Search Results for author:
Found 339 papers, 115 papers with code
LingJing at SemEval-2022 Task 1: Multi-task Self-supervised Pre-training for Multilingual Reverse Dictionary
This paper introduces the approach of Team LingJing’s experiments on SemEval-2022 Task 1 Comparing Dictionaries and Word Embeddings (CODWOE).
VPAI_Lab at MedVidQA 2022: A Two-Stage Cross-modal Fusion Method for Medical Instructional Video Classification
Given an input video, the MedVidCL task aims to correctly classify it into one of three following categories: Medical Instructional, Medical Non-instructional, and Non-medical.
LingJing at SemEval-2022 Task 3: Applying DeBERTa to Lexical-level Presupposed Relation Taxonomy with Knowledge Transfer
For the classification sub-task, we adopt the DeBERTa-v3 pre-trained model for fine-tuning datasets of different languages.
The First International Ancient Chinese Word Segmentation and POS Tagging Bakeoff: Overview of the EvaHan 2022 Evaluation Campaign
This paper presents the results of the First Ancient Chinese Word Segmentation and POS Tagging Bakeoff (EvaHan), which was held at the Second Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA) 2022, in the context of the 13th Edition of the Language Resources and Evaluation Conference (LREC 2022).
Align-smatch: A Novel Evaluation Method for Chinese Abstract Meaning Representation Parsing based on Alignment of Concept and Relation
Therefore, to make up for the vacancy of Chinese AMR parsing evaluation methods, based on AMR evaluation metric smatch, we have improved the algorithm of generating triples so that to make it compatible with concept alignment and relation alignment.
DynGL-SDP: Dynamic Graph Learning for Semantic Dependency Parsing
A recent success in semantic dependency parsing shows that graph neural networks can make significant accuracy improvements, owing to its powerful ability in learning expressive graph representations.
Continuing Pre-trained Model with Multiple Training Strategies for Emotional Classification
This paper describes the contribution of the LingJing team’s method to the Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis (WASSA) 2022 shared task on Emotion Classification.
A Knowledge storage and semantic space alignment Method for Multi-documents dialogue generation
Question Answering (QA) is a Natural Language Processing (NLP) task that can measure language and semantics understanding ability, it requires a system not only to retrieve relevant documents from a large number of articles but also to answer corresponding questions according to documents.
基于大规模语料库的《古籍汉字分级字表》研究(The Formulation of The graded Chinese character list of ancient books Based on Large-scale Corpus)
"《古籍汉字分级字表》是基于大规模古籍文本语料库、为辅助学习者古籍文献阅读而研制的分级字表。该字表填补了古籍字表研究成果的空缺, 依据各汉字学习优先级别的不同, 实现了古籍汉字的等级划分, 目前收录一级字105个, 二级字340个, 三级字555个。本文介绍了该字表研制的主要依据和基本步骤, 并将其与传统识字教材“三百千”及《现代汉语常用字表》进行比较, 验证了其收字的合理性。该字表有助于学习者优先掌握古籍文本常用字, 提升古籍阅读能力, 从而促进中华优秀传统文化的继承与发展。”
先秦词网构建及梵汉对比研究(The Construction of Pre-Qin Ancient Chinese WordNet and Cross Language Comparative Study between Ancient Sanskrit WordNet and Pre-Qin Ancient Chinese WordNet)
“先秦汉语在汉语史研究上具有重要地位, 然而以往的研究始终没有形成结构化的先秦词汇资源, 难以满足古汉语信息处理和跨语言对比的研究需要。国际上以英文词网(WordNet)的义类架构为基础, 已经建立了数十种语言的词网, 已经成为多语言自然语言处理和跨语言对比的基础资源。本文综述了国内外各种词网的构建情况, 特别是古代语言的词网和汉语词网, 然后详细介绍了先秦词网的构建和校正过程, 构建起了涵盖43591个词语、61227个义项、17975个义类的先秦汉语词网。本文还通过与古梵语词网的跨语言对比, 尝试分析这两种古老语言在词汇上的共性和差异, 初步验证先秦词网的有效性。”
中文词语离合现象识别研究(Research on Recognition of the Separation and Reunion Phenomena of Words in Chinese)
“汉语词语的离合现象是汉语中一种词语可分可合的特殊现象。本文采用字符级序列标注方法解决二字动词离合现象的自动识别问题, 以避免中文分词及词性标注的错误传递, 节省制定匹配规则与特征模板的人工开支。在训练过程中微调BERT中文预训练模型, 获取面向目标任务的字符向量表示, 并引入掩码机制对模型隐藏离用法中分离的词语, 减轻词语本身对识别结果的影响, 强化中间插入成分的学习, 并对前后语素采用不同的掩码以强调其出现顺序, 进而使模型具备了识别复杂及偶发性离用法的能力。为获得含有上下文信息的句子表达, 将原始的句子表达与采用掩码的句子表达分别输入两个不同参数的BiLSTM层进行训练, 最后采用CRF算法捕捉句子标签序列的依赖关系。本文提出的BERT MASK + 2BiLSTMs + CRF模型比现有最优的离合词识别模型提高了2. 85%的F1值。”
中文连动句语义关系识别研究(Research on Semantic Relation Recognition of Chinese Serial-verb Sentences)
“连动句是形如“NP+VP1+VP2”的句子, 句中含有两个或两个以上的动词(或动词结构)且动词的施事为同一对象。相同结构的连动句可以表示多种不同的语义关系。本文基于前人对连动句中VP1和VP2之间的语义关系分类, 标注了连动句语义关系数据集, 基于神经网络完成了对连动句语义关系的识别。该方法将连动句语义识别任务进行分解, 基于BERT进行编码, 利用BiLSTM-CRF先识别出连动句中连动词(VP)及其主语(NP), 再基于融合连动词信息的编码, 利用BiLSTM-Attention对连动词进行关系判别, 实验结果验证了所提方法的有效性。”
多轮对话的篇章级抽象语义表示标注体系研究(Research on Discourse-level Abstract Meaning Representation Annotation framework in Multi-round Dialogue)
对话分析是智能客服、聊天机器人等自然语言对话应用的基础课题, 而对话语料与常规书面语料有较大差异, 存在大量的称谓、情感短语、省略、语序颠倒、冗余等复杂现象, 对句法和语义分析器的影响较大, 对话自动分析的准确率相对书面语料一直不高。其主要原因在于对多轮对话缺乏严整的形式化描写方式, 不利于后续的分析计算。因此, 本文在梳理国内外针对对话的标注体系和语料库的基础上, 提出了基于抽象语义表示的篇章级多轮对话标注体系。具体探讨了了篇章级别的语义结构标注方法, 给出了词语和概念关系的对齐方案, 针对称谓语和情感短语增加了相应的语义关系和概念, 调整了表示主观情感词语的论元结构, 并对对话中一些特殊现象进行了规定, 设计了人工标注平台, 为大规模的多轮对话语料库标注与计算研究奠定基础。
基于深度学习的实体关系抽取研究综述(Review of Entity Relation Extraction based on deep learning)
作为信息抽取的一项核心子任务, 实体关系抽取对于知识图谱、智能问答、语义搜索等自然语言处理应用都十分重要。关系抽取在于从非结构化文本中自动地识别实体之间具有的某种语义关系。该文聚焦句子级别的关系抽取研究, 介绍用于关系抽取的主要数据集并对现有的技术作了阐述, 主要分为:有监督的关系抽取、远程监督的关系抽取和实体关系联合抽取。我们对比用于该任务的各种模型, 分析它们的贡献与缺 陷。最后介绍中文实体关系抽取的研究现状和方法。
基于神经网络的连动句识别(Recognition of serial-verb sentences based on Neural Network)
连动句是具有连动结构的句子, 是汉语中的特殊句法结构, 在现代汉语中十分常见且使用频繁。连动句语法结构和语义关系都很复杂, 在识别中存在许多问题, 对此本文针对连动句的识别问题进行了研究, 提出了一种基于神经网络的连动句识别方法。本方法分两步:第一步, 运用简单的规则对语料进行预处理;第二步, 用文本分类的思想, 使用BERT编码, 利用多层CNN与BiLSTM模型联合提取特征进行分类, 进而完成连动句识别任务。在人工标注的语料上进行实验, 实验结果达到92. 71%的准确率, F1值为87. 41%。
基于抽象语义表示的汉语疑问句的标注与分析(Chinese Interrogative Sentences Annotation and Analysis Based on the Abstract Meaning Representation)
疑问句的句法语义分析在搜索引擎、信息抽取和问答系统等领域有着广泛的应用。计算语言学多采取问句分类和句法分析相结合的方式来处理疑问句, 精度和效率还不理想。而疑问句的语言学研究成果丰富, 比如疑问句的结构类型、疑问焦点和疑问代词的非疑问用法等, 但缺乏系统的形式化表示。本文致力于解决这一难题, 采用基于图结构的汉语句子语义的整体表示方法—中文抽象语义表示(CAMR)来标注疑问句的语义结构, 将疑问焦点和整句语义一体化表示出来。然后选取了宾州中文树库CTB8. 0网络媒体语料、小学语文教材以及《小王子》中文译本的2万句语料中共计2071句疑问句, 统计了疑问句的主要特点。统计表明, 各种疑问代词都可以通过疑问概念amr-unknown和语义关系的组合来表示, 能够完整地表示出疑问句的关键信息、疑问焦点和语义结构。最后, 根据疑问代词所关联的语义关系, 统计了疑问焦点的概率分布, 其中原因、修饰语和受事的占比最高, 分别占26. 53%、16. 73%以及16. 44%。基于抽象语义表示的疑问句标注与分析可以为汉语疑问句研究提供基础理论与资源。
Building a Chinese AMR Bank with Concept and Relation Alignments
One significant change we have made to the AMR annotation methodology is the inclusion of the alignment between word tokens in the sentence and the concepts/relations in the CAMR annotation to make it easier for automatic parsers to model the correspondence between a sentence and its meaning representation.
Knowledge Transfer with Visual Prompt in multi-modal Dialogue Understanding and Generation
In this work, we propose a knowledge transfer method with visual prompt (VPTG) fusing multi-modal data, which is a flexible module that can utilize the text-only seq2seq model to handle visual dialogue tasks.
Event Signal Filtering via Probability Flux Estimation
The state and process information within events is modeled as continuous probability flux at threshold boundaries of the underlying irradiance diffusion.
Hierarchical Modeling for Medical Visual Question Answering with Cross-Attention Fusion
This study provides an effective pathway for hierarchical visual question answering systems, advancing medical image understanding.
Optimal Insurance in a Monopoly: Dual Utilities with Hidden Risk Attitudes
Notably, insurance coverage and premia are monotone in the level of risk aversion; the most risk-averse consumer receives full insurance $(\textit{efficiency at the top})$; the monopoly absorbs all surplus from the least-risk averse consumer; and consumers with a higher level of risk aversion induce a higher expected profit for the insurer.
Instruction-Aligned Visual Attention for Mitigating Hallucinations in Large Vision-Language Models
Despite the significant success of Large Vision-Language models(LVLMs), these models still suffer hallucinations when describing images, generating answers that include non-existent objects.
PHT-CAD: Efficient CAD Parametric Primitive Analysis with Progressive Hierarchical Tuning
Additionally, we propose PHT-CAD, a novel 2D PPA framework that harnesses the modality alignment and reasoning capabilities of Vision-Language Models (VLMs) for precise engineering drawing analysis.
Multi-modal Multi-platform Person Re-Identification: Benchmark and Method
To address these challenges, we introduce the MP-ReID benchmark, a novel dataset designed specifically for multi-modality and multi-platform ReID.
UMIT: Unifying Medical Imaging Tasks via Vision-Language Models
In addition, it is applicable to multiple imaging modalities (e. g., X-ray, CT and PET), covering a wide range of applications from basic diagnostics to complex lesion analysis.
DRoPE: Directional Rotary Position Embedding for Efficient Agent Interaction Modeling
We theoretically analyze DRoPE's correctness and efficiency, demonstrating its capability to simultaneously optimize trajectory generation accuracy, time complexity, and space complexity.
Adaptive Mixture of Experts Learning for Robust Audio Spoofing Detection
In audio spoofing detection, most studies rely on clean datasets, making models susceptible to real-world post-processing attacks, such as channel compression and noise.
Proxy-Tuning: Tailoring Multimodal Autoregressive Models for Subject-Driven Image Generation
Multimodal autoregressive (AR) models, based on next-token prediction and transformer architecture, have demonstrated remarkable capabilities in various multimodal tasks including text-to-image (T2I) generation.
VLForgery Face Triad: Detection, Localization and Attribution via Multimodal Large Language Models
In this work, we integrate Multimodal Large Language Models (MLLMs) within DM-based face forensics, and propose a fine-grained analysis triad framework called VLForgery, that can 1) predict falsified facial images; 2) locate the falsified face regions subjected to partial synthesis; and 3) attribute the synthesis with specific generators.
Small but Mighty: Enhancing Time Series Forecasting with Lightweight LLMs
By redefining the efficiency-accuracy trade-off landscape, this work establishes SLMs as viable alternatives to resource-intensive LLMs for practical time series forecasting.
DLF: Extreme Image Compression with Dual-generative Latent Fusion
DLF decomposes the latent into semantic and detail elements, compressing them through two distinct branches.
Towards Practical Real-Time Neural Video Compression
In practice, the coding speed of NVCs depends on 1) computational costs, and 2) non-computational operational costs, such as memory I/O and the number of function calls.
ChatReID: Open-ended Interactive Person Retrieval via Hierarchical Progressive Tuning for Vision Language Models
Person re-identification (Re-ID) is a critical task in human-centric intelligent systems, enabling consistent identification of individuals across different camera views using multi-modal query information.
Accurate and Scalable Graph Neural Networks via Message Invariance
Message passing-based graph neural networks (GNNs) have achieved great success in many real-world applications.
Accurate Pose Estimation for Flight Platforms based on Divergent Multi-Aperture Imaging System
To this end we propose a calibration method for DMAIS based on the 3D calibration field.}
Measuring trade costs and analyzing the determinants of trade growth between Cambodia and major trading partners: 1993 to 2019
This study aims to measure trade costs and explore the driving forces behind the growth of bilateral trade between Cambodia and its top 30 trading partners from 1993 to 2019.
VesselSAM: Leveraging SAM for Aortic Vessel Segmentation with LoRA and Atrous Attention
Medical image segmentation is crucial for clinical diagnosis and treatment planning, especially when dealing with complex anatomical structures such as vessels.
AURORA:Automated Training Framework of Universal Process Reward Models via Ensemble Prompting and Reverse Verification
In this paper, we present AURORA, a novel automated framework for training universal process reward models (PRMs) using ensemble prompting and reverse verification.
Range and Bird's Eye View Fused Cross-Modal Visual Place Recognition
Compared to single-modal VPR, this approach benefits from the widespread availability of RGB cameras and the robustness of point clouds in providing accurate spatial geometry and distance information.
ClinKD: Cross-Modal Clinical Knowledge Distiller For Multi-Task Medical Images
To address these issues, we introduce the Cross-Modal Clinical Knowledge Distiller (ClinKD), an innovative framework designed to enhance image-text alignment and establish more effective medical knowledge adaptation mechanisms, which enables MLLMs to adapt to medical knowledge.
AttentionPredictor: Temporal Pattern Matters for Efficient LLM Inference
With the development of large language models (LLMs), efficient inference through Key-Value (KV) cache compression has attracted considerable attention, especially for long-context generation.
LLMER: Crafting Interactive Extended Reality Worlds with JSON Data Generated by Large Language Models
Unlike prior approaches focusing on coding script generation, LLMER translates natural language inputs into JSON data, significantly reducing the likelihood of application crashes and processing latency.
VQLTI: Long-Term Tropical Cyclone Intensity Forecasting with Physical Constraints
(2) Incorporating physical knowledge and physical constraints can help mitigate the accumulation of forecasting errors.
Exploratory Mean-Variance Portfolio Optimization with Regime-Switching Market Dynamics
In a real market data study, EMVRS with OC learning outperforms its counterparts with the highest mean and reasonably low volatility of the annualized portfolio returns.
Global Semantic-Guided Sub-image Feature Weight Allocation in High-Resolution Large Vision-Language Models
As the demand for high-resolution image processing in Large Vision-Language Models (LVLMs) grows, sub-image partitioning has become a popular approach for mitigating visual information loss associated with fixed-resolution processing.
Pre-Trained Large Language Model Based Remaining Useful Life Transfer Prediction of Bearing
Accurately predicting the remaining useful life (RUL) of rotating machinery, such as bearings, is essential for ensuring equipment reliability and minimizing unexpected industrial failures.
Lossless Privacy-Preserving Aggregation for Decentralized Federated Learning
In this paper, we propose a novel lossless privacy-preserving aggregation rule named LPPA to enhance gradient protection as much as possible but without loss of DFL model predictive accuracy.
Gradient Purification: Defense Against Poisoning Attack in Decentralized Federated Learning
It aims to mitigate the harm in model gradients while retaining the benefit in model weights for enhancing accuracy.
On the Low-Complexity of Fair Learning for Combinatorial Multi-Armed Bandit
By setting $M$ to a constant, the number of comparison steps in the pessimistic-optimistic algorithm can be reduced to a constant, thereby significantly reducing the computational complexity.
Instruction-Guided Fusion of Multi-Layer Visual Features in Large Vision-Language Models
Our findings reveal that multilayer features provide complementary strengths with varying task dependencies, and uniform fusion leads to suboptimal performance.
CoF: Coarse to Fine-Grained Image Understanding for Multi-modal Large Language Models
We argue that this limitation is closely linked to the models' visual grounding capabilities.
GSGTrack: Gaussian Splatting-Guided Object Pose Tracking from RGB Videos
Tracking the 6DoF pose of unknown objects in monocular RGB video sequences is crucial for robotic manipulation.
Event-Based Tracking Any Point with Motion-Augmented Temporal Consistency
Tracking Any Point (TAP) plays a crucial role in motion analysis.
When Large Vision-Language Models Meet Person Re-Identification
Large Vision-Language Models (LVLMs) that incorporate visual models and Large Language Models (LLMs) have achieved impressive results across various cross-modal understanding and reasoning tasks.
Self-supervised Monocular Depth and Pose Estimation for Endoscopy with Generative Latent Priors
Accurate 3D mapping in endoscopy enables quantitative, holistic lesion characterization within the gastrointestinal (GI) tract, requiring reliable depth and pose estimation.
A Quality-Centric Framework for Generic Deepfake Detection
To tackle this issue, we propose a novel quality-centric framework for generic deepfake detection, which is composed of a Quality Evaluator, a low-quality data enhancement module, and a learning pacing strategy that explicitly incorporates forgery quality into the training process.
LLM-R: A Framework for Domain-Adaptive Maintenance Scheme Generation Combining Hierarchical Agents and RAG
The increasing use of smart devices has emphasized the critical role of maintenance in production activities.
Learning to Unify Audio, Visual and Text for Audio-Enhanced Multilingual Visual Answer Localization
Specifically, we integrate features from three modalities and develop three predictors, each tailored to the unique contributions of the fused modalities: an audio-visual predictor, a visual predictor, and a textual predictor.
Improving Viewpoint-Independent Object-Centric Representations through Active Viewpoint Selection
Through experiments on various datasets, we demonstrate the effectiveness of our active viewpoint selection strategy, significantly enhancing segmentation and reconstruction performance compared to random viewpoint selection.
Uncertainty-based Offline Variational Bayesian Reinforcement Learning for Robustness under Diverse Data Corruptions
Based on the aforementioned measure, TRACER can regulate the loss associated with corrupted data to reduce its influence, thereby enhancing robustness and performance in clean environments.
MILP-StuDio: MILP Instance Generation via Block Structure Decomposition
However, existing approaches do not take into account specific block structures -- which are closely related to the problem formulations -- in the constraint coefficient matrices (CCMs) of MILPs.
An Efficient Watermarking Method for Latent Diffusion Models via Low-Rank Adaptation
Moreover, we also propose a dynamic loss weight tuning algorithm to balance the generative task with the watermark embedding task, ensuring that the model can be watermarked with a limited impact on the quality of the generated images.
Coarse-to-Fine Highlighting: Reducing Knowledge Hallucination in Large Language Models
Generation of plausible but incorrect factual information, often termed hallucination, has attracted significant research interest.
Towards General Deepfake Detection with Dynamic Curriculum
Specifically, we present a novel simple yet effective strategy, named Dynamic Facial Forensic Curriculum (DFFC), which makes the model gradually focus on hard samples during the training.
One-shot Generative Domain Adaptation in 3D GANs
This paper first considers a novel task known as One-shot 3D Generative Domain Adaptation (GDA), aimed at transferring a pre-trained 3D generator from one domain to a new one, relying solely on a single reference image.
BeSimulator: A Large Language Model Powered Text-based Behavior Simulator
Traditional robot simulators focus on physical process modeling and realistic rendering, often suffering from high computational costs, inefficiencies, and limited adaptability.
Fake It till You Make It: Curricular Dynamic Forgery Augmentations towards General Deepfake Detection
Previous studies in deepfake detection have shown promising results when testing face forgeries from the same dataset as the training.
DSparsE: Dynamic Sparse Embedding for Knowledge Graph Completion
An ablation study is performed to examine the effects of the dynamic layer and relation-aware layer, where the combined model achieves the best performance.
Contract Structure and Risk Aversion in Longevity Risk Transfers
This paper introduces an economic framework to assess optimal longevity risk transfers between institutions, focusing on the interactions between a buyer exposed to long-term longevity risk and a seller offering longevity protection.
Standing on the Shoulders of Giants: Reprogramming Visual-Language Model for General Deepfake Detection
The proliferation of deepfake faces poses huge potential negative impacts on our daily lives.
Large Language Models are Good Attackers: Efficient and Stealthy Textual Backdoor Attacks
With the burgeoning advancements in the field of natural language processing (NLP), the demand for training data has increased significantly.
SZU-AFS Antispoofing System for the ASVspoof 5 Challenge
This paper presents the SZU-AFS anti-spoofing system, designed for Track 1 of the ASVspoof 5 Challenge under open conditions.
5%>100%: Breaking Performance Shackles of Full Fine-Tuning on Visual Recognition Tasks
To fully demonstrate the practicality and generality of Mona, we conduct experiments on multiple representative visual tasks, including instance segmentation on COCO, semantic segmentation on ADE20K, object detection on Pascal VOC, oriented object detection on DOTA/STAR, and image classification on three common datasets.
Enhanced Scale-aware Depth Estimation for Monocular Endoscopic Scenes with Geometric Modeling
The results demonstrate that our method can learn the absolute scale with geometric modeling and accurately estimate scale-aware depth for monocular scenes.
Enhancing Partially Spoofed Audio Localization with Boundary-aware Attention Mechanism
The task of partially spoofed audio localization aims to accurately determine audio authenticity at a frame level.
FedDEO: Description-Enhanced One-Shot Federated Learning with Diffusion Models
On the server, the descriptions are used as conditions to guide the DM in generating synthetic datasets that comply with the distributions of various clients, enabling the training of the aggregated model.
EAFormer: Scene Text Segmentation with Edge-Aware Transformers
In this paper, we propose Edge-Aware Transformers, termed EAFormer, to segment texts more accurately, especially at the edge of texts.
Robust Deep Hawkes Process under Label Noise of Both Event and Occurrence
To the best of our knowledge, this is the first study to successfully address both event and time label noise in deep Hawkes process models, offering a promising solution for medical applications, specifically in diagnosing OSAHS.
KiGRAS: Kinematic-Driven Generative Model for Realistic Agent Simulation
By establishing physical causality from actions (cause) to trajectories (effect) through the kinematic model, KiGRAS eliminates massive redundant trajectories.
Reconfigurable Intelligent Surface for Sensing, Communication, and Computation: Perspectives, Challenges, and Opportunities
To help the ISCC networks better support the comprehensive services of radar detection, data transmission and edge computing, Reconfigurable Intelligent Surface (RIS) can be employed to boost the transmission rate and the wireless coverage by smartly tuning the electromagnetic characteristics of the environment.
Benchmarking End-To-End Performance of AI-Based Chip Placement Algorithms
We executed six state-of-the-art AI-based chip placement algorithms on these designs and plugged the results of each single-point algorithm into the physical implementation workflow to obtain the final PPA results.
An Outline of Prognostics and Health Management Large Model: Concepts, Paradigms, and Challenges
To this end, based on a systematic analysis of the current challenges and bottlenecks in PHM, as well as the research status and advantages of Large Model, we propose a novel concept and three progressive paradigms of Prognosis and Health Management Large Model (PHM-LM) through the integration of the Large Model with PHM.
GM-DF: Generalized Multi-Scenario Deepfake Detection
In this paper, we elaborately investigate the generalization capacity of deepfake detection models when jointly trained on multiple face forgery detection datasets.
Enhancing Monotonic Modeling with Spatio-Temporal Adaptive Awareness in Diverse Marketing
OFOS platforms offer dynamic allocation incentives to users and merchants through diverse marketing campaigns to encourage payments while maintaining the platforms' budget efficiency.
Unleashing the Potential of Tracklets for Unsupervised Video Person Re-Identification
With rich temporal-spatial information, video-based person re-identification methods have shown broad prospects.
Deep Symbolic Optimization for Combinatorial Optimization: Accelerating Node Selection by Discovering Potential Heuristics
With data-driven approaches, Dso4NS guides the search for mathematical expressions within the high-dimensional discrete symbolic space and then incorporates the highest-performing mathematical expressions into a solver.
Vision Model Pre-training on Interleaved Image-Text Data via Latent Compression Learning
Recently, vision model pre-training has evolved from relying on manually annotated datasets to leveraging large-scale, web-crawled image-text data.
Synthesizing Efficient Data with Diffusion Models for Person Re-Identification Pre-Training
In this paper, we present a novel paradigm Diffusion-ReID to efficiently augment and generate diverse images based on known identities without requiring any cost of data collection and annotation.
Ghost imaging-based Non-contact Heart Rate Detection
Remote heart rate measurement is an increasingly concerned research field, usually using remote photoplethysmography (rPPG) to collect heart rate information through video data collection.
Distribution Aligned Semantics Adaption for Lifelong Person Re-Identification
Therefore, the adaptation of Re-ID models to new domains while preserving previously acquired knowledge is crucial, known as Lifelong person Re-IDentification (LReID).
World Models for General Surgical Grasping
Our learned visuomotor policy handles: i) unseen objects, including 5 types of target grasping objects and a robot gripper, in unstructured real-world surgery environments, and ii) disturbances in perception and control.
Content and Salient Semantics Collaboration for Cloth-Changing Person Re-Identification
Specifically, we propose the Content and Salient Semantics Collaboration (CSSC) framework, facilitating cross-parallel semantics interaction and refinement.
Ranked #4 on
Person Re-Identification
on LTCC
Image-Text-Image Knowledge Transferring for Lifelong Person Re-Identification with Hybrid Clothing States
To tackle the challenges of knowledge granularity mismatch and knowledge presentation mismatch that occurred in LReID-Hybrid, we take advantage of the consistency and generalization of the text space, and propose a novel framework, dubbed $Teata$, to effectively align, transfer and accumulate knowledge in an "image-text-image" closed loop.
Image Copy-Move Forgery Detection via Deep PatchMatch and Pairwise Ranking Learning
To address these limitations, this study proposes a novel end-to-end CMFD framework that integrates the strengths of conventional and deep learning methods.
FreqBlender: Enhancing DeepFake Detection by Blending Frequency Knowledge
Existing methods typically generate these faces by blending real or fake faces in spatial domain.
Prediction of soil fertility parameters using USB-microscope imagery and portable X-ray fluorescence spectrometry
A data fusion approach, incorporating IFs, AVs, and PXRF data, further enhanced predictions for available Mn and SAI, with R2 values of 0. 72 and 0. 70, respectively.
Chaos in Motion: Unveiling Robustness in Remote Heart Rate Measurement through Brain-Inspired Skin Tracking
To address these issues, we regard the remote heart rate measurement as the process of analyzing the spatiotemporal characteristics of the optical flow signal in the video.
SparseAD: Sparse Query-Centric Paradigm for Efficient End-to-End Autonomous Driving
End-to-End paradigms use a unified framework to implement multi-tasks in an autonomous driving system.
Uncertainty-Aware Deep Video Compression with Ensembles
Deep learning-based video compression is a challenging task, and many previous state-of-the-art learning-based video codecs use optical flows to exploit the temporal correlation between successive frames and then compress the residual error.
Infinite-ID: Identity-preserved Personalization via ID-semantics Decoupling Paradigm
Drawing on recent advancements in diffusion models for text-to-image generation, identity-preserved personalization has made significant progress in accurately capturing specific identities with just a single reference image.
Learning-augmented Online Minimization of Age of Information and Transmission Costs
To address this challenge, we develop a robust online algorithm to minimize the sum of transmission and staleness costs, ensuring a worst-case performance guarantee.
DF-RAP: A Robust Adversarial Perturbation for Defending against Deepfakes in Real-world Social Network Scenarios
In this paper, we propose a Robust Adversarial Perturbation (DF-RAP) that provides persistent protection for facial images under OSN compression.
Unsupervised Cross-Domain Image Retrieval via Prototypical Optimal Transport
This paper introduces ProtoOT, a novel Optimal Transport formulation explicitly tailored for UCIR, which integrates intra-domain feature representation learning and cross-domain alignment into a unified framework.
Neural Video Compression with Feature Modulation
This results in a better learning of the quantization scaler and helps our NVC support about 11. 4 dB PSNR range.
Global Tropical Cyclone Intensity Forecasting with Multi-modal Multi-scale Causal Autoregressive Model
Accurate forecasting of Tropical cyclone (TC) intensity is crucial for formulating disaster risk reduction strategies.
SA-MDKIF: A Scalable and Adaptable Medical Domain Knowledge Injection Framework for Large Language Models
In the next stage, we train the skill router using task-specific downstream data and use this router to integrate the acquired skills with LLMs during inference.
A Systematic Literature Review on Explainability for Machine/Deep Learning-based Software Engineering Research
The remarkable achievements of Artificial Intelligence (AI) algorithms, particularly in Machine Learning (ML) and Deep Learning (DL), have fueled their extensive deployment across multiple sectors, including Software Engineering (SE).
Towards Generative Abstract Reasoning: Completing Raven's Progressive Matrix via Rule Abstraction and Selection
In the odd-one-out task and two held-out configurations, RAISE can leverage acquired latent concepts and atomic rules to find the rule-breaking image in a matrix and handle problems with unseen combinations of rules and attributes.
Accelerating Data Generation for Neural Operators via Krylov Subspace Recycling
To the best of our knowledge, SKR is the first attempt to address the time-consuming nature of data generation for learning neural operators.
A Study on Training and Developing Large Language Models for Behavior Tree Generation
The core contribution of this paper lies in the design of a BT generation framework based on LLM, which encompasses the entire process, from data synthesis and model training to application developing and data verification.
Unsupervised Object-Centric Learning from Multiple Unspecified Viewpoints
This ability is essential for humans to identify the same object while moving and to learn from vision efficiently.
CMA: A Chromaticity Map Adapter for Robust Detection of Screen-Recapture Document Images
Then we extract a chromaticity map from the recaptured image to highlight the presence of color artifacts even under low-quality samples.
Fast Adaptation for Human Pose Estimation via Meta-Optimization
Domain shift is a challenge for supervised human pose estimation where the source data and target data come from different distributions.
Generative Latent Coding for Ultra-Low Bitrate Image Compression
To address this issue we introduce a Generative Latent Coding (GLC) architecture which performs transform coding in the latent space of a generative vector-quantized variational auto-encoder (VQ-VAE) instead of in the pixel space.
MoML: Online Meta Adaptation for 3D Human Motion Prediction
In the academic field the research on human motion prediction tasks mainly focuses on exploiting the observed information to forecast human movements accurately in the near future horizon.
InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks
However, the progress in vision and vision-language foundation models, which are also critical elements of multi-modal AGI, has not kept pace with LLMs.
Ranked #1 on
Zero-Shot Video Retrieval
on MSR-VTT-full
(using extra training data)
Adapter is All You Need for Tuning Visual Tasks
To fully demonstrate the practicality and generality of Mona, we conduct experiments on multiple representative visual tasks, including instance segmentation on COCO, semantic segmentation on ADE20K, object detection on Pascal VOC, and image classification on several common datasets.
Federated Transformed Learning for a Circular, Secure, and Tiny AI
Deep Learning (DL) is penetrating into a diverse range of mass mobility, smart living, and industrial applications, rapidly transforming the way we live and work.
Efficient Trigger Word Insertion
With the boom in the natural language processing (NLP) field these years, backdoor attacks pose immense threats against deep neural network models.
FedRA: A Random Allocation Strategy for Federated Tuning to Unleash the Power of Heterogeneous Clients
The implementation of FedRA is straightforward and can be seamlessly integrated into any transformer-based model without the need for further modification to the original model.
NAS-ASDet: An Adaptive Design Method for Surface Defect Detection Network using Neural Architecture Search
Deep convolutional neural networks (CNNs) have been widely used in surface defect detection.
One-Shot Federated Learning with Classifier-Guided Diffusion Models
Leveraging the extensive knowledge stored in the pre-trained diffusion model, the synthetic datasets can assist us in surpassing the knowledge limitations of the client samples, resulting in aggregation models that even outperform the performance ceiling of centralized training in some cases, which is convincingly demonstrated in the sufficient quantification and visualization experiments conducted on three large-scale multi-domain image datasets.
Peer is Your Pillar: A Data-unbalanced Conditional GANs for Few-shot Image Generation
Few-shot image generation aims to train generative models using a small number of training images.
Adaptive Digital Twin for UAV-Assisted Integrated Sensing, Communication, and Computation Networks
In this paper, we study a digital twin (DT)-empowered integrated sensing, communication, and computation network.
Evading Detection Actively: Toward Anti-Forensics against Forgery Localization
In adversarial training, SEAR employs a forgery localization model as a supervisor to explore tampering features and constructs a deep-learning concealer to erase corresponding traces.
Explore the Effect of Data Selection on Poison Efficiency in Backdoor Attacks
In this study, we focus on improving the poisoning efficiency of backdoor attacks from the sample selection perspective.
Orientation-Independent Chinese Text Recognition in Scene Images
We conduct experiments on a scene dataset for benchmarking Chinese text recognition, and the results demonstrate that the proposed method can indeed improve performance through disentangling content and orientation information.
Chinese Text Recognition with A Pre-Trained CLIP-Like Model Through Image-IDS Aligning
However, despite Chinese characters possessing different characteristics from Latin characters, such as complex inner structures and large categories, few methods have been proposed for Chinese Text Recognition (CTR).
Robust Computation Offloading and Trajectory Optimization for Multi-UAV-Assisted MEC: A Multi-Agent DRL Approach
For multiple Unmanned-Aerial-Vehicles (UAVs) assisted Mobile Edge Computing (MEC) networks, we study the problem of combined computation and communication for user equipments deployed with multi-type tasks.
Exploring Fine-Grained Representation and Recomposition for Cloth-Changing Person Re-Identification
Cloth-changing person Re-IDentification (Re-ID) is a particularly challenging task, suffering from two limitations of inferior discriminative features and limited training samples.
Ranked #3 on
Person Re-Identification
on LTCC
Rethinking Person Re-identification from a Projection-on-Prototypes Perspective
In this paper, we rethink the role of the classifier in person Re-ID, and advocate a new perspective to conceive the classifier as a projection from image features to class prototypes.
Ranked #2 on
Person Re-Identification
on CUHK03
ForensicsForest Family: A Series of Multi-scale Hierarchical Cascade Forests for Detecting GAN-generated Faces
The proposed ForensicsForest family is composed of three variants, which are {\em ForensicsForest}, {\em Hybrid ForensicsForest} and {\em Divide-and-Conquer ForensicsForest} respectively.
Abstracting Concept-Changing Rules for Solving Raven's Progressive Matrix Problems
Finally, we conduct experiments to illustrate the interpretability of CRAB in concept learning, answer selection, and global rule abstraction.
Payload-Independent Direct Cost Learning for Image Steganography
This framework directly learns universal costs that can be applied to any payload.
GujiBERT and GujiGPT: Construction of Intelligent Information Processing Foundation Language Models for Ancient Texts
In the context of the rapid development of large language models, we have meticulously trained and introduced the GujiBERT and GujiGPT language models, which are foundational models specifically designed for intelligent information processing of ancient texts.
Prototypes as Explanation for Time Series Anomaly Detection
Detecting abnormal patterns that deviate from a certain regular repeating pattern in time series is essential in many big data applications.
OCTScenes: A Versatile Real-World Dataset of Tabletop Scenes for Object-Centric Learning
The results demonstrate the shortcomings of state-of-the-art methods for learning meaningful representations from real-world data, despite their impressive performance on complex synthesis datasets.
Parameter-efficient is not sufficient: Exploring Parameter, Memory, and Time Efficient Adapter Tuning for Dense Predictions
We provide a gradient backpropagation highway for low-rank adapters which eliminates the need for expensive backpropagation through the frozen pre-trained model, resulting in substantial savings of training memory and training time.
Efficient Backdoor Attacks for Deep Neural Networks in Real-world Scenarios
However, existing backdoor attack methods make unrealistic assumptions, assuming that all training data comes from a single source and that attackers have full access to the training data.
A Proxy Attack-Free Strategy for Practically Improving the Poisoning Efficiency in Backdoor Attacks
To address these concerns, we present a Proxy attack-Free Strategy (PFS) designed to identify efficient poisoning samples based on the similarity between clean samples and their corresponding poisoning samples, as well as the diversity of the poisoning set.
Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memory
These agents, equipped with the logic and common sense capabilities of LLMs, can skillfully navigate complex, sparse-reward environments with text-based interactions.
Enhanced Fine-grained Motion Diffusion for Text-driven Human Motion Synthesis
The emergence of text-driven motion synthesis technique provides animators with great potential to create efficiently.
Collaborative Chinese Text Recognition with Personalized Federated Learning
In Chinese text recognition, to compensate for the insufficient local data and improve the performance of local few-shot character recognition, it is often necessary for one organization to collect a large amount of data from similar organizations.
Large Language Models Need Holistically Thought in Medical Conversational QA
The medical conversational question answering (CQA) system aims at providing a series of professional medical services to improve the efficiency of medical care.
Exploring One-shot Semi-supervised Federated Learning with A Pre-trained Diffusion Model
Recently, semi-supervised federated learning (semi-FL) has been proposed to handle the commonly seen real-world scenarios with labeled data on the server and unlabeled data on the clients.
Frequency Decomposition to Tap the Potential of Single Domain for Generalization
Then, a new method that learns through multiple frequency domains is proposed.
Meta-Auxiliary Learning for Adaptive Human Pose Prediction
Predicting high-fidelity future human poses, from a historically observed sequence, is decisive for intelligent robots to interact with humans.
DeFeeNet: Consecutive 3D Human Motion Prediction with Deviation Feedback
Let us rethink the real-world scenarios that require human motion prediction techniques, such as human-robot collaboration.
RAPID: Enabling Fast Online Policy Learning in Dynamic Public Cloud Environments
Resource sharing between multiple workloads has become a prominent practice among cloud service providers, motivated by demand for improved resource utilization and reduced cost of ownership.
FengWu: Pushing the Skillful Global Medium-range Weather Forecast beyond 10 Days Lead
We present FengWu, an advanced data-driven global medium-range weather forecast system based on Artificial Intelligence (AI).
Mastering Symbolic Operations: Augmenting Language Models with Compiled Neural Networks
Our work highlights the potential of seamlessly unifying explicit rule learning via CoNNs and implicit pattern learning in LMs, paving the way for true symbolic comprehension capabilities.
Mechanism Design for Ad Auctions with Display Prices
In this paper, we study ad auctions with display prices from the perspective of mechanism design, in which advertisers are asked to submit both the costs and prices of their products.
Weakly-Supervised Text Instance Segmentation
Text segmentation is a challenging vision task with many downstream applications.
Uncertainty-aware U-Net for Medical Landmark Detection
To estimate the uncertainty, we propose a module named Pyramid Covariance Predictor to predict the covariance matrices of the target Gaussian distributions, which determine the distributions of landmarks and represent the uncertainty of landmark annotation.
Provably Convergent Subgraph-wise Sampling for Fast GNN Training
During the message passing (MP) in GNNs, subgraph-wise sampling methods discard messages outside the mini-batches in backward passes to avoid the well-known neighbor explosion problem, i. e., the exponentially increasing dependencies of nodes with the number of MP iterations.
Neural Video Compression with Diverse Contexts
Better yet, our codec has surpassed the under-developing next generation traditional codec/ECM in both RGB and YUV420 colorspaces, in terms of PSNR.
Demonstration-Guided Reinforcement Learning with Efficient Exploration for Task Automation of Surgical Robot
Task automation of surgical robot has the potentials to improve surgical efficiency.
Generalization in Visual Reinforcement Learning with the Reward Sequence Distribution
The appealing features of RSD-OA include that: (1) RSD-OA is invariant to visual distractions, as it is conditioned on the predefined subsequent action sequence without task-irrelevant information from transition dynamics, and (2) the reward sequence captures long-term task-relevant information in both rewards and transition dynamics.
Energy Efficient Computation Offloading in Aerial Edge Networks With Multi-Agent Cooperation
With the high flexibility of supporting resource-intensive and time-sensitive applications, unmanned aerial vehicle (UAV)-assisted mobile edge computing (MEC) is proposed as an innovational paradigm to support the mobile users (MUs).
EVC: Towards Real-Time Neural Image Compression with Mask Decay
Both mask decay and residual representation learning greatly improve the RD performance of our scalable encoder.
Kainate receptor modulation by NETO2
Glutamate-gated kainate receptors (KARs) are ubiquitous in the central nervous system of vertebrates, mediate synaptic transmission on post-synapse, and modulate transmitter release on pre-synapse.
Learning Trustworthy Model from Noisy Labels based on Rough Set for Surface Defect Detection
In the surface defect detection, there are some suspicious regions that cannot be uniquely classified as abnormal or normal.
Time-Conditioned Generative Modeling of Object-Centric Representations for Video Decomposition and Prediction
To reconstruct the complete shape of an object accurately, we enhance the disentanglement between the latent representations of objects and views, where the latent representations of time-conditioned views are jointly inferred with a Transformer and then are input to a sequential extension of Slot Attention to learn object-centric representations.
Test-time Personalizable Forecasting of 3D Human Poses
Current motion forecasting approaches typically train a deep end-to-end model from the source domain data, and then apply it directly to target subjects.
Motion Information Propagation for Neural Video Compression
Meanwhile, besides assisting frame coding at the current time step, the feature from context generation will be propagated as motion condition when coding the subsequent motion latent.
Learning Accurate 3D Shape Based on Stereo Polarimetric Imaging
As to the orthographic projection problem, we propose a novel Viewing Direction-aided Positional Encoding (VDPE) strategy.
Large Language Models are Better Reasoners with Self-Verification
By performing a backward verification of the answers that LLM deduced for itself, we can obtain interpretable answer validation scores to select the candidate answer with the highest score.
Adversarial Example Defense via Perturbation Grading Strategy
In addition, the proposed method does not modify any task model, which can be used as a preprocessing module, which significantly reduces the deployment cost in practical applications.
Artificial Text Detection with Multiple Training Strategies
As the deep learning rapidly promote, the artificial texts created by generative models are commonly used in news and social media.
Chinese Character Recognition with Radical-Structured Stroke Trees
In this paper, we represent each Chinese character as a stroke tree, which is organized according to its radical structures, to fully exploit the merits of both radical and stroke levels in a decent way.
Compositional Scene Modeling with Global Object-Centric Representations
Inspired by such an ability of humans, this paper proposes a compositional scene modeling method to infer global representations of canonical images of objects without any supervision.
Towards All-in-one Pre-training via Maximizing Multi-modal Mutual Information
It has been proved that combining multiple pre-training strategies and data from various modalities/sources can greatly boost the training of large-scale models.
Ranked #2 on
Object Detection
on COCO test-dev
Federated Adaptive Prompt Tuning for Multi-Domain Collaborative Learning
In this paper, we propose a federated adaptive prompt tuning algorithm, FedAPT, for multi-domain collaborative image classification with powerful foundation models, like CLIP.
Visual Answer Localization with Cross-modal Mutual Knowledge Transfer
In this paper, we propose a cross-modal mutual knowledge transfer span localization (MutualSL) method to reduce the knowledge deviation.
Slippage-robust Gaze Tracking for Near-eye Display
In recent years, head-mounted near-eye display devices have become the key hardware foundation for virtual reality and augmented reality.
Human Joint Kinematics Diffusion-Refinement for Stochastic Motion Prediction
This process offers a natural way to obtain the "whitened" latents without any trainable parameters, and human motion prediction can be regarded as the reverse diffusion process that converts the noise distribution into realistic future motions conditioned on the observed sequence.
Learning to Locate Visual Answer in Video Corpus Using Question
We introduce a new task, named video corpus visual answer localization (VCVAL), which aims to locate the visual answer in a large collection of untrimmed instructional videos using a natural language question.
Domain Discrepancy Aware Distillation for Model Aggregation in Federated Learning
In this paper, we first analyze the generalization bound of the aggregation model produced from knowledge distillation for the client domains, and then describe two challenges, server-to-client discrepancy and client-to-client discrepancy, brought to the aggregation model by the domain discrepancies.
Domain-Unified Prompt Representations for Source-Free Domain Generalization
The proposed scheme generates diverse prompts from a domain bank that contains many more diverse domains than existing DG datasets.
TODE-Trans: Transparent Object Depth Estimation with Transformer
We observe that the global characteristics of the transformer make it easier to extract contextual information to perform depth estimation of transparent areas.
Compositional Law Parsing with Latent Random Functions
The automatic parsing of these laws indicates the model's ability to understand the scene, which makes law parsing play a central role in many visual tasks.
Rain Removal from Light Field Images with 4D Convolution and Multi-scale Gaussian Process
However, making full use of the abundant information available from LFIs, such as 2D array of sub-views and the disparity map of each sub-view, for effective rain removal is still a challenging problem.
Style Spectroscope: Improve Interpretability and Controllability through Fourier Analysis
We connect Fourier amplitude and phase with Gram matrices and a content reconstruction loss in style transfer, respectively.
Clear Memory-Augmented Auto-Encoder for Surface Defect Detection
At first, we propose a novel clear memory-augmented module (CMAM), which combines the encoding and memoryencoding in a way of forgetting and inputting, thereby repairing abnormal foregrounds and preserving clear backgrounds.
Overlooked Poses Actually Make Sense: Distilling Privileged Knowledge for Human Motion Prediction
Previous works on human motion prediction follow the pattern of building a mapping relation between the sequence observed and the one to be predicted.
FakeCLR: Exploring Contrastive Learning for Solving Latent Discontinuity in Data-Efficient GANs
Since data augmentation strategies have largely alleviated the training instability, how to further improve the generative performance of DE-GANs becomes a hotspot.
Hybrid Spatial-Temporal Entropy Modelling for Neural Video Compression
Besides estimating the probability distribution, our entropy model also generates the quantization step at spatial-channel-wise.
Scene-Aware Prompt for Multi-modal Dialogue Understanding and Generation
To fully leverage the visual information for both scene understanding and dialogue generation, we propose the scene-aware prompt for the MDUG task.
Cross-domain Federated Object Detection
Federated learning can enable multi-party collaborative learning without leaking client data.
Adversarial Reconfigurable Intelligent Surface Against Physical Layer Key Generation
The development of reconfigurable intelligent surfaces (RIS) has recently advanced the research of physical layer security (PLS).
STD-NET: Search of Image Steganalytic Deep-learning Architecture via Hierarchical Tensor Decomposition
We propose a normalized distortion threshold to evaluate the sensitivity of each involved convolutional layer of the base model to guide STD-NET to compress target network in an efficient and unsupervised approach, and obtain two network structures of different shapes with low computation cost and similar performance compared with the original one.
Siamese Image Modeling for Self-Supervised Vision Representation Learning
Driven by these analysis, we propose Siamese Image Modeling (SiameseIM), which predicts the dense representations of an augmented view, based on another masked view from the same image but with different augmentations.
Dog nose print matching with dual global descriptor based on Contrastive Learning
These methods generally extract the global features as descriptor to represent the original image.
Learning Task-relevant Representations for Generalization via Characteristic Functions of Reward Sequence Distributions
Generalization across different environments with the same tasks is critical for successful applications of visual reinforcement learning (RL) in real scenarios.
