original training instances and thus synthesizing negative instances that are more likely to be mistaken by the model as known relations.
RE-Matching: A Fine-Grained Semantic Matching Method for Zero-Shot Relation Extraction
However, general matching methods lack explicit modeling of the above matching pattern.
InsPro: Propagating Instance Query and Proposal for Online Video Instance Segmentation
When using such a pair to predict an object instance on the current frame, not only the generated instance is automatically associated with its precursors on previous frames, but the model gets a good prior for predicting the same object.
Biomedical image analysis competitions: The state of current participation practice
Of these, 84% were based on standard architectures.
3D Matting: A Benchmark Study on Soft Segmentation Method for Pulmonary Nodules Applied in Computed Tomography
In this work, we introduce the image matting into the 3D scenes and use the alpha matte, i. e., a soft mask, to describe lesions in a 3D medical image.
3D Matting: A Soft Segmentation Method Applied in Computed Tomography
It can be caused by many factors, such as the imaging properties, pathological anatomy, and the weak representation of the binary masks, which brings challenges to accurate 3D segmentation.
Multimodal foundation models are better simulators of the human brain
Further, from the perspective of neural encoding (based on our foundation model), we find that both visual and lingual encoders trained multimodally are more brain-like compared with unimodal ones.
Attribute Controllable Beautiful Caucasian Face Generation by Aesthetics Driven Reinforcement Learning
In recent years, image generation has made great strides in improving the quality of images, producing high-fidelity ones.
Multi-target Tracking of Zebrafish based on Particle Filter
Firstly, by analyzing the motion characteristics of zebrafish, we establish an efficient hybrid motion model to predict its positions; then we establish an appearance model based on the predicted positions to predict the postures of every targets, meanwhile weigh the particles by comparing the difference of predicted pose and observation pose ; finally, we get the optimal position of single zebrafish through the weighted position, and use the joint particle filter to process trajectory linking of multiple zebrafish.
MLRIP: Pre-training a military language representation model with informative factual knowledge and professional knowledge base
Incorporating prior knowledge into pre-trained language models has proven to be effective for knowledge-driven NLP tasks, such as entity typing and relation extraction.
JDRec: Practical Actor-Critic Framework for Online Combinatorial Recommender System
A combinatorial recommender (CR) system feeds a list of items to a user at a time in the result page, in which the user behavior is affected by both contextual information and items.
QueryProp: Object Query Propagation for High-Performance Video Object Detection
The proposed QueryProp contains two propagation strategies: 1) query propagation is performed from sparse key frames to dense non-key frames to reduce the redundant computation on non-key frames; 2) query propagation is performed from previous key frames to the current key frame to improve feature representation by temporal context modeling.
Unsupervised Domain Adaptive Fundus Image Segmentation with Category-level Regularization
Existing unsupervised domain adaptation methods based on adversarial learning have achieved good performance in several medical imaging tasks.
PanopticDepth: A Unified Framework for Depth-aware Panoptic Segmentation
To overcome these limitations, we propose a unified framework for the DPS task by applying a dynamic convolution technique to both the PS and depth prediction tasks.
SOTVerse: A User-defined Task Space of Single Object Tracking
Single object tracking (SOT) research falls into a cycle -- trackers perform well on most benchmarks but quickly fail in challenging scenarios, causing researchers to doubt the insufficient data content and take more effort to construct larger datasets with more challenging situations.
Flexible Sampling for Long-tailed Skin Lesion Classification
To address this, in this paper, we propose a curriculum learning-based framework called Flexible Sampling for the long-tailed skin lesion classification task.
Three-dimensional Microstructural Image Synthesis from 2D Backscattered Electron Image of Cement Paste
This paper proposes a deep learning-based method for generating 3D microstructures from a single two-dimensional (2D) image, capable of producing high-quality, realistic 3D images at low cost.
An application of Pixel Interval Down-sampling (PID) for dense tiny microorganism counting on environmental microorganism images
This paper proposes a novel pixel interval down-sampling network (PID-Net) for dense tiny object (yeast cells) counting tasks with higher accuracy.
Global Instance Tracking: Locating Target More Like Humans
Finally, we design a scientific evaluation procedure using human capabilities as the baseline to judge tracking intelligence.
A Comprehensive Survey with Quantitative Comparison of Image Analysis Methods for Microorganism Biovolume Measurements
This study has high research significance and application value, which can be referred to microbial researchers to have a comprehensive understanding of microorganism biovolume measurements using digital image analysis methods and potential applications.
Neural Architecture Search for Inversion
Over the year, people have been using deep learning to tackle inversion problems, and we see the framework has been applied to build relationship between recording wavefield and velocity (Yang et al., 2016).
CUGE: A Chinese Language Understanding and Generation Evaluation Benchmark
We argue that for general-purpose language intelligence evaluation, the benchmark itself needs to be comprehensive and systematic.
Validating the Lottery Ticket Hypothesis with Inertial Manifold Theory
Despite achieving remarkable efficiency, traditional network pruning techniques often follow manually-crafted heuristics to generate pruned sparse networks.
Hierarchical Knowledge Guided Learning for Real-world Retinal Diseases Recognition
From a modeling perspective, most deep learning models trained on these datasets may lack the ability to generalize to rare diseases where only a few available samples are presented for training.
EMDS-7: Environmental Microorganism Image Dataset Seventh Version for Multiple Object Detection Evaluation
The Environmental Microorganism Image Dataset Seventh Version (EMDS-7) is a microscopic image data set, including the original Environmental Microorganism images (EMs) and the corresponding object labeling files in ". XML" format file.
Image Dataset Compression Based on Matrix Product States
Based on the MPS structure, we propose a new dataset compression method that compresses datasets by filtering long-range correlation information in task-agnostic scenarios and uses dataset distillation to supplement the information in task-specific scenarios.
Unsupervised Domain Adaptation for Retinal Vessel Segmentation with Adversarial Learning and Transfer Normalization
In this work, we explore unsupervised domain adaptation in retinal vessel segmentation by using entropy-based adversarial learning and transfer normalization layer to train a segmentation network, which generalizes well across domains and requires no annotation of the target domain.
A Comparison for Patch-level Classification of Deep Learning Methods on Transparent Environmental Microorganism Images: from Convolutional Neural Networks to Visual Transformers
We conclude that ViT performs the worst in classifying 8 * 8 pixel patches, but it outperforms most convolutional neural networks in classifying 224 * 224 pixel patches.
Medical Matting: A New Perspective on Medical Segmentation with Uncertainty
None of them investigate the influence of the ambiguous nature of the lesion itself. Inspired by image matting, this paper introduces alpha matte as a soft mask to represent uncertain areas in medical scenes and accordingly puts forward a new uncertainty quantification method to fill the gap of uncertainty research for lesion structure.
A State-of-the-art Survey of Object Detection Techniques in Microorganism Image Analysis: From Classical Methods to Deep Learning Approaches
In this review, first, we analyse the existing microorganism detection methods in chronological order, from traditional image processing and traditional machine learning to deep learning methods.
Relational Subsets Knowledge Distillation for Long-tailed Retinal Diseases Recognition
For example, there are estimated more than 40 different kinds of retinal diseases with variable morbidity, however with more than 30+ conditions are very rare from the global patient cohorts, which results in a typical long-tailed learning problem for deep learning-based screening models.
A Comprehensive Review of Image Analysis Methods for Microorganism Counting: From Classical Image Processing to Deep Learning Approaches
In this article, we have studied the development of microorganism counting methods using digital image analysis.
Improving Medical Image Classification with Label Noise Using Dual-uncertainty Estimation
In this paper, we systematically discuss and define the two common types of label noise in medical images - disagreement label noise from inconsistency expert opinions and single-target label noise from wrong diagnosis record.
A New Pairwise Deep Learning Feature For Environmental Microorganism Image Analysis
In order to fasten, low the cost, increase consistency and accuracy of identification, we propose the novel pairwise deep learning features to analyze microorganisms.
STS-GAN: Can We Synthesize Solid Texture with High Fidelity from Arbitrary 2D Exemplar?
Solid texture synthesis (STS), an effective way to extend a 2D exemplar to a 3D solid volume, exhibits advantages in computational photography.
Leveraging Regular Fundus Images for Training UWF Fundus Diagnosis Models via Adversarial Learning and Pseudo-Labeling
We propose the use of a modified cycle generative adversarial network (CycleGAN) model to bridge the gap between regular and UWF fundus and generate additional UWF fundus images for training.
Learning Category- and Instance-Aware Pixel Embedding for Fast Panoptic Segmentation
Panoptic segmentation (PS) is a complex scene understanding task that requires providing high-quality segmentation for both thing objects and stuff regions.
A Lite Microphone Array Beamforming Scheme with Maximum Signal-to-Noise Ratio Filter
Since space-domain information can be utilized, microphone array beamforming is often used to enhance the quality of the speech by suppressing directional disturbance.
Synergic Adversarial Label Learning for Grading Retinal Diseases via Knowledge Distillation and Multi-task Learning
In addition, we conduct additional experiments to show the effectiveness of SALL from the aspects of reliability and interpretability in the context of medical imaging application.
A Multi-scale CNN-CRF Framework for Environmental Microorganism Image Segmentation
In order to assist researchers to identify Environmental Microorganisms (EMs) effectively, a Multi-scale CNN-CRF (MSCC) framework for the EM image segmentation is proposed in this paper.
GlobalTrack: A Simple and Strong Baseline for Long-term Tracking
Specifically, we propose GlobalTrack, a pure global instance search based tracker that makes no assumption on the temporal consistency of the target's positions and scales.
TANet: Robust 3D Object Detection from Point Clouds with Triple Attention
In this paper, we focus on exploring the robustness of the 3D object detection in point clouds, which has been rarely discussed in existing approaches.
UER: An Open-Source Toolkit for Pre-training Models
Existing works, including ELMO and BERT, have revealed the importance of pre-training for NLP tasks.
SSAP: Single-Shot Instance Segmentation With Affinity Pyramid
Moreover, incorporating with the learned affinity pyramid, a novel cascaded graph partition module is presented to sequentially generate instances from coarse to fine.
Hyperspectral Image Classification with Deep Metric Learning and Conditional Random Field
To improve the classification performance in the context of hyperspectral image processing, many works have been developed based on two common strategies, namely the spatial-spectral information integration and the utilization of neural networks.
Ranked #8 on
Hyperspectral Image Classification
on Indian Pines
(Overall Accuracy metric)
General Classification
Hyperspectral Image Classification
+3
An End-to-End Solution for Effectively Demoting Watermarked Images in Image Search
We demonstrate that using these watermark signals together with the new metric in image search ranker can significantly demote the watermarked images during the online image ranking.
3D Object Detection Using Scale Invariant and Feature Reweighting Networks
On the other hand, our network obtains the useful features and suppresses the features with less information by a SENet module.
EANet: Enhancing Alignment for Cross-Domain Person Re-identification
Person re-identification (ReID) has achieved significant improvement under the single-domain setting.
GOT-10k: A Large High-Diversity Benchmark for Generic Object Tracking in the Wild
(5) Finally, we develop a comprehensive platform for the tracking community that offers full-featured evaluation toolkits, an online evaluation server, and a responsive leaderboard.
Deep Crisp Boundaries: From Boundaries to Higher-level Tasks
These ConvNet based edge detectors have approached human level performance on standard benchmarks.
Locality-Sensitive Deconvolution Networks With Gated Fusion for RGB-D Indoor Semantic Segmentation
This layer can learn to adjust the contributions of RGB and depth over each pixel for high-performance object recognition.
Ranked #85 on
Semantic Segmentation
on NYU Depth v2
Deep Crisp Boundaries
Edge detection had made significant progress with the help of deep Convolutional Networks (ConvNet).
Query Adaptive Similarity Measure for RGB-D Object Recognition
The reasons are in two-fold: (1) existing similarity measures are sensitive to object pose and scale changes, as well as intra-class variations; and (2) effectively fusing RGB and depth cues is still an open problem.
Anatomical Feature-guided Volumeric Registration of Multimodal Prostate MRI
Prostate scans of the same patient taken in three different orientations are first aligned for the accurate detection of anatomical features in 3D.
