Search Results for author:
Found 54 papers, 22 papers with code
Modeling Aspect Correlation for Aspect-based Sentiment Analysis via Recurrent Inverse Learning Guidance
Second, we propose Inverse Learning Guidance to improve the selection of aspect feature by considering aspect correlation, which provides more useful information to determine polarity.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+1
ChronoSteer: Bridging Large Language Model and Time Series Foundation Model via Synthetic Data
To address the scarcity of event-series paired data, we propose a decoupled framework: an LLM is employed to transform textual events into revision instructions, which are then used to steer the output of TSFM.
Unlocking the Potential of Linear Networks for Irregular Multivariate Time Series Forecasting
Time series forecasting holds significant importance across various industries, including finance, transportation, energy, healthcare, and climate.
Simultaneous Polysomnography and Cardiotocography Reveal Temporal Correlation Between Maternal Obstructive Sleep Apnea and Fetal Hypoxia
FHR changes were significantly associated with maternal hypoxia, primarily characterized by accelerations.
Perception-R1: Pioneering Perception Policy with Reinforcement Learning
In this work, we return to the fundamentals and explore the effects of RL on different perception tasks.
OIPR: Evaluation for Time-series Anomaly Detection Inspired by Operator Interest
Furthermore, we build a special scenario dataset to compare the characteristics of different evaluation methods.
Erasing Without Remembering: Implicit Knowledge Forgetting in Large Language Models
In this paper, we investigate knowledge forgetting in large language models with a focus on its generalisation--ensuring that models forget not only specific training samples but also related implicit knowledge.
NTP-INT: Network Traffic Prediction-Driven In-band Network Telemetry for High-load Switches
Specifically, NTP-INT consists of three modules: network traffic prediction module, network pruning module, and probe path planning module.
Unhackable Temporal Rewarding for Scalable Video MLLMs
In the pursuit of superior video-processing MLLMs, we have encountered a perplexing paradox: the "anti-scaling law", where more data and larger models lead to worse performance.
Fast Searching of Extreme Operating Conditions for Relay Protection Setting Calculation Based on Graph Neural Network and Reinforcement Learning
Searching for the Extreme Operating Conditions (EOCs) is one of the core problems of power system relay protection setting calculation.
Deep Generative Model-Aided Power System Dynamic State Estimation and Reconstruction with Unknown Control Inputs or Data Distributions
The proposed approach employs an encoder-decoder architecture to estimate unknown control input variables, a robust encoder to mitigate the impact of bad PMU data, and latent diffusion model to address communication issues in centralized DSE.
Pose-Guided Temporal Enhancement for Robust Low-Resolution Hand Reconstruction
We introduce Triplane Features, a dense representation with 3D spatial awareness, to bridge the gap between the joint features and visual features that are misaligned in terms of representation form and semantics.
ChatTime: A Unified Multimodal Time Series Foundation Model Bridging Numerical and Textual Data
In this paper, we innovatively model time series as a foreign language and construct ChatTime, a unified framework for time series and text processing.
MEGL: Multimodal Explanation-Guided Learning
A Visual Explanation Distribution Consistency loss further reinforces visual coherence by aligning the generated visual explanations with dataset-level patterns, enabling the model to effectively learn from incomplete multimodal supervision.
DRL Optimization Trajectory Generation via Wireless Network Intent-Guided Diffusion Models for Optimizing Resource Allocation
This model can be generated and fine-tuned in real time to achieve the objective and meet the constraints of target intent networks, significantly reducing state information exposure during wireless communication.
Interdependency Matters: Graph Alignment for Multivariate Time Series Anomaly Detection
To capitalize on this insight, we introduce MADGA (MTS Anomaly Detection via Graph Alignment), which redefines anomaly detection as a graph alignment (GA) problem that explicitly utilizes interdependencies for anomaly detection.
RISE-SDF: a Relightable Information-Shared Signed Distance Field for Glossy Object Inverse Rendering
Our experiments demonstrate that our algorithm achieves state-of-the-art performance in inverse rendering and relighting, with particularly strong results in the reconstruction of highly reflective objects.
Rethinking the Power of Timestamps for Robust Time Series Forecasting: A Global-Local Fusion Perspective
Time series forecasting has played a pivotal role across various industries, including finance, transportation, energy, healthcare, and climate.
Enhanced Fine-Tuning of Lightweight Domain-Specific Q&A Model Based on Large Language Models
Large language models (LLMs) excel at general question-answering (Q&A) but often fall short in specialized domains due to a lack of domain-specific knowledge.
OutlierTune: Efficient Channel-Wise Quantization for Large Language Models
The pre-execution of dequantization updates the model weights by the activation scaling factors, avoiding the internal scaling and costly additional computational overheads brought by the per-channel activation quantization.
Finite-difference-informed graph network for solving steady-state incompressible flows on block-structured grids
To address this issue, \blueText{graphs and graph networks are used} to learn flow representations across multi-block-structured grids.
MLS-Track: Multilevel Semantic Interaction in RMOT
The new trend in multi-object tracking task is to track objects of interest using natural language.
Object-level Copy-Move Forgery Image Detection based on Inconsistency Mining
Additionally, we extract inconsistent regions between coarse similar regions obtained through self-correlation calculations and regions composed of prototypes.
An Order-Complexity Aesthetic Assessment Model for Aesthetic-aware Music Recommendation
In order to improve the quality of AI music generation and further guide computer music production, synthesis, recommendation and other tasks, we use Birkhoff's aesthetic measure to design a aesthetic model, objectively measuring the aesthetic beauty of music, and form a recommendation list according to the aesthetic feeling of music.
Understanding and Guiding Weakly Supervised Entity Alignment with Potential Isomorphism Propagation
In this paper, we present a propagation perspective to analyze weakly supervised EA and explain the existing aggregation-based EA models.
Multi-Level Aggregation and Recursive Alignment Architecture for Efficient Parallel Inference Segmentation Network
Real-time semantic segmentation is a crucial research for real-world applications.
Towards Semantic Consistency: Dirichlet Energy Driven Robust Multi-Modal Entity Alignment
This study introduces a novel approach, DESAlign, which addresses these issues by applying a theoretical framework based on Dirichlet energy to ensure semantic consistency.
Gradient Flow of Energy: A General and Efficient Approach for Entity Alignment Decoding
However, the decoding process in EA - essential for effective operation and alignment accuracy - has received limited attention and remains tailored to specific datasets and model architectures, necessitating both entity and additional explicit relation embeddings.
Dynamic Support Information Mining for Category-Agnostic Pose Estimation
Category-agnostic pose estimation (CAPE) aims to predict the pose of a query image based on few support images with pose annotations.
Multi-Scale Video Anomaly Detection by Multi-Grained Spatio-Temporal Representation Learning
ecent progress in video anomaly detection suggests that the features of appearance and motion play crucial roles in distinguishing abnormal patterns from normal ones.
A Comprehensive End-to-End Computer Vision Framework for Restoration and Recognition of Low-Quality Engineering Drawings
Existing computer vision approaches for digitizing engineering drawings typically assume the input drawings have high quality.
Detection and Imputation based Two-Stage Denoising Diffusion Power System Measurement Recovery under Cyber-Physical Uncertainties
Power system cyber-physical uncertainties, including measurement ambiguities stemming from cyber attacks and data losses, along with system uncertainties introduced by massive renewables and complex dynamics, reduce the likelihood of enhancing the quality of measurements.
Extracting Physical Causality from Measurements to Detect and Localize False Data Injection Attacks
They are sensitive to the violation of physical laws caused by FDIA, but tend to remain stable with the drift of system operating points.
Interpretable Online Log Analysis Using Large Language Models with Prompt Strategies
LogPrompt employs large language models (LLMs) to perform online log analysis tasks via a suite of advanced prompt strategies tailored for log tasks, which enhances LLMs' performance by up to 380. 7% compared with simple prompts.
How Does Diffusion Influence Pretrained Language Models on Out-of-Distribution Data?
It shows that finetuning PLMs with diffusion degrades the reconstruction ability on OOD data.
Adaptive DNN Surgery for Selfish Inference Acceleration with On-demand Edge Resource
Deep Neural Networks (DNNs) have significantly improved the accuracy of intelligent applications on mobile devices.
Automatic Generation of Topology Diagrams for Strongly-Meshed Power Transmission Systems
This paper proposes an integrated framework for generating aesthetically-pleasing topology diagrams for power transmission systems.
Decoupled Iterative Refinement Framework for Interacting Hands Reconstruction from a Single RGB Image
On the other hand, there are complex spatial relationship between interacting hands, which significantly increases the solution space of hand poses and increases the difficulty of network learning.
Ranked #4 on
3D Interacting Hand Pose Estimation
on InterHand2.6M
HaMuCo: Hand Pose Estimation via Multiview Collaborative Self-Supervised Learning
Recent advancements in 3D hand pose estimation have shown promising results, but its effectiveness has primarily relied on the availability of large-scale annotated datasets, the creation of which is a laborious and costly process.
Universal adaptive optics for microscopy through embedded neural network control
Unlike previous ML methods, we used a bespoke neural network (NN) architecture, designed using physical understanding of image formation, that was embedded in the control loop of the microscope.
Can Shuffling Video Benefit Temporal Bias Problem: A Novel Training Framework for Temporal Grounding
Our framework introduces two auxiliary tasks, cross-modal matching and temporal order discrimination, to promote the grounding model training.
Approximation of Images via Generalized Higher Order Singular Value Decomposition over Finite-dimensional Commutative Semisimple Algebra
Higher order singular value decomposition (HOSVD) extends the SVD and can approximate higher order data using sums of a few rank-one components.
Mining Multi-View Information: A Strong Self-Supervised Framework for Depth-Based 3D Hand Pose and Mesh Estimation
However, these methods ignore the rich semantic information in each view and ignore the complex dependencies between different regions of different views.
CAP-RAM: A Charge-Domain In-Memory Computing 6T-SRAM for Accurate and Precision-Programmable CNN Inference
A compact, accurate, and bitwidth-programmable in-memory computing (IMC) static random-access memory (SRAM) macro, named CAP-RAM, is presented for energy-efficient convolutional neural network (CNN) inference.
Question-Driven Span Labeling Model for Aspect–Opinion Pair Extraction
Specifically, we divide the AOPE task into aspect term extraction (ATE) and aspect-specified opinion extraction (ASOE) subtasks; we first extract all the candidate aspect terms and then the corresponding opinion words given the aspect term.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+3
Robust Unsupervised Video Anomaly Detection by Multi-Path Frame Prediction
In this paper, we propose a novel and robust unsupervised video anomaly detection method by frame prediction with proper design which is more in line with the characteristics of surveillance videos.
Towards automatic visual inspection: A weakly supervised learning method for industrial applicable object detection
With the recent progress of deep learning, advanced industrial object detectors are built for smart industrial applications.
Ranked #28 on
Weakly Supervised Object Detection
on PASCAL VOC 2007
AWR: Adaptive Weighting Regression for 3D Hand Pose Estimation
In this paper, we propose an adaptive weighting regression (AWR) method to leverage the advantages of both detection-based and regression-based methods.
Ranked #1 on
Hand Pose Estimation
on HANDS 2017
Adversarial and Domain-Aware BERT for Cross-Domain Sentiment Analysis
To tackle these problems, we design a post-training procedure, which contains the target domain masked language model task and a novel domain-distinguish pre-training task.
Capsule Network with Interactive Attention for Aspect-Level Sentiment Classification
Aspect-level sentiment classification is a crucial task for sentiment analysis, which aims to identify the sentiment polarities of specific targets in their context.
Investigating Capsule Network and Semantic Feature on Hyperplanes for Text Classification
It has been demonstrated that multiple senses of a word actually reside in linear superposition within the word embedding so that specific senses can be extracted from the original word embedding.
OICSR: Out-In-Channel Sparsity Regularization for Compact Deep Neural Networks
Many channel pruning works utilize structured sparsity regularization to zero out all the weights in some channels and automatically obtain structure-sparse network in training stage.
Fewer is More: Image Segmentation Based Weakly Supervised Object Detection with Partial Aggregation
As most weakly supervised object detection methods are based on pre-generated proposals, they often show two false detections: (i) group multiple object instances with one bounding box, and (ii) focus on only parts rather than the whole objects.
Ranked #31 on
Weakly Supervised Object Detection
on PASCAL VOC 2007
Chinese/English mixed Character Segmentation as Semantic Segmentation
We take advantage of the successful architecture called fully convolutional networks (FCN) in the field of semantic segmentation.
