Search Results for author:
Found 79 papers, 37 papers with code
Leveraging Bidding Graphs for Advertiser-Aware Relevance Modeling in Sponsored Search
As the fundamental basis of sponsored search, relevance modeling has attracted increasing attention due to the tremendous practical value.
Weakly Supervised Semantic Segmentation with Boundary Exploration
Weakly supervised semantic segmentation with image-level labels has attracted a lot of attention recently because these labels are already available in most datasets.
Unsupervised Adverbial Identification in Modern Chinese Literature
In Chinese, the derivation may be marked either with the standard adverbial marker DI, or the non-standard marker DE.
Learning Flow Fields in Attention for Controllable Person Image Generation
Additionally, we show that our loss is model-agnostic and can be used to improve the performance of other diffusion models.
Stain-aware Domain Alignment for Imbalance Blood Cell Classification
In real-world scenarios, blood cell image datasets often present the issues of domain shift and data imbalance, posing challenges for accurate blood cell identification.
From Machine Learning to Machine Unlearning: Complying with GDPR's Right to be Forgotten while Maintaining Business Value of Predictive Models
Recent privacy regulations (e. g., GDPR) grant data subjects the `Right to Be Forgotten' (RTBF) and mandate companies to fulfill data erasure requests from data subjects.
ChemSafetyBench: Benchmarking LLM Safety on Chemistry Domain
To address this issue in the field of chemistry, we introduce ChemSafetyBench, a benchmark designed to evaluate the accuracy and safety of LLM responses.
GSEditPro: 3D Gaussian Splatting Editing with Attention-based Progressive Localization
With the emergence of large-scale Text-to-Image(T2I) models and implicit 3D representations like Neural Radiance Fields (NeRF), many text-driven generative editing methods based on NeRF have appeared.
StdGEN: Semantic-Decomposed 3D Character Generation from Single Images
We present StdGEN, an innovative pipeline for generating semantically decomposed high-quality 3D characters from single images, enabling broad applications in virtual reality, gaming, and filmmaking, etc.
MarDini: Masked Autoregressive Diffusion for Video Generation at Scale
We introduce MarDini, a new family of video diffusion models that integrate the advantages of masked auto-regression (MAR) into a unified diffusion model (DM) framework.
KAN4TSF: Are KAN and KAN-based models Effective for Time Series Forecasting?
To this end, we introduce the Kolmogorov-Arnold Network (KAN) into time series forecasting research, which has better mathematical properties and interpretability.
Swarm Intelligence in Geo-Localization: A Multi-Agent Large Vision-Language Model Collaborative Framework
Visual geo-localization demands in-depth knowledge and advanced reasoning skills to associate images with precise real-world geographic locations.
GARLIC: GPT-Augmented Reinforcement Learning with Intelligent Control for Vehicle Dispatching
As urban residents demand higher travel quality, vehicle dispatch has become a critical component of online ride-hailing services.
Towards Practical Human Motion Prediction with LiDAR Point Clouds
In this paper, we propose \textit{LiDAR-HMP}, the first single-LiDAR-based 3D human motion prediction approach, which receives the raw LiDAR point cloud as input and forecasts future 3D human poses directly.
LiveHPS++: Robust and Coherent Motion Capture in Dynamic Free Environment
LiDAR-based human motion capture has garnered significant interest in recent years for its practicability in large-scale and unconstrained environments.
SoftDedup: an Efficient Data Reweighting Method for Speeding Up Language Model Pre-training
The effectiveness of large language models (LLMs) is often hindered by duplicated data in their extensive pre-training datasets.
Boosting Consistency in Story Visualization with Rich-Contextual Conditional Diffusion Models
Moreover, RCDMs can generate consistent stories with a single forward inference compared to autoregressive models.
Adapting Job Recommendations to User Preference Drift with Behavioral-Semantic Fusion Learning
To address this issue, we propose a novel session-based framework, BISTRO, to timely model user preference through fusion learning of semantic and behavioral information.
V-Express: Conditional Dropout for Progressive Training of Portrait Video Generation
In our work on portrait video generation, we identified audio signals as particularly weak, often overshadowed by stronger signals such as facial pose and reference image.
DSDL: Data Set Description Language for Bridging Modalities and Tasks in AI Data
In the era of artificial intelligence, the diversity of data modalities and annotation formats often renders data unusable directly, requiring understanding and format conversion before it can be used by researchers or developers with different needs.
Ensembling Diffusion Models via Adaptive Feature Aggregation
In this paper, we propose a novel ensembling method, Adaptive Feature Aggregation (AFA), which dynamically adjusts the contributions of multiple models at the feature level according to various states (i. e., prompts, initial noises, denoising steps, and spatial locations), thereby keeping the advantages of multiple diffusion models, while suppressing their disadvantages.
G3: An Effective and Adaptive Framework for Worldwide Geolocalization Using Large Multi-Modality Models
Worldwide geolocalization aims to locate the precise location at the coordinate level of photos taken anywhere on the Earth.
WiTUnet: A U-Shaped Architecture Integrating CNN and Transformer for Improved Feature Alignment and Local Information Fusion
Low-dose computed tomography (LDCT) has become the technology of choice for diagnostic medical imaging, given its lower radiation dose compared to standard CT, despite increasing image noise and potentially affecting diagnostic accuracy.
A Unified Framework for Human-centric Point Cloud Video Understanding
Human-centric Point Cloud Video Understanding (PVU) is an emerging field focused on extracting and interpreting human-related features from sequences of human point clouds, further advancing downstream human-centric tasks and applications.
LiveHPS: LiDAR-based Scene-level Human Pose and Shape Estimation in Free Environment
For human-centric large-scale scenes, fine-grained modeling for 3D human global pose and shape is significant for scene understanding and can benefit many real-world applications.
Graph Contrastive Learning with Cohesive Subgraph Awareness
However, such stochastic augmentations may severely damage the intrinsic properties of a graph and deteriorate the following representation learning process.
Safety and Performance, Why Not Both? Bi-Objective Optimized Model Compression against Heterogeneous Attacks Toward AI Software Deployment
To mitigate this issue, AI software compression plays a crucial role, which aims to compress model size while keeping high performance.
From Authority-Respect to Grassroots-Dissent: Degree-Weighted Social Learning and Convergence Speed
Opinions are influenced by neighbors, with varying degrees of emphasis based on their connections.
Image Super-resolution Via Latent Diffusion: A Sampling-space Mixture Of Experts And Frequency-augmented Decoder Approach
To alleviate the huge computational cost required by pixel-based diffusion SR, latent-based methods utilize a feature encoder to transform the image and then implement the SR image generation in a compact latent space.
Effortless Cross-Platform Video Codec: A Codebook-Based Method
Due to the absence of autoregressive modeling and optical flow alignment, we can design an extremely minimalist framework that can greatly benefit computational efficiency.
Advancing Pose-Guided Image Synthesis with Progressive Conditional Diffusion Models
Specifically, in the first stage, we design a simple prior conditional diffusion model that predicts the global features of the target image by mining the global alignment relationship between pose coordinates and image appearance.
Algorithmic Recourse for Anomaly Detection in Multivariate Time Series
Anomaly detection in multivariate time series has received extensive study due to the wide spectrum of applications.
LogGPT: Log Anomaly Detection via GPT
However, there is a gap between language modeling and anomaly detection as the objective of training a sequential model via a language modeling loss is not directly related to anomaly detection.
Towards Real-Time Neural Video Codec for Cross-Platform Application Using Calibration Information
First, to solve the problem of inconsistency of codec caused by the uncertainty of floating point calculations across platforms, we design a calibration transmitting system to guarantee the consistent quantization of entropy parameters between the encoding and decoding stages.
VIGC: Visual Instruction Generation and Correction
A practical solution to this problem would be to utilize the available multimodal large language models (MLLMs) to generate instruction data for vision-language tasks.
Dynamic Low-Rank Instance Adaptation for Universal Neural Image Compression
We thus introduce a dynamic gating network on top of the low-rank adaptation method, in order to decide which decoder layer should employ adaptation.
IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models
Despite the simplicity of our method, an IP-Adapter with only 22M parameters can achieve comparable or even better performance to a fully fine-tuned image prompt model.
Ranked #2 on
Personalized Image Generation
on DreamBooth
RLTF: Reinforcement Learning from Unit Test Feedback
The goal of program synthesis, or code generation, is to generate executable code based on given descriptions.
FAME-ViL: Multi-Tasking Vision-Language Model for Heterogeneous Fashion Tasks
In the fashion domain, there exists a variety of vision-and-language (V+L) tasks, including cross-modal retrieval, text-guided image retrieval, multi-modal classification, and image captioning.
Achieving Counterfactual Fairness for Anomaly Detection
Ensuring fairness in anomaly detection models has received much attention recently as many anomaly detection applications involve human beings.
Slate-Aware Ranking for Recommendation
Therefore, the ranking stage is still essential for most applications to provide high-quality candidate set for the re-ranking stage.
Federated attention consistent learning models for prostate cancer diagnosis and Gleason grading
We assessed the effectiveness of FACL in cancer diagnosis and Gleason grading tasks using 19, 461 whole-slide images of prostate cancer from multiple centers.
Cross-center Early Sepsis Recognition by Medical Knowledge Guided Collaborative Learning for Data-scarce Hospitals
In this paper, for a common disease in ICU patients, sepsis, we propose a novel cross-center collaborative learning framework guided by medical knowledge, SofaNet, to achieve early recognition of this disease.
Vertical Federated Knowledge Transfer via Representation Distillation for Healthcare Collaboration Networks
In order to improve the information-sharing capability and innovation of various healthcare-related institutions, and then to establish a next-generation open medical collaboration network, we propose a unified framework for vertical federated knowledge transfer mechanism (VFedTrans) based on a novel cross-hospital representation distillation component.
Artificial intelligence for diagnosing and predicting survival of patients with renal cell carcinoma: Retrospective multi-center study
The OSrisk for the prediction of 5-year survival status achieved AUC of 0. 784 (0. 746-0. 819) in the TCGA cohort, which was further verified in the independent General cohort and the CPTAC cohort, with AUC of 0. 774 (0. 723-0. 820) and 0. 702 (0. 632-0. 765), respectively.
Controllable Person Image Synthesis with Pose-Constrained Latent Diffusion
Controllable person image synthesis aims at rendering a source image based on user-specified changes in body pose or appearance.
How To Prevent the Poor Performance Clients for Personalized Federated Learning?
Intuitively, these poor clients may come from biased universal information shared with others.
A Unified Knowledge Graph Augmentation Service for Boosting Domain-specific NLP Tasks
We propose KnowledgeDA, a unified domain language model development service to enhance the task-specific training procedure with domain knowledge graphs.
On Root Cause Localization and Anomaly Mitigation through Causal Inference
After that, we further propose an anomaly mitigation approach that aims to recommend mitigation actions on abnormal features to revert the abnormal outcomes such that the counterfactuals guided by the causal mechanism are normal.
RLogist: Fast Observation Strategy on Whole-slide Images with Deep Reinforcement Learning
Most of the existing methods rely on a multiple instance learning framework that requires densely sampling local patches at high magnification.
Resolution enhancement of NMR by decoupling with low-rank Hankel model
Nuclear magnetic resonance (NMR) spectroscopy has become a formidable tool for biochemistry and medicine.
Adap DP-FL: Differentially Private Federated Learning with Adaptive Noise
The heterogeneity and convergence of training parameters were simply not considered.
Gait Recognition in Large-scale Free Environment via Single LiDAR
Human gait recognition is crucial in multimedia, enabling identification through walking patterns without direct interaction, enhancing the integration across various media forms in real-world applications like smart homes, healthcare and non-intrusive security.
RAPO: An Adaptive Ranking Paradigm for Bilingual Lexicon Induction
Bilingual lexicon induction induces the word translations by aligning independently trained word embeddings in two languages.
DeepNoise: Signal and Noise Disentanglement based on Classifying Fluorescent Microscopy Images via Deep Learning
The high-content image-based assay is commonly leveraged for identifying the phenotypic impact of genetic perturbations in biology field.
Safety and Performance, Why not Both? Bi-Objective Optimized Model Compression toward AI Software Deployment
By simulating the attack mechanism as the safety test, SafeCompress can automatically compress a big model to a small one following the dynamic sparse training paradigm.
NMR spectrum reconstruction as a pattern recognition problem
A new deep neural network based on the WaveNet architecture (WNN) is presented, which is designed to grasp specific patterns in the NMR spectra.
Large-Scale Product Retrieval with Weakly Supervised Representation Learning
Large-scale weakly supervised product retrieval is a practically useful yet computationally challenging problem.
FashionViL: Fashion-Focused Vision-and-Language Representation Learning
We thus propose a Multi-View Contrastive Learning task for pulling closer the visual representation of one image to the compositional multimodal representation of another image+text.
Large-Scale Privacy-Preserving Network Embedding against Private Link Inference Attacks
Basically, we propose to perturb the original network by adding or removing links, and expect the embedding generated on the perturbed network can leak little information about private links but hold high utility for various downstream tasks.
Deep learning-based approach to reveal tumor mutational burden status from whole slide images across multiple cancer types
MC-TMB algorithm also exhibited good generalization on the external validation cohort with an AUC of 0. 732 (0. 683-0. 761), and better performance when compared to other methods.
UIGR: Unified Interactive Garment Retrieval
In this paper, we propose a Unified Interactive Garment Retrieval (UIGR) framework to unify TGR and VCR.
Node-Aligned Graph Convolutional Network for Whole-Slide Image Representation and Classification
In this paper, we propose a hierarchical global-to-local clustering strategy to build a Node-Aligned GCN (NAGCN) to represent WSI with rich local structural information as well as global distribution.
Data Valuation for Vertical Federated Learning: A Model-free and Privacy-preserving Method
In response, we propose FedValue, a privacy-preserving, task-specific but model-free data valuation method for VFL, which consists of a data valuation metric and a federated computation method.
HyObscure: Hybrid Obscuring for Privacy-Preserving Data Publishing
We then design a novel hybrid protection mechanism called HyObscure, to cross-iteratively optimize the generalization and obfuscation operations for maximum privacy protection under a certain utility guarantee.
Label Hierarchy Transition: Delving into Class Hierarchies to Enhance Deep Classifiers
Existing methods commonly address hierarchical classification by decoupling it into a series of multi-class classification tasks.
CoDiM: Learning with Noisy Labels via Contrastive Semi-Supervised Learning
Labels are costly and sometimes unreliable.
Ranked #5 on
Image Classification
on mini WebVision 1.0
Text-Based Person Search with Limited Data
Firstly, to fully utilize the existing small-scale benchmarking datasets for more discriminative feature learning, we introduce a cross-modal momentum contrastive learning framework to enrich the training data for a given mini-batch.
Ranked #12 on
Text based Person Retrieval
on CUHK-PEDES
(using extra training data)
Label Confusion Learning to Enhance Text Classification Models
LCM can learn label confusion to capture semantic overlap among labels by calculating the similarity between instances and labels during training and generate a better label distribution to replace the original one-hot label vector, thus improving the final classification performance.
Federated Crowdsensing: Framework and Challenges
In particular, we first propose a federated crowdsensing framework, which analyzes the privacy concerns of each crowdsensing stage (i. e., task creation, task assignment, task execution, and data aggregation) and discuss how federated learning techniques may take effect.
Microscope Based HER2 Scoring System
Recently, artificial intelligence (AI) has been used in various disease diagnosis to improve diagnostic accuracy and reliability, but the interpretation of diagnosis results is still an open problem.
Covidex: Neural Ranking Models and Keyword Search Infrastructure for the COVID-19 Open Research Dataset
We present Covidex, a search engine that exploits the latest neural ranking models to provide information access to the COVID-19 Open Research Dataset curated by the Allen Institute for AI.
Semi-Supervised Deep Learning Using Improved Unsupervised Discriminant Projection
Deep learning demands a huge amount of well-labeled data to train the network parameters.
CreditPrint: Credit Investigation via Geographic Footprints by Deep Learning
Credit investigation is critical for financial services.
SIMPLE: Statistical Inference on Membership Profiles in Large Networks
Both tests are of the Hotelling-type statistics based on the rows of empirical eigenvectors or their ratios, whose asymptotic covariance matrices are very challenging to derive and estimate.
Multi-Perspective Neural Architecture for Recommendation System
In one stage, the user and item are represented from multiple perspectives and in each perspective, the representations of user and item put attentions to each other.
Automatic Liver Lesion Segmentation Using A Deep Convolutional Neural Network Method
Liver lesion segmentation is an important step for liver cancer diagnosis, treatment planning and treatment evaluation.
MR-based synthetic CT generation using a deep convolutional neural network method
Applying a trained model to generate a complete sCT volume for each new patient MR image only took 9 s, which was much faster than the atlas‐based approach.
