Search Results for author:
Found 221 papers, 91 papers with code
Self-Modulating Nonparametric Event-Tensor Factorization
Tensor factorization is a fundamental framework to analyze high-order interactions in data.
NeighborRetr: Balancing Hub Centrality in Cross-Modal Retrieval
Cross-modal retrieval aims to bridge the semantic gap between different modalities, such as visual and textual data, enabling accurate retrieval across them.
Ensemble Learning for Large Language Models in Text and Code Generation: A Survey
This information offers valuable insights for selecting models for various real-world tasks involving text and code generation, and potentially applying methods to multimodal LLMs.
SimROD: A Simple Baseline for Raw Object Detection with Global and Local Enhancements
Most visual models are designed for sRGB images, yet RAW data offers significant advantages for object detection by preserving sensor information before ISP processing.
A Generalist Cross-Domain Molecular Learning Framework for Structure-Based Drug Discovery
To fill this gap, we propose a general-purpose foundation model named BIT (an abbreviation for Biomolecular Interaction Transformer), which is capable of encoding a range of biochemical entities, including small molecules, proteins, and protein-ligand complexes, as well as various data formats, encompassing both 2D and 3D structures.
Can Large Language Models Unveil the Mysteries? An Exploration of Their Ability to Unlock Information in Complex Scenarios
Notably, our approach improves the performance of models on combinatorial reasoning, with a 22. 17% boost on CVQA and 9. 40% on CPVQA over the SOTA closed-source model, demonstrating its effectiveness in enhancing combinatorial reasoning with multiple perceptual inputs in complex scenarios.
Less is More: Improving LLM Alignment via Preference Data Selection
Direct Preference Optimization (DPO) has emerged as a promising approach for aligning large language models with human preferences.
PSCon: Toward Conversational Product Search
Conversational Product Search (CPS) is confined to simulated conversations due to the lack of real-world CPS datasets that reflect human-like language.
Leader and Follower: Interactive Motion Generation under Trajectory Constraints
To generate interactive motion following specified trajectories, this paper decouples complex motion into a Leader - Follower dynamic, inspired by role allocation in partner dancing.
A Survey of LLM-based Agents in Medicine: How far are we from Baymax?
Large Language Models (LLMs) are transforming healthcare through the development of LLM-based agents that can understand, reason about, and assist with medical tasks.
GENERator: A Long-Context Generative Genomic Foundation Model
Recent developments in genomic language models have underscored the potential of LLMs in deciphering DNA sequences.
AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders
We introduce a novel weakly-supervised representational method (Rank-1 Representation Finetuning; ReFT-r1), which is competitive on both tasks while providing the interpretability advantages that prompting lacks.
Spectrum Sharing in Satellite-Terrestrial Integrated Networks: Frameworks, Approaches, and Opportunities
Furthermore, advanced SS approaches related to interference management in STINs and performance metrics of SS in STINs are introduced.
An Investigation into Value Misalignment in LLM-Generated Texts for Cultural Heritage
As Large Language Models (LLMs) become increasingly prevalent in tasks related to cultural heritage, such as generating descriptions of historical monuments, translating ancient texts, preserving oral traditions, and creating educational content, their ability to produce accurate and culturally aligned texts is being increasingly relied upon by users and researchers.
Enhancing Deployment-Time Predictive Model Robustness for Code Analysis and Optimization
By relabeling up to 5% of the Prom-identified samples through incremental learning, Prom can help a deployed model achieve a performance comparable to that attained during its model training phase.
ProtCLIP: Function-Informed Protein Multi-Modal Learning
However, these works were still unable to replicate the extraordinary success of language-supervised visual foundation models due to the ineffective usage of aligned protein-text paired data and the lack of an effective function-informed pre-training paradigm.
Rethinking Cancer Gene Identification through Graph Anomaly Analysis
Graph neural networks (GNNs) have shown promise in integrating protein-protein interaction (PPI) networks for identifying cancer genes in recent studies.
Local Features Meet Stochastic Anonymization: Revolutionizing Privacy-Preserving Face Recognition for Black-Box Models
The task of privacy-preserving face recognition (PPFR) currently faces two major unsolved challenges: (1) existing methods are typically effective only on specific face recognition models and struggle to generalize to black-box face recognition models; (2) current methods employ data-driven reversible representation encoding for privacy protection, making them susceptible to adversarial learning and reconstruction of the original image.
Optimizing Personalized Federated Learning through Adaptive Layer-Wise Learning
Personalized FL (pFL) tackles these issues by tailoring local models to individual data sources and using weighted aggregation methods for client-specific learning.
StarWhisper Telescope: Agent-Based Observation Assistant System to Approach AI Astrophysicist
Additionally, the integration of AI agents within the system provides online accessibility, saving astronomers' time and encouraging greater participation from amateur astronomers in the NGSS project.
Mix-Modality Person Re-Identification: A New and Practical Paradigm
Current visible-infrared cross-modality person re-identification research has only focused on exploring the bi-modality mutual retrieval paradigm, and we propose a new and more practical mix-modality retrieval paradigm.
Cross-Modality Person Re-identification
Person Re-Identification
+1
Multi-Level Correlation Network For Few-Shot Image Classification
In this paper, we argue that measure at such a level may not be effective enough to generalize from base to novel classes when using only a few images.
Prompt as Free Lunch: Enhancing Diversity in Source-Free Cross-domain Few-shot Learning through Semantic-Guided Prompting
After training of the first step, support samples with different diversity prompts are input into the CLIP backbone to generate enhanced features.
Online Adaptive Real-Time Beamforming Design for Dynamic Environments in Cell-Free Systems
In this paper, we consider real-time beamforming design for dynamic wireless environments with varying channels and different numbers of access points (APs) and users in cell-free systems.
TokenSelect: Efficient Long-Context Inference and Length Extrapolation for LLMs via Dynamic Token-Level KV Cache Selection
With the development of large language models (LLMs), the ability to handle longer contexts has become a key capability for Web applications such as cross-document understanding and LLM-powered search systems.
Bridge-IF: Learning Inverse Protein Folding with Markov Bridges
To fill these gaps, we propose Bridge-IF, a generative diffusion bridge model for inverse folding, which is designed to learn the probabilistic dependency between the distributions of backbone structures and protein sequences.
P4GCN: Vertical Federated Social Recommendation with Privacy-Preserving Two-Party Graph Convolution Network
To address this issue, we propose a novel vertical federated social recommendation method leveraging privacy-preserving two-party graph convolution networks (P4GCN) to enhance recommendation accuracy without requiring direct access to sensitive social information.
Cross-Modal Few-Shot Learning: a Generative Transfer Learning Framework
Most existing studies on few-shot learning focus on unimodal settings, where models are trained to generalize on unseen data using only a small number of labeled examples from the same modality.
A Learning Rate Path Switching Training Paradigm for Version Updates of Large Language Models
Preliminary experiments demonstrate that PTFS achieves better pre-training performance, while CPT has lower training cost.
Structure-Enhanced Protein Instruction Tuning: Towards General-Purpose Protein Understanding
Recent development of protein language models (pLMs) with supervised fine tuning provides a promising solution to this problem.
Empowering Large Language Model for Continual Video Question Answering with Collaborative Prompting
In recent years, the rapid increase in online video content has underscored the limitations of static Video Question Answering (VideoQA) models trained on fixed datasets, as they struggle to adapt to new questions or tasks posed by newly available content.
ASQuery: A Query-based Model for Action Segmentation
For the task of temporal action segmentation, existing works commonly treat it as a frame-wise classification problem.
Ranked #1 on
Action Segmentation
on Assembly101
Devil is in Details: Locality-Aware 3D Abdominal CT Volume Generation for Self-Supervised Organ Segmentation
To address the overlooked challenge, we introduce the Locality-Aware Diffusion (Lad), a novel method tailored for exquisite 3D abdominal CT volume generation.
Crafting Personalized Agents through Retrieval-Augmented Generation on Editable Memory Graphs
In the age of mobile internet, user data, often referred to as memories, is continuously generated on personal devices.
GalleryGPT: Analyzing Paintings with Large Multimodal Models
Specifically, we first propose a task of composing paragraph analysis for artworks, i. e., painting in this paper, only focusing on visual characteristics to formulate more comprehensive understanding of artworks.
rLLM: Relational Table Learning with LLMs
To illustrate the usage of rLLM, we introduce a simple RTL method named \textbf{BRIDGE}.
Ranked #1 on
Classification
on TACM12K
A3S: A General Active Clustering Method with Pairwise Constraints
Active clustering aims to boost the clustering performance by integrating human-annotated pairwise constraints through strategic querying.
Model Tells You Where to Merge: Adaptive KV Cache Merging for LLMs on Long-Context Tasks
To mitigate computational costs, LLMs often employ the KV Cache technique to improve the generation speed.
Zero-shot Object Counting with Good Exemplars
Zero-shot object counting (ZOC) aims to enumerate objects in images using only the names of object classes during testing, without the need for manual annotations.
EDGE-LLM: Enabling Efficient Large Language Model Adaptation on Edge Devices via Layerwise Unified Compression and Adaptive Layer Tuning and Voting
Efficient adaption of large language models (LLMs) on edge devices is essential for applications requiring continuous and privacy-preserving adaptation and inference.
Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibration
Specifically, this work begins with comprehensive visualizations of the attention distributions in LLMs during inference across various inputs and tasks.
Semantic Enhanced Few-shot Object Detection
As a result, our method allows each novel class to construct a compact feature space without being confused with similar base classes.
Technique Report of CVPR 2024 PBDL Challenges
The intersection of physics-based vision and deep learning presents an exciting frontier for advancing computer vision technologies.
When Linear Attention Meets Autoregressive Decoding: Towards More Effective and Efficient Linearized Large Language Models
Autoregressive Large Language Models (LLMs) have achieved impressive performance in language tasks but face two significant bottlenecks: (1) quadratic complexity in the attention module as the number of tokens increases, and (2) limited efficiency due to the sequential processing nature of autoregressive LLMs during generation.
Selective Knowledge Sharing for Personalized Federated Learning Under Capacity Heterogeneity
Finally, we facilitate the implicit aggregation of personal parameters by aggregating client embeddings through a self-attention module.
FedSAC: Dynamic Submodel Allocation for Collaborative Fairness in Federated Learning
Second, to implement the BCF, we design a submodel allocation module with a theoretical guarantee of fairness.
The SkatingVerse Workshop & Challenge: Methods and Results
The SkatingVerse Workshop & Challenge aims to encourage research in developing novel and accurate methods for human action understanding.
M-RAG: Reinforcing Large Language Model Performance through Retrieval-Augmented Generation with Multiple Partitions
Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by retrieving relevant memories from an external database.
CodeIP: A Grammar-Guided Multi-Bit Watermark for Large Language Models of Code
Experiments conducted on a real-world dataset across five programming languages demonstrate the effectiveness of CodeIP in watermarking LLMs for code generation while maintaining the syntactical correctness of code.
Pushing the Boundaries of Text to Motion with Arbitrary Text: A New Task
Text to Motion aims to generate human motions from texts.
A Massive MIMO Sampling Detection Strategy Based on Denoising Diffusion Model
The Langevin sampling method relies on an accurate score matching while the existing massive multiple-input multiple output (MIMO) Langevin detection involves an inevitable singular value decomposition (SVD) to calculate the posterior score.
FedPFT: Federated Proxy Fine-Tuning of Foundation Models
Adapting Foundation Models (FMs) for downstream tasks through Federated Learning (FL) emerges a promising strategy for protecting data privacy and valuable FMs.
ReFT: Representation Finetuning for Language Models
We define a strong instance of the ReFT family, Low-rank Linear Subspace ReFT (LoReFT), and we identify an ablation of this method that trades some performance for increased efficiency.
Iterative Refinement of Project-Level Code Context for Precise Code Generation with Compiler Feedback
Large Language Models (LLMs) have shown remarkable progress in automated code generation.
pyvene: A Library for Understanding and Improving PyTorch Models via Interventions
Interventions on model-internal states are fundamental operations in many areas of AI, including model editing, steering, robustness, and interpretability.
Multimodal Query Suggestion with Multi-Agent Reinforcement Learning from Human Feedback
In this paper, we introduce a novel Multimodal Query Suggestion (MMQS) task, which aims to generate query suggestions based on user query images to improve the intentionality and diversity of search results.
Mitigating Prior Shape Bias in Point Clouds via Differentiable Center Learning
Experimental results demonstrate that our method enhances the expressive capacity of existing point cloud models and effectively addresses the issue of information leakage.
Contributing Dimension Structure of Deep Feature for Coreset Selection
Existing methods typically measure both the representation and diversity of data based on similarity metrics, such as L2-norm.
IQ-VFI: Implicit Quadratic Motion Estimation for Video Frame Interpolation
To this end we propose a novel framework for implicit quadratic video frame interpolation (IQ-VFI) which explores latent acceleration information and accurate intermediate motions via knowledge distillation.
SynSP: Synergy of Smoothness and Precision in Pose Sequences Refinement
To leverage this quality information we propose a motion refinement network termed SynSP to achieve a Synergy of Smoothness and Precision in the sequence refinement tasks.
Bi-Causal: Group Activity Recognition via Bidirectional Causality
This network establishes a causality communication channel while modeling relations and interactions enabling reciprocal enhancement between human-object interactions and human relations ensuring their mutual consistency.
Group Activity Recognition
Human-Object Interaction Detection
+1
Ensemble Diversity Facilitates Adversarial Transferability
With the advent of ensemble-based attacks the transferability of generated adversarial examples is elevated by a noticeable margin despite many methods only employing superficial integration yet ignoring the diversity between ensemble models.
Open-Vocabulary Video Relation Extraction
A comprehensive understanding of videos is inseparable from describing the action with its contextual action-object interactions.
HumanNeRF-SE: A Simple yet Effective Approach to Animate HumanNeRF with Diverse Poses
Our architecture involving both explicit and implicit representation is simple yet effective.
A manometric feature descriptor with linear-SVM to distinguish esophageal contraction vigor
We conducted image processing of HRM to predict the esophageal contraction vigor for assisting the evaluation of esophageal dynamic function.
Diffusion-Generative Multi-Fidelity Learning for Physical Simulation
We propose a conditional score model to control the solution generation by the input parameters and the fidelity.
Dynamic Association Learning of Self-Attention and Convolution in Image Restoration
Thus, we propose to refine background textures with the predicted degradation prior in an association learning manner.
Functional Bayesian Tucker Decomposition for Continuous-indexed Tensor Data
To generalize Tucker decomposition to such scenarios, we propose Functional Bayesian Tucker Decomposition (FunBaT).
Foundation Models Meet Visualizations: Challenges and Opportunities
Recent studies have indicated that foundation models, such as BERT and GPT, excel in adapting to a variety of downstream tasks.
Label Deconvolution for Node Representation Learning on Large-scale Attributed Graphs against Learning Bias
The inverse mapping leads to an objective function that is equivalent to that by the joint training, while it can effectively incorporate GNNs in the training phase of NEs against the learning bias.
Ranked #1 on
Node Property Prediction
on ogbn-proteins
From Cluster Assumption to Graph Convolution: Graph-based Semi-Supervised Learning Revisited
Graph-based semi-supervised learning (GSSL) has long been a hot research topic.
Beyond Domain Gap: Exploiting Subjectivity in Sketch-Based Person Retrieval
2) Multi-perspective and multi-style.
An Effective Two-stage Training Paradigm Detector for Small Dataset
Learning from the limited amount of labeled data to the pre-train model has always been viewed as a challenging task.
Uncovering the Unseen: Discover Hidden Intentions by Micro-Behavior Graph Reasoning
HID presents a unique challenge in that hidden intentions lack the obvious visual representations to distinguish them from normal intentions.
A Survey of Diffusion Based Image Generation Models: Issues and Their Solutions
Fortunately, the availability of open-source stable diffusion models and their underlying mathematical principles has enabled the academic community to extensively analyze the performance of current image generation models and make improvements based on this stable diffusion framework.
Prototypical Cross-domain Knowledge Transfer for Cervical Dysplasia Visual Inspection
Early detection of dysplasia of the cervix is critical for cervical cancer treatment.
DAOT: Domain-Agnostically Aligned Optimal Transport for Domain-Adaptive Crowd Counting
Domain adaptation is commonly employed in crowd counting to bridge the domain gaps between different datasets.
A Generalized Physical-knowledge-guided Dynamic Model for Underwater Image Enhancement
To tackle these challenges, we design a Generalized Underwater image enhancement method via a Physical-knowledge-guided Dynamic Model (short for GUPDM), consisting of three parts: Atmosphere-based Dynamic Structure (ADS), Transmission-guided Dynamic Structure (TDS), and Prior-based Multi-scale Structure (PMS).
NNVISR: Bring Neural Network Video Interpolation and Super Resolution into Video Processing Framework
We present NNVISR - an open-source filter plugin for the VapourSynth video processing framework, which facilitates the application of neural networks for various kinds of video enhancing tasks, including denoising, super resolution, interpolation, and spatio-temporal super-resolution.
From Generation to Suppression: Towards Effective Irregular Glow Removal for Nighttime Visibility Enhancement
Most existing Low-Light Image Enhancement (LLIE) methods are primarily designed to improve brightness in dark regions, which suffer from severe degradation in nighttime images.
Revisiting Domain-Adaptive 3D Object Detection by Reliable, Diverse and Class-balanced Pseudo-Labeling
Unsupervised domain adaptation (DA) with the aid of pseudo labeling techniques has emerged as a crucial approach for domain-adaptive 3D object detection.
FLGo: A Fully Customizable Federated Learning Platform
Federated learning (FL) has found numerous applications in healthcare, finance, and IoT scenarios.
TransRef: Multi-Scale Reference Embedding Transformer for Reference-Guided Image Inpainting
For precise utilization of the reference features for guidance, a reference-patch alignment (Ref-PA) module is proposed to align the patch features of the reference and corrupted images and harmonize their style differences, while a reference-patch transformer (Ref-PT) module is proposed to refine the embedded reference feature.
Spatial-Temporal Graph Learning with Adversarial Contrastive Adaptation
In addition, we introduce a cross-view contrastive learning paradigm to model the inter-dependencies across view-specific region representations and preserve underlying relation heterogeneity.
Long term 5G network traffic forecasting via modeling non-stationarity with deep learning
However, long term prediction horizon exposes the non-stationarity of series data, which deteriorates the performance of existing approaches.
One for All: Unified Workload Prediction for Dynamic Multi-tenant Edge Cloud Platforms
In this paper, we propose an end-to-end framework with global pooling and static content awareness, DynEformer, to provide a unified workload prediction scheme for dynamic MT-ECP.
DisCo: Distilled Student Models Co-training for Semi-supervised Text Mining
Many text mining models are constructed by fine-tuning a large deep pre-trained language model (PLM) in downstream tasks.
The 3rd Anti-UAV Workshop & Challenge: Methods and Results
Second, we set up two tracks for the first time, i. e., Anti-UAV Tracking and Anti-UAV Detection & Tracking.
Group Activity Recognition via Dynamic Composition and Interaction
Group composition tells us the location of people and their relations inside the group, while interaction reflects the relation between humans and objects outside the group.
Group Activity Recognition
Human-Object Interaction Detection
+1
Automated Spatio-Temporal Graph Contrastive Learning
In this paper, we tackle the above challenges by exploring the Automated Spatio-Temporal graph contrastive learning paradigm (AutoST) over the heterogeneous region graph generated from multi-view data sources.
ScanERU: Interactive 3D Visual Grounding based on Embodied Reference Understanding
Despite their effectiveness, existing methods suffer from the difficulty of low recognition accuracy in cases of multiple adjacent objects with similar appearances. To address this issue, this work intuitively introduces the human-robot interaction as a cue to facilitate the development of 3D visual grounding.
Adaptive Modeling of Uncertainties for Traffic Forecasting
We evaluated QuanTraffic by applying it to five representative DNN models for traffic forecasting across seven public datasets.
DiffusionAD: Norm-guided One-step Denoising Diffusion for Anomaly Detection
Anomaly detection has garnered extensive applications in real industrial manufacturing due to its remarkable effectiveness and efficiency.
Ranked #1 on
Unsupervised Anomaly Detection
on DAGM2007
Unleashing the Potential of Acquisition Functions in High-Dimensional Bayesian Optimization
Bayesian optimization (BO) is widely used to optimize expensive-to-evaluate black-box functions. BO first builds a surrogate model to represent the objective function and assesses its uncertainty.
Hierarchical Graph Neural Networks for Causal Discovery and Root Cause Localization
REASON consists of Topological Causal Discovery and Individual Causal Discovery.
Multilateral Semantic Relations Modeling for Image Text Retrieval
Specifically, a given query is first mapped as a probabilistic embedding to learn its true semantic distribution based on Mahalanobis distance.
Scratch Each Other's Back: Incomplete Multi-Modal Brain Tumor Segmentation via Category Aware Group Self-Support Learning
In this paper, considering the sensitivity of different modalities to diverse tumor regions, we propose a Category Aware Group Self-Support Learning framework, called GSS, to make up for the information deficit among the modalities in the individual modal feature extraction phase.
Good Is Bad: Causality Inspired Cloth-Debiasing for Cloth-Changing Person Re-Identification
Entangled representation of clothing and identity (ID)-intrinsic clues are potentially concomitant in conventional person Re-IDentification (ReID).
HOTCOLD Block: Fooling Thermal Infrared Detectors with a Novel Wearable Design
Adversarial attacks on thermal infrared imaging expose the risk of related applications.
Error-aware Quantization through Noise Tempering
In this work, we incorporate exponentially decaying quantization-error-aware noise together with a learnable scale of task loss gradient to approximate the effect of a quantization operator.
Prototypical Residual Networks for Anomaly Detection and Localization
Anomaly detection and localization are widely used in industrial manufacturing for its efficiency and effectiveness.
Ranked #4 on
Supervised Anomaly Detection
on MVTec AD
(using extra training data)
Instance-level Heterogeneous Domain Adaptation for Limited-labeled Sketch-to-Photo Retrieval
Therefore, previous works pre-train their models on rich-labeled photo retrieval data (i. e., source domain) and then fine-tune them on the limited-labeled sketch-to-photo retrieval data (i. e., target domain).
Ranked #1 on
Image Retrieval
on PKU-Reid
FedGS: Federated Graph-based Sampling with Arbitrary Client Availability
Second, constrained by the far-distance in data distribution of the sampled clients, we further minimize the variance of the numbers of times that the clients are sampled, to mitigate long-term bias.
On Inferring User Socioeconomic Status with Mobility Records
The DeepSEI model incorporates two networks called deep network and recurrent network, which extract the features of the mobility records from three aspects, namely spatiality, temporality and activity, one at a coarse level and the other at a detailed level.
Online Anomalous Subtrajectory Detection on Road Networks with Deep Reinforcement Learning
Detecting anomalous trajectories has become an important task in many location-based applications.
UmeTrack: Unified multi-view end-to-end hand tracking for VR
In this paper, we present a unified end-to-end differentiable framework for multi-view, multi-frame hand tracking that directly predicts 3D hand pose in world space.
A Survey of Dataset Refinement for Problems in Computer Vision Datasets
In addition, we organize these dataset refinement methods according to the addressed data problems and provide a systematic comparative description.
Context-Enhanced Stereo Transformer
We construct our stereo depth estimation model, Context Enhanced Stereo Transformer (CSTR), by plugging CEP into the state-of-the-art stereo depth estimation method Stereo Transformer.
SQuAT: Sharpness- and Quantization-Aware Training for BERT
Quantization is an effective technique to reduce memory footprint, inference latency, and power consumption of deep learning models.
Physical Adversarial Attack meets Computer Vision: A Decade Survey
Building upon this foundation, we uncover the pervasive role of artifacts carrying adversarial perturbations in the physical world.
Faith: An Efficient Framework for Transformer Verification on GPUs
In this paper, we propose Faith, an efficient framework for transformer verification on GPUs.
MGG: Accelerating Graph Neural Networks with Fine-grained intra-kernel Communication-Computation Pipelining on Multi-GPU Platforms
For irregularly sparse and fine-grained GNN workloads, such solutions miss the opportunity to jointly schedule/optimize the computation and communication operations for high-performance delivery.
Detecting Algorithmically Generated Domains Using a GCNN-LSTM Hybrid Neural Network
Domain generation algorithm (DGA) is used by botnets to build a stealthy command and control (C&C) communication channel between the C&C server and the bots.
Understanding Adversarial Robustness of Vision Transformers via Cauchy Problem
Recent research on the robustness of deep learning has shown that Vision Transformers (ViTs) surpass the Convolutional Neural Networks (CNNs) under some perturbations, e. g., natural corruption, adversarial attacks, etc.
Reference-Guided Texture and Structure Inference for Image Inpainting
Existing learning-based image inpainting methods are still in challenge when facing complex semantic environments and diverse hole patterns.
Magic ELF: Image Deraining Meets Association Learning and Transformer
Convolutional neural network (CNN) and Transformer have achieved great success in multimedia applications.
Balanced Contrastive Learning for Long-Tailed Visual Recognition
In this paper, we focus on representation learning for imbalanced data.
You Only Align Once: Bidirectional Interaction for Spatial-Temporal Video Super-Resolution
Spatial-Temporal Video Super-Resolution (ST-VSR) technology generates high-quality videos with higher resolution and higher frame rates.
Nonparametric Embeddings of Sparse High-Order Interaction Events
High-order interaction events are common in real-world applications.
Nonparametric Factor Trajectory Learning for Dynamic Tensor Decomposition
In practice, tensor data is often accompanied by temporal information, namely the time points when the entry values were generated.
Infinite-Fidelity Coregionalization for Physical Simulation
Our model can interpolate and/or extrapolate the predictions to novel fidelities, which can be even higher than the fidelities of training data.
Towards Generalizable Person Re-identification with a Bi-stream Generative Model
Guided by original pedestrian images, one stream is employed to learn a camera-invariant global feature for the CC problem via filtering cross-camera interference factors.
Domain Generalization
Generalizable Person Re-identification
Improving Generalization of Metric Learning via Listwise Self-distillation
Most deep metric learning (DML) methods employ a strategy that forces all positive samples to be close in the embedding space while keeping them away from negative ones.
Unsupervised Foggy Scene Understanding via Self Spatial-Temporal Label Diffusion
Specifically, based on the two discoveries of local spatial similarity and adjacent temporal correspondence of the sequential image data, we propose a novel Target-Domain driven pseudo label Diffusion (TDo-Dif) scheme.
Geo-Localization via Ground-to-Satellite Cross-View Image Retrieval
The large variation of viewpoint and irrelevant content around the target always hinder accurate image retrieval and its subsequent tasks.
Spatial-Temporal Space Hand-in-Hand: Spatial-Temporal Video Super-Resolution via Cycle-Projected Mutual Learning
Specifically, we propose to exploit the mutual information among them via iterative up-and-down projections, where the spatial and temporal features are fully fused and distilled, helping the high-quality video reconstruction.
Deep Quality Assessment of Compressed Videos: A Subjective and Objective Study
In this work, a semi-automatic labeling method is adopted to build a large-scale compressed video quality database, which allows us to label a large number of compressed videos with manageable human workload.
A Survey on Legal Judgment Prediction: Datasets, Metrics, Models and Challenges
In this paper, to address the current lack of comprehensive survey of existing LJP tasks, datasets, models and evaluations, (1) we analyze 31 LJP datasets in 6 languages, present their construction process and define a classification method of LJP with 3 different attributes; (2) we summarize 14 evaluation metrics under four categories for different outputs of LJP tasks; (3) we review 12 legal-domain pretrained models in 3 languages and highlight 3 major research directions for LJP; (4) we show the state-of-art results for 8 representative datasets from different court cases and discuss the open challenges.
Unsupervised Manga Character Re-identification via Face-body and Spatial-temporal Associated Clustering
In the past few years, there has been a dramatic growth in e-manga (electronic Japanese-style comics).
Exploring the Impact of Negative Samples of Contrastive Learning: A Case Study of Sentence Embedding
We define a maximum traceable distance metric, through which we learn to what extent the text contrastive learning benefits from the historical information of negative samples.
AutoIP: A United Framework to Integrate Physics into Gaussian Processes
Physical modeling is critical for many modern science and engineering applications.
Visual-Tactile Sensing for Real-time Liquid Volume Estimation in Grasping
We propose a deep visuo-tactile model for realtime estimation of the liquid inside a deformable container in a proprioceptive way. We fuse two sensory modalities, i. e., the raw visual inputs from the RGB camera and the tactile cues from our specific tactile sensor without any extra sensor calibrations. The robotic system is well controlled and adjusted based on the estimation model in real time.
Dynamic GPU Energy Optimization for Machine Learning Training Workloads
This paper presents GPOEO, an online GPU energy optimization framework for machine learning training workloads.
TC-GNN: Bridging Sparse GNN Computation and Dense Tensor Cores on GPUs
Recently, graph neural networks (GNNs), as the backbone of graph-based machine learning, demonstrate great success in various domains (e. g., e-commerce).
Self-Adaptable Point Processes with Nonparametric Time Decays
Specifically, we use an embedding to represent each event type and model the event influence as an unknown function of the embeddings and time span.
Both Style and Fog Matter: Cumulative Domain Adaptation for Semantic Foggy Scene Understanding
Unlike previous methods that mainly focus on closing the domain gap caused by fog -- defogging the foggy images or fogging the clear images, we propose to alleviate the domain gap by considering fog influence and style variation simultaneously.
Ranked #4 on
Domain Adaptation
on Cityscapes-to-FoggyZurich
Stable and Compact Face Recognition via Unlabeled Data Driven Sparse Representation-Based Classification
The proposed model aims to mine the hidden semantic information and intrinsic structure information of all available data, which is suitable for few labeled samples and proportion imbalance between labeled samples and unlabeled samples problems in frontal face recognition.
Optimizing Sparse Matrix Multiplications for Graph Neural Networks
Our model is first trained offline using training matrix samples, and the trained model can be applied to any input matrix and GNN kernels with SpMM computation.
Nonparametric Sparse Tensor Factorization with Hierarchical Gamma Processes
Compared with the existent works, our model not only leverages the structural information underlying the observed entry indices, but also provides extra interpretability and flexibility -- it can simultaneously estimate a set of location factors about the intrinsic properties of the tensor nodes, and another set of sociability factors reflecting their extrovert activity in interacting with others; users are free to choose a trade-off between the two types of factors.
Meta-Learning with Adjoint Methods
the initialization, we only need to run the standard ODE solver twice -- one is forward in time that evolves a long trajectory of gradient flow for the sampled task; the other is backward and solves the adjoint ODE.
GANet: Glyph-Attention Network for Few-Shot Font Generation
Font generation is a valuable but challenging task, it is time consuming and costly to design font libraries which cover all glyphs with various styles.
Detecting Mitosis against Domain Shift using a Fused Detector and Deep Ensemble Classification Model for MIDOG Challenge
Mitotic figure count is an important marker of tumor proliferation and has been shown to be associated with patients' prognosis.
Modularized Interaction Network for Named Entity Recognition
Although the existing Named Entity Recognition (NER) models have achieved promising performance, they suffer from certain drawbacks.
DISP6D: Disentangled Implicit Shape and Pose Learning for Scalable 6D Pose Estimation
Scalable 6D pose estimation for rigid objects from RGB images aims at handling multiple objects and generalizing to novel objects.
Spectrum Gaussian Processes Based On Tunable Basis Functions
Spectral approximation and variational inducing learning for the Gaussian process are two popular methods to reduce computational complexity.
Reinforcement Learning-based Dialogue Guided Event Extraction to Exploit Argument Relations
Our approach leverages knowledge of the already extracted arguments of the same sentence to determine the role of arguments that would be difficult to decide individually.
Zero-shot Node Classification with Decomposed Graph Prototype Network
Node classification is a central task in graph data analysis.
Unsupervised Video Person Re-identification via Noise and Hard frame Aware Clustering
NHAC consists of a graph trimming module and a node re-sampling module.
Effect of Adaptive and Fixed Shared Steering Control on Distracted Driver Behavior
Evaluation results indicated that, for both attentive and distracted drivers, haptic guidance with adaptive authority yielded lower driver workload and reduced lane departure risk than manual driving and fixed authority.
CNTLS: A Benchmark Dataset for Abstractive or Extractive Chinese Timeline Summarization
We meticulously analyze the corpus using well-known metrics, focusing on the style of the summaries and the complexity of the summarization task.
Federated Learning with Fair Averaging
Fairness has emerged as a critical problem in federated learning (FL).
Expanding Semantic Knowledge for Zero-shot Graph Embedding
Zero-shot graph embedding is a major challenge for supervised graph learning.
Degrade is Upgrade: Learning Degradation for Low-light Image Enhancement
Different from existing methods tending to accomplish the relighting task directly by ignoring the fidelity and naturalness recovery, we investigate the intrinsic degradation and relight the low-light image while refining the details and color in two steps.
A Reinforcement Learning Based R-Tree for Spatial Data Indexing in Dynamic Environments
Learned indices have been proposed to replace classic index structures like B-Tree with machine learning (ML) models.
Model Rectification via Unknown Unknowns Extraction from Deployment Samples
Model deficiency that results from incomplete training data is a form of structural blindness that leads to costly errors, oftentimes with high confidence.
Deep unsupervised anomaly detection
This paper proposes a novel method to detect anomalies in large datasets under a fully unsupervised setting.
Image Inpainting Guided by Coherence Priors of Semantics and Textures
In this paper, we introduce coherence priors between the semantics and textures which make it possible to concentrate on completing separate textures in a semantic-wise manner.
Re-identification = Retrieval + Verification: Back to Essence and Forward with a New Metric
In essence, current re-ID overemphasizes the importance of retrieval but underemphasizes that of verification, \textit{i. e.}, all returned images are considered as the target.
Intention-Based Lane Changing and Lane Keeping Haptic Guidance Steering System
By exerting continuous torque on the steering wheel, both the driver and support system can share lateral control of the vehicle.
Towards Context-Aware Code Comment Generation
Code comments are vital for software maintenance and comprehension, but many software projects suffer from the lack of meaningful and up-to-date comments in practice.
Learning Personalized Discretionary Lane-Change Initiation for Fully Autonomous Driving Based on Reinforcement Learning
In this article, the authors present a novel method to learn the personalized tactic of discretionary lane-change initiation for fully autonomous vehicles through human-computer interactions.
Universal Weighting Metric Learning for Cross-Modal Matching
Furthermore, we introduce a new polynomial loss under the universal weighting framework, which defines a weight function for the positive and negative informative pairs respectively.
Uncertainty-aware Attention Graph Neural Network for Defending Adversarial Attacks
With the increasing popularity of graph-based learning, graph neural networks (GNNs) emerge as the essential tool for gaining insights from graphs.
DTDN: Dual-task De-raining Network
Removing rain streaks from rainy images is necessary for many tasks in computer vision, such as object detection and recognition.
Towards Unsupervised Crowd Counting via Regression-Detection Bi-knowledge Transfer
We formulate the mutual transformations between the outputs of regression- and detection-based models as two scene-agnostic transformers which enable knowledge distillation between the two models.
Lifelong Property Price Prediction: A Case Study for the Toronto Real Estate Market
As a departure from prior work, Luce organizes the house data in a heterogeneous information network (HIN) where graph nodes are house entities and attributes that are important for house price valuation.
3D Spectrum Mapping Based on ROI-Driven UAV Deployment
Given the explosive growth of Internet of Things (IoT) devices ranging from the two-dimensional (2D) ground to the three-dimensional (3D) space, it is a necessity to establish a 3D spectrum map to comprehensively present and effectively manage the 3D spatial spectrum resources in smart city infrastructures.
Exploring Image Enhancement for Salient Object Detection in Low Light Images
Low light images captured in a non-uniform illumination environment usually are degraded with the scene depth and the corresponding environment lights.
Streaming Probabilistic Deep Tensor Factorization
Our algorithm provides responsive incremental updates for the posterior of the latent factors and NN weights upon receiving new tensor entries, and meanwhile select and inhibit redundant/useless weights.
Network Embedding with Completely-imbalanced Labels
Network embedding, aiming to project a network into a low-dimensional space, is increasingly becoming a focus of network research.
Road Network Metric Learning for Estimated Time of Arrival
To address the data sparsity problem, we propose the Road Network Metric Learning framework for ETA (RNML-ETA).
Sparse Gaussian Process Based On Hat Basis Functions
Based on hat basis functions, we propose a new sparse Gaussian process method to solve the unconstrained regression problem.
Multi-Fidelity High-Order Gaussian Processes for Physical Simulation
To address these issues, we propose Multi-Fidelity High-Order Gaussian Process (MFHoGP) that can capture complex correlations both between the outputs and between the fidelities to enhance solution estimation, and scale to large numbers of outputs.
Physics Informed Deep Kernel Learning
Deep kernel learning is a promising combination of deep neural networks and nonparametric function learning.
FMA-ETA: Estimating Travel Time Entirely Based on FFN With Attention
Estimated time of arrival (ETA) is one of the most important services in intelligent transportation systems and becomes a challenging spatial-temporal (ST) data mining task in recent years.
Fusion Recurrent Neural Network
Furthermore, in order to evaluate Fusion RNN's sequence feature extraction capability, we choose a representative data mining task for sequence data, estimated time of arrival (ETA) and present a novel model based on Fusion RNN.
Neighborhood Matching Network for Entity Alignment
This paper presents Neighborhood Matching Network (NMN), a novel entity alignment framework for tackling the structural heterogeneity challenge.
Constructing Geographic and Long-term Temporal Graph for Traffic Forecasting
Recently, deep learning based methods have achieved promising results by adopting graph convolutional network (GCN) to extract the spatial correlations and recurrent neural network (RNN) to capture the temporal dependencies.
Guidance and Evaluation: Semantic-Aware Image Inpainting for Mixed Scenes
Completing a corrupted image with correct structures and reasonable textures for a mixed scene remains an elusive challenge.
Optimizing Streaming Parallelism on Heterogeneous Many-Core Architectures: A Machine Learning Based Approach
This article presents an automatic approach to quickly derive a good solution for hardware resource partition and task granularity for task-based parallel applications on heterogeneous many-core architectures.
Efficient and Effective Similar Subtrajectory Search with Deep Reinforcement Learning
Similar trajectory search is a fundamental problem and has been well studied over the past two decades.
Robotic Cane as a Soft SuperLimb for Elderly Sit-to-Stand Assistance
Many researchers have identified robotics as a potential solution to the aging population faced by many developed and developing countries.
Curriculum Audiovisual Learning
Associating sound and its producer in complex audiovisual scene is a challenging task, especially when we are lack of annotated training data.
Learning Canonical Shape Space for Category-Level 6D Object Pose and Size Estimation
To tackle intra-class shape variations, we learn canonical shape space (CASS), a unified representation for a large variety of instances of a certain object category.
Characterizing Scalability of Sparse Matrix-Vector Multiplications on Phytium FT-2000+ Many-cores
Understanding the scalability of parallel programs is crucial for software optimization and hardware architecture design.
Optimizing Deep Learning Inference on Embedded Systems Through Adaptive Model Selection
For image classification, we achieve a 1. 8x reduction in inference time with a 7. 52% improvement in accuracy, over the most-capable single DNN model.
Conditional Expectation Propagation
Expectation propagation (EP) is a powerful approximate inference algorithm.
BAIL: Best-Action Imitation Learning for Batch Deep Reinforcement Learning
There has recently been a surge in research in batch Deep Reinforcement Learning (DRL), which aims for learning a high-performing policy from a given dataset without additional interactions with the environment.
Jointly Learning Entity and Relation Representations for Entity Alignment
Entity alignment is a viable means for integrating heterogeneous knowledge among different knowledge graphs (KGs).
Ranked #18 on
Entity Alignment
on DBP15k zh-en
(using extra training data)
Relation-Aware Entity Alignment for Heterogeneous Knowledge Graphs
Entity alignment is the task of linking entities with the same real-world identity from different knowledge graphs (KGs), which has been recently dominated by embedding-based methods.
Ranked #20 on
Entity Alignment
on DBP15k zh-en
(using extra training data)
Zero-Shot Feature Selection via Transferring Supervised Knowledge
Feature selection, an effective technique for dimensionality reduction, plays an important role in many machine learning systems.
Robust Linear Discriminant Analysis Using Ratio Minimization of L1,2-Norms
In this paper, we propose a novel robust linear discriminant analysis method based on the L1, 2-norm ratio minimization.
Beyond Intra-modality: A Survey of Heterogeneous Person Re-identification
An efficient and effective person re-identification (ReID) system relieves the users from painful and boring video watching and accelerates the process of video analysis.
Less Memory, Faster Speed: Refining Self-Attention Module for Image Reconstruction
Self-attention (SA) mechanisms can capture effectively global dependencies in deep neural networks, and have been applied to natural language processing and image processing successfully.
DotSCN: Group Re-identification via Domain-Transferred Single and Couple Representation Learning
To gain the superiority of deep learning models, we treat a group as multiple persons and transfer the domain of a labeled ReID dataset to a G-ReID target dataset style to learn single representations.
Ensemble Super-Resolution with A Reference Dataset
In this paper, we present a simple but effective single image SR method based on ensemble learning, which can produce a better performance than that could be obtained from any of SR methods to be ensembled (or called component super-resolvers).
Illumination-Adaptive Person Re-identification
To demonstrate the illumination issue and to evaluate our model, we construct two large-scale simulated datasets with a wide range of illumination variations.
Robust Semantic Segmentation By Dense Fusion Network On Blurred VHR Remote Sensing Images
Robust semantic segmentation of VHR remote sensing images from UAV sensors is critical for earth observation, land use, land cover or mapping applications.
