Search Results for author:
Found 41 papers, 12 papers with code
Slot Dependency Modeling for Zero-Shot Cross-Domain Dialogue State Tracking
Zero-shot learning for Dialogue State Tracking (DST) focuses on generalizing to an unseen domain without the expense of collecting in domain data.
AlignVSR: Audio-Visual Cross-Modal Alignment for Visual Speech Recognition
Then, based on the temporal correspondence between audio and video, a frame-level local alignment loss is introduced to refine the global alignment, improving the utility of the audio information.
Generalization Boosted Adapter for Open-Vocabulary Segmentation
To address these limitations, we propose Generalization Boosted Adapter (GBA), a novel adapter strategy that enhances the generalization and robustness of VLMs for open-vocabulary segmentation.
PSTNet: Enhanced Polyp Segmentation with Multi-scale Alignment and Frequency Domain Integration
Accurate segmentation of colorectal polyps in colonoscopy images is crucial for effective diagnosis and management of colorectal cancer (CRC).
The Prevalence of Neural Collapse in Neural Multivariate Regression
After empirically establishing the prevalence of (NRC1)-(NRC3) for a variety of datasets and network architectures, we provide an explanation of these phenomena by modeling the regression task in the context of the Unconstrained Feature Model (UFM), in which the last layer feature vectors are treated as free variables when minimizing the loss function.
Automatic Medical Report Generation: Methods and Applications
The increasing demand for medical imaging has surpassed the capacity of available radiologists, leading to diagnostic delays and potential misdiagnoses.
HCF-Net: Hierarchical Context Fusion Network for Infrared Small Object Detection
Infrared small object detection is an important computer vision task involving the recognition and localization of tiny objects in infrared images, which usually contain only a few pixels.
Cross Entropy versus Label Smoothing: A Neural Collapse Perspective
We first show empirically that models trained with label smoothing converge faster to neural collapse solutions and attain a stronger level of neural collapse.
Local Feature Matching Using Deep Learning: A Survey
The objective of this endeavor is to furnish a comprehensive overview of local feature matching methods.
Boosting Few-Shot Segmentation via Instance-Aware Data Augmentation and Local Consensus Guided Cross Attention
On the other hand, the large visual difference between query and support images may hinder knowledge transfer and cripple the segmentation performance.
Spectral Prompt Tuning:Unveiling Unseen Classes for Zero-Shot Semantic Segmentation
Recently, CLIP has found practical utility in the domain of pixel-level zero-shot segmentation tasks.
Advances in Embodied Navigation Using Large Language Models: A Survey
This article offers an exhaustive summary of the symbiosis between LLMs and embodied intelligence with a focus on navigation.
Knowledge-driven Meta-learning for CSI Feedback
In this article, a knowledge-driven meta-learning approach is proposed, where the DL model initialized by the meta model obtained from meta training phase is able to achieve rapid convergence when facing a new scenario during target retraining phase.
VisionFM: a Multi-Modal Multi-Task Vision Foundation Model for Generalist Ophthalmic Artificial Intelligence
To be commensurate with this capacity, in addition to the real data used for pre-training, we also generated and leveraged synthetic ophthalmic imaging data.
Recursively Summarizing Enables Long-Term Dialogue Memory in Large Language Models
We evaluate our method on both open and closed LLMs, and the experiments on the widely-used public dataset show that our method can generate more consistent responses in a long-context conversation.
Divide, Conquer, and Combine: Mixture of Semantic-Independent Experts for Zero-Shot Dialogue State Tracking
Zero-shot transfer learning for Dialogue State Tracking (DST) helps to handle a variety of task-oriented dialogue domains without the cost of collecting in-domain data.
Meta Omnium: A Benchmark for General-Purpose Learning-to-Learn
Meta-learning and other approaches to few-shot learning are widely studied for image recognition, and are increasingly applied to other vision tasks such as pose estimation and dense prediction.
A Knowledge-Driven Meta-Learning Method for CSI Feedback
Recently, deep learning (DL) has been introduced to enhance CSI feedback in massive MIMO application, where the massive collected training data and lengthy training time are costly and impractical for realistic deployment.
A Comprehensive Survey on Video Saliency Detection with Auditory Information: the Audio-visual Consistency Perceptual is the Key!
Video saliency detection (VSD) aims at fast locating the most attractive objects/things/patterns in a given video clip.
Deep CardioSound-An Ensembled Deep Learning Model for Heart Sound MultiLabelling
Heart sound diagnosis and classification play an essential role in detecting cardiovascular disorders, especially when the remote diagnosis becomes standard clinical practice.
Distribution Locational Marginal Pricing Under Uncertainty Considering Coordination of Distribution and Wholesale Markets
An effective distribution electricity market (DEM) is required to manage the rapidly growing small-scale distributed energy resources (DERs) in distribution systems (DSs).
A New Weakly Supervised Learning Approach for Real-time Iron Ore Feed Load Estimation
Iron ore feed load control is one of the most critical settings in a mineral grinding process, directly impacting the quality of final products.
A Time-Varying Network for Cryptocurrencies
To investigate these effects, we build a time-varying network for cryptocurrencies, based on the evolution of return cross-predictability and technological similarities.
Renormalization of quasisymmetric functions
As a natural basis of the Hopf algebra of quasisymmetric functions, monomial quasisymmetric functions are formal power series defined from compositions.
Combinatorics Mathematical Physics Mathematical Physics Number Theory Quantum Algebra 05E05, 81%15, 16T05, 17B38, 11M32, 16W99, 11B73
Vision-based Price Suggestion for Online Second-hand Items
Then, we design a vision-based price suggestion module which takes the extracted visual features along with some statistical item features from the shopping platform as the inputs to determine whether an uploaded item image is qualified for price suggestion by a binary classification model, and provide price suggestions for items with qualified images by a regression model.
Document-level Relation Extraction with Dual-tier Heterogeneous Graph
Document-level relation extraction (RE) poses new challenges over its sentence-level counterpart since it requires an adequate comprehension of the whole document and the multi-hop reasoning ability across multiple sentences to reach the final result.
Intelligent Reflecting Surface Enhanced Indoor Robot Path Planning: A Radio Map based Approach
Based on the obtained channel power gain map, the communication-aware robot path planing problem is solved by exploiting graph theory.
Intelligent Reflecting Surface Enhanced Indoor Robot Path Planning Using Radio Maps
Based on the obtained channel power gain map, the communication-aware robot path planing problem is solved as a shortest path problem by exploiting graph theory.
A Relation-Specific Attention Network for Joint Entity and Relation Extraction
Joint extraction of entities and relations is an important task in natural language processing (NLP), which aims to capture all relational triplets from plain texts.
Ranked #11 on
Relation Extraction
on WebNLG
Exploiting Intelligent Reflecting Surfaces in NOMA Networks: Joint Beamforming Optimization
Our goal is to maximize the sum rate of all users by jointly optimizing the active beamforming at the BS and the passive beamforming at the IRS, subject to successive interference cancellation decoding rate conditions and IRS reflecting elements constraints.
Deep Active Learning for Anchor User Prediction
Due to the expensive costs of labeling anchor users for training prediction models, we consider in this paper the problem of minimizing the number of user pairs across multiple networks for labeling as to improve the accuracy of the prediction.
Improving Knowledge Graph Embedding Using Simple Constraints
We examine non-negativity constraints on entity representations and approximate entailment constraints on relation representations.
Modeling Text with Graph Convolutional Network for Cross-Modal Information Retrieval
A dual-path neural network model is proposed for couple feature learning in cross-modal information retrieval.
Knowledge Graph Embedding with Iterative Guidance from Soft Rules
In this paper, we propose Rule-Guided Embedding (RUGE), a novel paradigm of KG embedding with iterative guidance from soft rules.
Ranked #2 on
Link Prediction
on YAGO37
Joint News, Attention Spillover,and Market Returns
We analyze over 2. 6 million news articles and propose a novel measure of aggregate joint news coverage of firms.
