Search Results for author:
Found 52 papers, 27 papers with code
The NiuTrans Machine Translation Systems for WMT20
This paper describes NiuTrans neural machine translation systems of the WMT20 news translation tasks.
Focus-Driven Contrastive Learning for Medical Question Summarization
Automatic medical question summarization can significantly help the system to understand consumer health questions and retrieve correct answers.
DiffKAN-Inpainting: KAN-based Diffusion model for brain tumor inpainting
Brain tumors delay the standard preprocessing workflow for further examination.
Spectral Enhancement and Pseudo-Anchor Guidance for Infrared-Visible Person Re-Identification
The development of deep learning has facilitated the application of person re-identification (ReID) technology in intelligent security.
SlimGPT: Layer-wise Structured Pruning for Large Language Models
Large language models (LLMs) have garnered significant attention for their remarkable capabilities across various domains, whose vast parameter scales present challenges for practical deployment.
TimeRefine: Temporal Grounding with Time Refining Video LLM
Recent work has focused on enabling Video LLMs to perform video temporal grounding via next-token prediction of temporal timestamps.
Simple but Efficient: A Multi-Scenario Nearline Retrieval Framework for Recommendation on Taobao
In recommendation systems, the matching stage is becoming increasingly critical, serving as the upper limit for the entire recommendation process.
Deformation-Recovery Diffusion Model (DRDM): Instance Deformation for Image Manipulation and Synthesis
The further experimental results in downstream tasks, 2D image segmentation and 3D image registration, indicate significant improvements resulting from DRDM, showcasing the potential of our model to advance image manipulation and synthesis in medical imaging and beyond.
HoneyGPT: Breaking the Trilemma in Terminal Honeypots with Large Language Model
Our evaluation of HoneyGPT comprises a baseline comparison based on a collected dataset and a three-month field evaluation.
VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos
Specifically, we incorporate multigranularity information into a tree-based representation, allowing VideoTree to extract query-relevant details from long videos in a coarse-to-fine manner.
VMambaMorph: a Multi-Modality Deformable Image Registration Framework based on Visual State Space Model with Cross-Scan Module
This novel hybrid VMamba-CNN network is designed specifically for 3D image registration.
Unleashing Large Language Models' Proficiency in Zero-shot Essay Scoring
Then, an LLM is prompted to extract trait scores from several conversational rounds, each round scoring one of the traits based on the scoring criteria.
FPT: Feature Prompt Tuning for Few-shot Readability Assessment
Our proposed method establishes a new architecture for prompt tuning that sheds light on how linguistic features can be easily adapted to linguistic-related tasks.
OC4-ReID: Occluded Cloth-Changing Person Re-Identification
The study of Cloth-Changing Person Re-identification (CC-ReID) focuses on retrieving specific pedestrians when their clothing has changed, typically under the assumption that the entire pedestrian images are visible.
DAM: Dynamic Adapter Merging for Continual Video QA Learning
Our DAM model outperforms prior state-of-the-art continual learning approaches by 9. 1% while exhibiting 1. 9% less forgetting on 6 VidQA datasets spanning various domains.
Weak-Mamba-UNet: Visual Mamba Makes CNN and ViT Work Better for Scribble-based Medical Image Segmentation
Medical image segmentation is increasingly reliant on deep learning techniques, yet the promising performance often come with high annotation costs.
Semi-Mamba-UNet: Pixel-Level Contrastive and Pixel-Level Cross-Supervised Visual Mamba-based UNet for Semi-Supervised Medical Image Segmentation
Medical image segmentation is essential in diagnostics, treatment planning, and healthcare, with deep learning offering promising advancements.
Mamba-UNet: UNet-Like Pure Visual Mamba for Medical Image Segmentation
Mamba-UNet adopts a pure Visual Mamba (VMamba)-based encoder-decoder structure, infused with skip connections to preserve spatial information across different scales of the network.
A Simple LLM Framework for Long-Range Video Question-Answering
Furthermore, we show that a specialized prompt that asks the LLM first to summarize the noisy short-term visual captions and then answer a given input question leads to a significant LVQA performance boost.
Ranked #2 on
Zero-Shot Video Question Answer
on NExT-GQA
Residual Aligner-based Network (RAN): Motion-separable structure for coarse-to-fine discontinuous deformable registration
Deformable image registration, the estimation of the spatial transformation between different images, is an important task in medical imaging.
Ranked #1 on
Image Registration
on Unpaired-lung-CT
Computed Tomography (CT)
Deformable Medical Image Registration
+2
Unified Coarse-to-Fine Alignment for Video-Text Retrieval
Specifically, our model captures the cross-modal similarity information at different granularity levels.
Ranked #12 on
Video Retrieval
on MSR-VTT
Investigation of temperature stress tolerance in Arabidopsis STTM165/166 using electrophysiology and RNA-Seq
These findings provide experimental evidence for the use of plant electrical signals in characterizing stress tolerance and explore potential ion mechanisms through patch-clamp recording and DEG Gene Ontology analysis.
Towards Hierarchical Policy Learning for Conversational Recommendation with Hypergraph-based Reinforcement Learning
Conversational recommendation systems (CRS) aim to timely and proactively acquire user dynamic preferred attributes through conversations for item recommendation.
Measuring complex refractive index through deeplearning-enabled optical reflectometry
Optical spectroscopy is indispensable for research and development in nanoscience and nanotechnology, microelectronics, energy, and advanced manufacturing.
A Unified Neural Network Model for Readability Assessment with Feature Projection and Length-Balanced Loss
For readability assessment, traditional methods mainly employ machine learning classifiers with hundreds of linguistic features.
EllipsoNet: Deep-learning-enabled optical ellipsometry for complex thin films
Optical spectroscopy is indispensable for research and development in nanoscience and nanotechnology, microelectronics, energy, and advanced manufacturing.
Focus-Driven Contrastive Learniang for Medical Question Summarization
Automatic medical question summarization can significantly help the system to understand consumer health questions and retrieve correct answers.
Multi-level Contrastive Learning Framework for Sequential Recommendation
Different from the previous contrastive learning-based methods for SR, MCLSR learns the representations of users and items through a cross-view contrastive learning paradigm from four specific views at two different levels (i. e., interest- and feature-level).
Improving Knowledge-aware Recommendation with Multi-level Interactive Contrastive Learning
Specifically, we first construct local and non-local graphs for user/item in KG, exploring more KG facts for KGR.
Triple-View Feature Learning for Medical Image Segmentation
The confidence of each model gets improved through the other two views of the feature learning.
When CNN Meet with ViT: Towards Semi-Supervised Learning for Multi-Class Medical Image Semantic Segmentation
A topological exploration of all alternative supervision modes with CNN and ViT are detailed validated, demonstrating the most promising performance and specific setting of our method on semi-supervised medical image segmentation tasks.
Person-job fit estimation from candidate profile and related recruitment history with co-attention neural networks
Existing studies on person-job fit, however, mainly focus on calculating the similarity between the candidate resumes and the job postings on the basis of their contents, without taking the recruiters' experience (i. e., historical successful recruitment records) into consideration.
Accurate Virus Identification with Interpretable Raman Signatures by Machine Learning
We present such a machine learning approach for analyzing Raman spectra of human and avian viruses.
Recursive Deformable Image Registration Network with Mutual Attention
Deformable image registration, estimating the spatial transformation between different images, is an important task in medical imaging.
Ranked #3 on
Image Registration
on Unpaired-lung-CT
Multi-level Cross-view Contrastive Learning for Knowledge-aware Recommender System
Different from traditional contrastive learning methods which generate two graph views by uniform data augmentation schemes such as corruption or dropping, we comprehensively consider three different graph views for KG-aware recommendation, including global-level structural view, local-level collaborative and semantic views.
Residual Aligner Network
Image registration is important for medical imaging, the estimation of the spatial transformation between different images.
Region Semantically Aligned Network for Zero-Shot Learning
Zero-shot learning (ZSL) aims to recognize unseen classes based on the knowledge of seen classes.
Global Context Enhanced Graph Neural Networks for Session-based Recommendation
In GCE-GNN, we propose a novel global-level item representation learning layer, which employs a session-aware attention mechanism to recursively incorporate the neighbors' embeddings of each node on the global graph.
Atrous Residual Interconnected Encoder to Attention Decoder Framework for Vertebrae Segmentation via 3D Volumetric CT Images
The proposed model is based on the structure of encoder to decoder, using layer normalization to optimize mini-batch training performance.
Quadruple Augmented Pyramid Network for Multi-class COVID-19 Segmentation via CT
COVID-19, a new strain of coronavirus disease, has been one of the most serious and infectious disease in the world.
Learning Light-Weight Translation Models from Deep Transformer
We proposed a novel group-permutation based knowledge distillation approach to compressing the deep Transformer model into a shallow model.
Exploiting Group-level Behavior Pattern forSession-based Recommendation
In RNMSR, we propose to learn the user preference from both instance-level and group-level, respectively: (i) instance-level, which employs GNNs on a similarity-based item-pairwise session graph to capture the users' preference in instance-level.
Exploring Global Information for Session-based Recommendation
Based on BGNN, we propose a novel approach, called Session-based Recommendation with Global Information (SRGI), which infers the user preferences via fully exploring global item-transitions over all sessions from two different perspectives: (i) Fusion-based Model (SRGI-FM), which recursively incorporates the neighbor embeddings of each node on global graph into the learning process of session level item representation; and (ii) Constrained-based Model (SRGI-CM), which treats the global-level item-transition information as a constraint to ensure the learned item embeddings are consistent with the global item-transition.
User-based Network Embedding for Collective Opinion Spammer Detection
Due to the huge commercial interests behind online reviews, a tremendousamount of spammers manufacture spam reviews for product reputation manipulation.
Shallow-to-Deep Training for Neural Machine Translation
We find that stacking layers is helpful in improving the representation ability of NMT models and adjacent layers perform similarly.
Weight Distillation: Transferring the Knowledge in Neural Network Parameters
Inspired by this, we investigate methods of model acceleration and compression in another line of research.
Deep Learning in Medical Ultrasound Image Segmentation: a Review
Applying machine learning technologies, especially deep learning, into medical image segmentation is being widely studied because of its state-of-the-art performance and results.
A Novel and Efficient Tumor Detection Framework for Pancreatic Cancer via CT Images
Experimental results achieve competitive performance in detection with the AUC of 0. 9455, which outperforms other state-of-the-art methods to our best of knowledge, demonstrating the proposed framework can detect the tumor of pancreatic cancer efficiently and accurately.
A Single RGB Camera Based Gait Analysis with a Mobile Tele-Robot for Healthcare
As gait analysis with a single camera is much more challenging compared to previous works utilizing multi-cameras, a RGB-D camera or wearable sensors, we propose using vision-based human pose estimation approaches.
The NiuTrans Machine Translation Systems for WMT19
We participated in 13 translation directions, including 11 supervised tasks, namely EN↔{ZH, DE, RU, KK, LT}, GU→EN and the unsupervised DE↔CS sub-track.
