Search Results for author:
Found 362 papers, 140 papers with code
Dome-DETR: DETR with Density-Oriented Feature-Query Manipulation for Efficient Tiny Object Detection
Tiny object detection plays a vital role in drone surveillance, remote sensing, and autonomous systems, enabling the identification of small targets across vast landscapes.
Efficient Spiking Point Mamba for Point Cloud Analysis
Due to the poor performance of simply transferring Mamba to 3D SNNs, SPM is designed to utilize both the sequence modeling capabilities of Mamba and the temporal feature extraction of SNNs.
Learning Physics-Informed Color-Aware Transforms for Low-Light Image Enhancement
To address these challenges, we introduce a Physics-informed Color-aware Transform (PiCat), a learning-based framework that converts low-light images from the sRGB color space into deep illumination-invariant descriptors via our proposed Color-aware Transform (CAT).
LightFormer: A lightweight and efficient decoder for remote sensing image segmentation
Deep learning techniques have achieved remarkable success in the semantic segmentation of remote sensing images and in land-use change detection.
Robust Offline Imitation Learning Through State-level Trajectory Stitching
Imitation learning (IL) has proven effective for enabling robots to acquire visuomotor skills through expert demonstrations.
Fast and Physically-based Neural Explicit Surface for Relightable Human Avatars
Efficiently modeling relightable human avatars from sparse-view videos is crucial for AR/VR applications.
Model Risk Management for Generative AI In Financial Institutions
The success of OpenAI's ChatGPT in 2023 has spurred financial enterprises into exploring Generative AI applications to reduce costs or drive revenue within different lines of businesses in the Financial Industry.
MagicComp: Training-free Dual-Phase Refinement for Compositional Video Generation
Text-to-video (T2V) generation has made significant strides with diffusion models.
Defense Against Model Stealing Based on Account-Aware Distribution Discrepancy
Malicious users attempt to replicate commercial models functionally at low cost by training a clone model with query responses.
R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning
To address this, we propose \textbf{R1-Searcher}, a novel two-stage outcome-based RL approach designed to enhance the search capabilities of LLMs.
An Empirical Study on Eliciting and Improving R1-like Reasoning Models
This approach achieves a remarkable accuracy of 86. 67% with greedy search on AIME 2024, underscoring its effectiveness in enhancing model capabilities.
ProAI: Proactive Multi-Agent Conversational AI with Structured Knowledge Base for Psychiatric Diagnosis
Most LLM-driven conversational AI systems operate reactively, responding to user prompts without guiding the interaction.
Pleno-Generation: A Scalable Generative Face Video Compression Framework with Bandwidth Intelligence
The novel PGen framework leverages scalable representation and layered reconstruction for Generative Face Video Compression (GFVC), in an attempt to imbue the bitstream with intelligence in different granularity.
SphereFusion: Efficient Panorama Depth Estimation via Gated Fusion
Specifically, SphereFusion initially employs 2D image convolution and mesh operations to extract two distinct types of features from the panorama image in both equirectangular and spherical projection domains.
Every Angle Is Worth A Second Glance: Mining Kinematic Skeletal Structures from Multi-view Joint Cloud
Multi-person motion capture over sparse angular observations is a challenging problem under interference from both self- and mutual-occlusions.
Teaching Language Models to Critique via Reinforcement Learning
Teaching large language models (LLMs) to critique and refine their outputs is crucial for building systems that can iteratively improve, yet it is fundamentally limited by the ability to provide accurate judgments and actionable suggestions.
Hybrid Two-Stage Reconstruction of Multiscale Subsurface Flow with Physics-informed Residual Connected Neural Operator
In the first stage, a data-driven model is used to reconstruct the multiscale basis function based on the permeability field to achieve effective dimensionality reduction while preserving the necessary multiscale features.
Hierarchical Banzhaf Interaction for General Video-Language Representation Learning
As an important subfield, video-language representation learning focuses on learning representations using global semantic interactions between pre-defined video-text pairs.
Scalable Hierarchical Reinforcement Learning for Hyper Scale Multi-Robot Task Planning
Also, our planner can successfully scale up to hyper scale MRTP instances in RMFS with up to 200 robots and 1000 retrieval racks on unlearned maps while keeping superior performance over other methods.
YuLan-Mini: An Open Data-efficient Language Model
Effective pre-training of large language models (LLMs) has been challenging due to the immense resource demands and the complexity of the technical processes involved.
Knowing Where to Focus: Attention-Guided Alignment for Text-based Person Search
be masked fail to contribute efficient interaction in the cross-modal MLM and hampers the representation alignment.
Seed-CTS: Unleashing the Power of Tree Search for Superior Performance in Competitive Coding Tasks
Leveraging Qwen2. 5-Coder-32B-Instruct, our approach achieves a pass rate of 0. 305 on LiveCodeBench-Hard, surpassing the pass@100 performance of GPT4o-0513 (0. 245).
Imitate, Explore, and Self-Improve: A Reproduction Report on Slow-thinking Reasoning Systems
We introduce an ``imitate, explore, and self-improve'' framework, denoted as \textbf{STILL-2}, as our primary technical approach to train the reasoning model.
Adversarial Purification by Consistency-aware Latent Space Optimization on Data Manifolds
Leveraging this insight, we propose Consistency Model-based Adversarial Purification (CMAP), which optimizes vectors within the latent space of a pre-trained consistency model to generate samples for restoring clean data.
Mind the Gap: Towards Generalizable Autonomous Penetration Testing via Domain Randomization and Meta-Reinforcement Learning
GAP introduces a Real-to-Sim-to-Real pipeline that (a) enables end-to-end policy learning in unknown real environments while constructing realistic simulations; (b) improves agents' generalization ability by leveraging domain randomization and meta-RL learning. Specially, we are among the first to apply domain randomization in autonomous pentesting and propose a large language model-powered domain randomization method for synthetic environment generation.
RelayGS: Reconstructing Dynamic Scenes with Large-Scale and Complex Motions via Relay Gaussians
Finally, we jointly learn the scene's temporal motion and refine the canonical Gaussians learned from the first two stages.
FullStack Bench: Evaluating LLMs as Full Stack Coders
As the capabilities of code large language models (LLMs) continue to expand, their applications across diverse code intelligence domains are rapidly increasing.
Conditional Distribution Learning on Graphs
To avoid the conflict between the MPM and the CL of negative pairs, positive pairs of node representations are retained for measuring the similarity between the original features and the corresponding weakly augmented features.
Enhancing LLM Reasoning with Reward-guided Tree Search
This framework is implemented by integrating the policy model, reward model, and search algorithm.
HiCoM: Hierarchical Coherent Motion for Streamable Dynamic Scene with 3D Gaussian Splatting
The online reconstruction of dynamic scenes from multi-view streaming videos faces significant challenges in training, rendering and storage efficiency.
An Efficient Hierarchical Preconditioner-Learner Architecture for Reconstructing Multi-scale Basis Functions of High-dimensional Subsurface Fluid Flow
This model offers a novel method for efficient and accurate subsurface fluid flow modeling, with promising potential for more complex real-world applications.
The D-Subspace Algorithm for Online Learning over Distributed Networks
This material introduces the D-Subspace algorithm derived on the basis of the centralized algorithm [1], which originally addresses parameter estimation problems under a subspace constraint.
Standardizing Generative Face Video Compression using Supplemental Enhancement Information
This paper proposes a Generative Face Video Compression (GFVC) approach using Supplemental Enhancement Information (SEI), where a series of compact spatial and temporal representations of a face video signal (i. e., 2D/3D key-points, facial semantics and compact features) can be coded using SEI message and inserted into the coded video bitstream.
Graph Neural Flows for Unveiling Systemic Interactions Among Irregularly Sampled Time Series
Interacting systems are prevalent in nature.
Beyond GFVC: A Progressive Face Video Compression Framework with Adaptive Visual Tokens
Recently, deep generative models have greatly advanced the progress of face video coding towards promising rate-distortion performance and diverse application functionalities.
Identifying Money Laundering Subgraphs on the Blockchain
Furthermore, we demonstrate the effectiveness of RevFilter in discovering new suspicious subgraphs, confirming its utility for practical AML.
Remote Sensing Image Segmentation Using Vision Mamba and Multi-Scale Multi-Frequency Feature Fusion
This method designs a cross-scanning visual state space block (CVSSBlock) that uses cross 2D scanning (CS2D) to fully capture global information from multiple directions, while by incorporating convolutional neural network branches to overcome the constraints of Vision Mamba (VMamba) in acquiring local information, this approach facilitates a comprehensive analysis of both global and local features.
Multimodal Large Language Models for Inverse Molecular Design with Retrosynthetic Planning
While large language models (LLMs) have integrated images, adapting them to graphs remains challenging, limiting their applications in materials and drug design.
Tannenbaum's gain-margin optimization meets Polyak's heavy-ball algorithm
The link between first-order optimization methods and robust control theory sheds new light into limits of algorithmic performance for such methods, and suggests a new framework where similar computational problems can be systematically studied and algorithms optimized.
Unrolling Plug-and-Play Network for Hyperspectral Unmixing
The carefully designed unfolding deep architecture is used to learn the spectral and spatial information from the hyperspectral image, which we refer to as inner priors.
Hierarchical Sparse Representation Clustering for High-Dimensional Data Streams
Second, these algorithms are highly sensitive to the noise contained in high-dimensional data streams.
Dynamic Self-Consistency: Leveraging Reasoning Paths for Efficient LLM Sampling
Self-Consistency (SC) is a widely used method to mitigate hallucinations in Large Language Models (LLMs) by sampling the LLM multiple times and outputting the most frequent solution.
Do Graph Neural Networks Work for High Entropy Alloys?
Graph neural networks (GNNs) have excelled in predictive modeling for both crystals and molecules, owing to the expressiveness of graph representations.
PartFormer: Awakening Latent Diverse Representation from Vision Transformer for Object Re-Identification
Extracting robust feature representation is critical for object re-identification to accurately identify objects across non-overlapping cameras.
Ranked #23 on
Person Re-Identification
on Occluded-DukeMTMC
CoT Rerailer: Enhancing the Reliability of Large Language Models in Complex Reasoning Tasks through Error Detection and Correction
We propose the CoT Rerailer to address these challenges, employing self-consistency and multi-agent debate systems to identify and rectify errors in the reasoning process.
Procedural Synthesis of Synthesizable Molecules
Drawing inspiration from syntax-guided synthesis approaches, we decouple the syntactic skeleton from the semantics of a synthetic tree to create a bilevel framework for reasoning about the combinatorial space of synthesis pathways.
A Digital Twin Framework Utilizing Machine Learning for Robust Predictive Maintenance: Enhancing Tire Health Monitoring
We introduce a novel digital twin framework for predictive maintenance of long-term physical systems.
Towards Effective and Efficient Continual Pre-training of Large Language Models
To make the CPT approach more traceable, this paper presents a technical report for continually pre-training Llama-3 (8B), which significantly enhances the Chinese language ability and scientific reasoning ability of the backbone model.
Make a Strong Teacher with Label Assistance: A Novel Knowledge Distillation Approach for Semantic Segmentation
Specifically, for the teacher model training, we propose to noise the label and then incorporate it into input to effectively boost the lightweight teacher performance.
Automated Label Unification for Multi-Dataset Semantic Segmentation with GNNs
This enables semantic segmentation models to be trained simultaneously on multiple datasets, resulting in performance improvements.
Local Action-Guided Motion Diffusion Model for Text-to-Motion Generation
Specifically, we provide an automated method for reference local action sampling and leverage graph attention networks to assess the guiding weight of each local action in the overall motion synthesis.
LLMBox: A Comprehensive Library for Large Language Models
To facilitate the research on large language models (LLMs), this paper presents a comprehensive and unified library, LLMBox, to ease the development, use, and evaluation of LLMs.
Unveiling the Flaws: Exploring Imperfections in Synthetic Data and Mitigation Strategies for Large Language Models
Synthetic data has been proposed as a solution to address the issue of high-quality data scarcity in the training of large language models (LLMs).
Unlock the Correlation between Supervised Fine-Tuning and Reinforcement Learning in Training Code Large Language Models
A large number of work has been conducted to improve the model's performance on code-related benchmarks with either modifications to the algorithm or refinement of the dataset.
Make Your Actor Talk: Generalizable and High-Fidelity Lip Sync with Motion and Appearance Disentanglement
Instead, we propose to disentangle the motion and appearance, and then generate them one by one with a speech-to-motion diffusion model and a motion-conditioned appearance generation model.
Exploring Mathematical Extrapolation of Large Language Models with Synthetic Data
In this paper, through a newly proposed arithmetical puzzle problem, we show that the model can perform well on multi-step reasoning tasks via fine-tuning on high-quality synthetic data.
Graph Neural Preconditioners for Iterative Solutions of Sparse Linear Systems
Empirical evaluation on over 800 matrices suggests that the construction time of these graph neural preconditioners (GNPs) is more predictable and can be much shorter than that of other widely used ones, such as ILU and AMG, while the execution time is faster than using a Krylov method as the preconditioner, such as in inner-outer GMRES.
Learning-Based Intermittent CSI Estimation with Adaptive Intervals in Integrated Sensing and Communication Systems
Due to the distinct objectives and multipath utilization mechanisms between the communication module and radar module, the system design of integrated sensing and communication (ISAC) necessitates two types of channel state information (CSI), i. e., communication CSI representing the whole channel gain and phase shifts, and radar CSI exclusively focused on target mobility and position information.
HARIS: Human-Like Attention for Reference Image Segmentation
In this paper, we propose a referring image segmentation method called HARIS, which introduces the Human-Like Attention mechanism and uses the parameter-efficient fine-tuning (PEFT) framework.
GraCo: Granularity-Controllable Interactive Segmentation
In this work, we introduce Granularity-Controllable Interactive Segmentation (GraCo), a novel approach that allows precise control of prediction granularity by introducing additional parameters to input.
The Shape of Money Laundering: Subgraph Representation Learning on the Blockchain with the Elliptic2 Dataset
We posit that certain domain applications, such as anti-money laundering (AML), are inherently subgraph problems and mainstream graph techniques have been operating at a suboptimal level of abstraction.
Generation of Uncorrelated Residual Variables for Chemical Process Fault Diagnosis via Transfer Learning-based Input-Output Decoupled Network
However, traditional methods exhibit limited effectiveness in modeling high-dimensional nonlinearity and big data, and the decoupling idea has not been well-valued in data-driven frameworks.
Adaptive Catalyst Discovery Using Multicriteria Bayesian Optimization with Representation Learning
The results demonstrate that our approach achieves high prediction accuracy, facilitates interpretable feature extraction, and enables multicriteria design optimization, leading to significant reduction of computing power and time (10x reduction of required DFT calculations) in high-performance catalyst discovery.
ParCo: Part-Coordinating Text-to-Motion Synthesis
However, these methods encounter challenges such as the lack of coordination between different part motions and difficulties for networks to understand part concepts.
Ranked #16 on
Motion Synthesis
on HumanML3D
Invertible Diffusion Models for Compressed Sensing
To enable such memory-intensive end-to-end fine-tuning, we propose a novel two-level invertible design to transform both (1) multi-step sampling process and (2) noise estimation U-Net in each step into invertible networks.
Deep unfolding Network for Hyperspectral Image Super-Resolution with Automatic Exposure Correction
In recent years, the fusion of high spatial resolution multispectral image (HR-MSI) and low spatial resolution hyperspectral image (LR-HSI) has been recognized as an effective method for HSI super-resolution (HSI-SR).
Representing Molecules as Random Walks Over Interpretable Grammars
Recent research in molecular discovery has primarily been devoted to small, drug-like molecules, leaving many similarly important applications in material design without adequate technology.
FaceChain-SuDe: Building Derived Class to Inherit Category Attributes for One-shot Subject-Driven Generation
In this paper, motivated by object-oriented programming, we model the subject as a derived class whose base class is its semantic category.
Causal Prototype-inspired Contrast Adaptation for Unsupervised Domain Adaptive Semantic Segmentation of High-resolution Remote Sensing Imagery
Then, a causal prototypical contrast module is used to learn domain invariant causal features.
Towards a Digital Twin Framework in Additive Manufacturing: Machine Learning and Bayesian Optimization for Time Series Process Optimization
Our work presents a digital twin (DT) framework for real-time predictive control of DED process parameters to meet specific design objectives.
Inverse Optimal Control for Linear Quadratic Tracking with Unknown Target States
A computationally efficient and numerically reliable parameter identification algorithm is proposed by equating optimal control strategies with a system of linear equations, and the associated relative error upper bound is derived in terms of data volume and signal-to-noise ratio.
Boundary Exploration for Bayesian Optimization With Unknown Physical Constraints
In this paper, we observe that in such scenarios optimal solution typically lies on the boundary between feasible and infeasible regions of the design space, making it considerably more difficult than that with interior optima.
Consistency Enhancement-Based Deep Multiview Clustering via Contrastive Learning
Furthermore, the representation process for clustering is enhanced through spectral clustering, and the consistency across multiple views is improved.
Structured Code Representations Enable Data-Efficient Adaptation of Code Language Models
In this work, we explore data-efficient adaptation of pre-trained code models by further pre-training and fine-tuning them with program structures.
Instance Brownian Bridge as Texts for Open-vocabulary Video Instance Segmentation
To mold instance queries to follow Brownian bridge and accomplish alignment with class texts, we design Bridge-Text Alignment (BTA) to learn discriminative bridge-level representations of instances via contrastive objectives.
Exploring Latent Cross-Channel Embedding for Accurate 3D Human Pose Reconstruction in a Diffusion Framework
However, there is still ample room for improvement as these methods often overlook the exploration of correlation between the 2D and 3D joint-level features.
The Dawn After the Dark: An Empirical Study on Factuality Hallucination in Large Language Models
To tackle the LLM hallucination, three key questions should be well studied: how to detect hallucinations (detection), why do LLMs hallucinate (source), and what can be done to mitigate them (mitigation).
Mind Marginal Non-Crack Regions: Clustering-Inspired Representation Learning for Crack Segmentation
Crack segmentation datasets make great efforts to obtain the ground truth crack or non-crack labels as clearly as possible.
MolSets: Molecular Graph Deep Sets Learning for Mixture Property Modeling
This complexity is particularly evident in molecular mixtures, a frequently explored space for materials such as battery electrolytes.
Multi-scale Progressive Feature Embedding for Accurate NIR-to-RGB Spectral Domain Translation
To address these challenges, we propose to colorize NIR images via a multi-scale progressive feature embedding network (MPFNet), with the guidance of grayscale image colorization.
Hyperspectral Image Reconstruction via Combinatorial Embedding of Cross-Channel Spatio-Spectral Clues
Existing learning-based hyperspectral reconstruction methods show limitations in fully exploiting the information among the hyperspectral bands.
CF-NeRF: Camera Parameter Free Neural Radiance Fields with Incremental Learning
Neural Radiance Fields (NeRF) have demonstrated impressive performance in novel view synthesis.
Prospective Role of Foundation Models in Advancing Autonomous Vehicles
With the development of artificial intelligence and breakthroughs in deep learning, large-scale Foundation Models (FMs), such as GPT, Sora, etc., have achieved remarkable results in many fields including natural language processing and computer vision.
Distributed Speech Dereverberation Using Weighted Prediction Error
However, in scenarios where microphone nodes are dispersed, the centralized approach of the WPE method requires aggregating all observations for inverse filtering, resulting in a significant computational burden.
Cross-View Graph Consistency Learning for Invariant Graph Representations
In this paper, we propose a cross-view graph consistency learning (CGCL) method that learns invariant graph representations for link prediction.
Robust Control of Unknown Switched Linear Systems from Noisy Data
This paper investigates the problem of data-driven stabilization for linear discrete-time switched systems with unknown switching dynamics.
Data-driven Control Against False Data Injection Attacks
To this end, a general FDI attack model is presented, which imposes minimally constraints on the switching frequency of attack channels and the magnitude of attack matrices.
Explain-then-Translate: An Analysis on Improving Program Translation with Self-generated Explanations
This work explores the use of self-generated natural language explanations as an intermediate step for code-to-code translation with language models.
Generative Face Video Coding Techniques and Standardization Efforts: A Review
Generative Face Video Coding (GFVC) techniques can exploit the compact representation of facial priors and the strong inference capability of deep generative models, achieving high-quality face video communication in ultra-low bandwidth scenarios.
Self-triggered Consensus Control of Multi-agent Systems from Data
In the presence of external disturbances, a model-based STC scheme is put forth for $\mathcal{H}_{\infty}$-consensus of MASs, serving as a baseline for the data-driven STC.
Changes-Aware Transformer: Learning Generalized Changes Representation
After refinement, the changed pixels in the difference feature space are closer to each other, which facilitates change detection.
Towards Real-World Burst Image Super-Resolution: Benchmark and Method
Despite substantial advances, single-image super-resolution (SISR) is always in a dilemma to reconstruct high-quality images with limited information from one input image, especially in realistic scenarios.
Monotone Tree-Based GAMI Models by Adapting XGBoost
It is straightforward to fit a monotone model to $f(x)$ using the options in XGBoost.
Hierarchical Grammar-Induced Geometry for Data-Efficient Molecular Property Prediction
Still, these techniques are faced with a common challenge in practice: Labeled data are limited by the cost of manual extraction from literature and laborious experimentation.
Improving Mandarin Prosodic Structure Prediction with Multi-level Contextual Information
For text-to-speech (TTS) synthesis, prosodic structure prediction (PSP) plays an important role in producing natural and intelligible speech.
Learning to Distill Global Representation for Sparse-View CT
The reconstructed images, however, suffer from strong artifacts, greatly limiting their diagnostic value.
Explicifying Neural Implicit Fields for Efficient Dynamic Human Avatar Modeling via a Neural Explicit Surface
This paper proposes a technique for efficiently modeling dynamic humans by explicifying the implicit neural fields via a Neural Explicit Surface (NES).
Cooperative Colorization: Exploring Latent Cross-Domain Priors for NIR Image Spectrum Translation
To address these challenges, we propose a cooperative learning paradigm that colorizes NIR images in parallel with another proxy grayscale colorization task by exploring latent cross-domain priors (i. e., latent spectrum context priors and task domain priors), dubbed CoColor.
Ranked #2 on
Image Colorization
on NIR2RGB VCIP Challange Dataset
Data-driven Polytopic Output Synchronization of Heterogeneous Multi-agent Systems from Noisy Data
This method utilizes measured data and a noise-matrix polytope to ensure near-optimal output synchronization.
Unsupervised Hyperspectral and Multispectral Images Fusion Based on the Cycle Consistency
In this paper, we propose an unsupervised HSI and MSI fusion model based on the cycle consistency, called CycFusion.
Hyperspectral and Multispectral Image Fusion Using the Conditional Denoising Diffusion Probabilistic Model
Specifically, the DDPM-Fus contains the forward diffusion process which gradually adds Gaussian noise to the high spatial resolution HSI (HrHSI) and another reverse denoising process which learns to predict the desired HrHSI from its noisy version conditioning on the corresponding high spatial resolution MSI (HrMSI) and low spatial resolution HSI (LrHSI).
Real-time Workload Pattern Analysis for Large-scale Cloud Databases
This has led to the increasing volume of database workloads, which provides the opportunity for pattern analysis.
AE-RED: A Hyperspectral Unmixing Framework Powered by Deep Autoencoder and Regularization by Denoising
In this way, both the characteristics of the deep autoencoder based unmixing methods and priors provided by denoisers are merged into our well-designed framework to enhance the unmixing performance.
Guided Deep Generative Model-based Spatial Regularization for Multiband Imaging Inverse Problems
More precisely, the regularization is conceived as a deep generative network able to encode spatial semantic features contained in this auxiliary image of high spatial resolution.
WiCo: Win-win Cooperation of Bottom-up and Top-down Referring Image Segmentation
Bottom-up methods are mainly perturbed by Inferior Positive (IP) errors due to the lack of prior object information.
A Gromov--Wasserstein Geometric View of Spectrum-Preserving Graph Coarsening
The study includes a set of experiments to support the theory and method, including approximating the GW distance, preserving the graph spectrum, classifying graphs using spectral information, and performing regression using graph convolutional networks.
Federated Learning of Models Pre-Trained on Different Features with Consensus Graphs
Second, we need to learn a consensus graph that captures the high-order interactions between local feature spaces and how to combine them to achieve a better prediction.
Out-of-Distributed Semantic Pruning for Robust Semi-Supervised Learning
We argue that an overlooked problem of robust SSL is its corrupted information on semantic level, practically limiting the development of the field.
GC-Flow: A Graph-Based Flow Network for Effective Clustering
Graph convolutional networks (GCNs) are \emph{discriminative models} that directly model the class posterior $p(y|\mathbf{x})$ for semi-supervised classification of graph data.
Interpretable Machine Learning based on Functional ANOVA Framework: Algorithms and Comparisons
To understand and explain the model results, one had to rely on post hoc explainability techniques, which are known to have limitations.
Text-Video Retrieval with Disentangled Conceptualization and Set-to-Set Alignment
In this paper, we propose the Disentangled Conceptualization and Set-to-set Alignment (DiCoSA) to simulate the conceptualizing and reasoning process of human beings.
Coordinated Transformer with Position \& Sample-aware Central Loss for Anatomical Landmark Detection
Heatmap-based anatomical landmark detection is still facing two unresolved challenges: 1) inability to accurately evaluate the distribution of heatmap; 2) inability to effectively exploit global spatial structure information.
TG-VQA: Ternary Game of Video Question Answering
Video question answering aims at answering a question about the video content by reasoning the alignment semantics within them.
Multi-view MERA Subspace Clustering
Benefiting from multiple interactions among orthogonal/semi-orthogonal (low-rank) factors, the low-rank MERA has a strong representation power to capture the complex inter/intra-view information in the self-representation tensor.
Long-lead forecasts of wintertime air stagnation index in southern China using oceanic memory effects
Stagnant weather condition is one of the major contributors to air pollution as it is favorable for the formation and accumulation of pollutants.
CoMoSpeech: One-Step Speech and Singing Voice Synthesis via Consistency Model
In this paper, we propose a "Co"nsistency "Mo"del-based "Speech" synthesis method, CoMoSpeech, which achieve speech synthesis through a single diffusion sampling step while achieving high audio quality.
Flexible Job Shop Scheduling via Dual Attention Network Based Reinforcement Learning
The complex relationships between operations and machines are represented precisely and concisely, for which a dual-attention network (DAN) comprising several interconnected operation message attention blocks and machine message attention blocks is proposed.
Communication-Efficient Graph Neural Networks with Probabilistic Neighborhood Expansion Analysis and Caching
To significantly reduce the communication volume without compromising prediction accuracy, we propose a policy for caching data associated with frequently accessed vertices in remote partitions.
Learning Robust Data-based LQG Controllers from Noisy Data
In this work, a data-based formulation for computing the steady-state Kalman gain is proposed based on semi-definite programming (SDP) using some noise-free input-state-output data.
Dynamic Video Frame Interpolation with integrated Difficulty Pre-Assessment
Extensive experiments show that easy samples pass through fast models while difficult samples inference with heavy models, and our proposed pipeline can improve the accuracy-efficiency trade-off for VFI.
Deep Multiview Clustering by Contrasting Cluster Assignments
Then, a cluster-level CVCL strategy is presented to explore consistent semantic label information among the multiple views in the fine-tuning stage.
DETRs Beat YOLOs on Real-time Object Detection
Our RT-DETR-R50 / R101 achieves 53. 1% / 54. 3% AP on COCO and 108 / 74 FPS on T4 GPU, outperforming previously advanced YOLOs in both speed and accuracy.
Ranked #9 on
Real-Time Object Detection
on MS COCO
Experts' cognition-driven safe noisy labels learning for precise segmentation of residual tumor in breast cancer
Precise segmentation of residual tumor in breast cancer (PSRTBC) after neoadjuvant chemotherapy is a fundamental key technique in the treatment process of breast cancer.
Video-Text as Game Players: Hierarchical Banzhaf Interaction for Cross-Modal Representation Learning
Contrastive learning-based video-language representation learning approaches, e. g., CLIP, have achieved outstanding performance, which pursue semantic interaction upon pre-defined video-text pairs.
Ranked #8 on
Video Question Answering
on MSRVTT-QA
Multi-granularity Interaction Simulation for Unsupervised Interactive Segmentation
Interactive segmentation enables users to segment as needed by providing cues of objects, which introduces human-computer interaction for many fields, such as image editing and medical image analysis.
DiffusionRet: Generative Text-Video Retrieval with Diffusion Model
Existing text-video retrieval solutions are, in essence, discriminant models focused on maximizing the conditional likelihood, i. e., p(candidates|query).
Ranked #15 on
Video Retrieval
on MSVD
GLASU: A Communication-Efficient Algorithm for Federated Learning with Vertically Distributed Graph Data
In this paper, we propose a model splitting method that splits a backbone GNN across the clients and the server and a communication-efficient algorithm, GLASU, to train such a model.
Nonlinear Hyperspectral Unmixing based on Multilinear Mixing Model using Convolutional Autoencoders
Current deep learning-based nonlinear unmixing focuses on the models in additive, bilinear-based formulations.
Parallel Vertex Diffusion for Unified Visual Grounding
An intuitive materialization of our paradigm is Parallel Vertex Diffusion (PVD) to directly set vertex coordinates as the generation target and use a diffusion model to train and infer.
Mastering Strategy Card Game (Hearthstone) with Improved Techniques
Strategy card game is a well-known genre that is demanding on the intelligent game-play and can be an ideal test-bench for AI.
Mastering Strategy Card Game (Legends of Code and Magic) via End-to-End Policy and Optimistic Smooth Fictitious Play
Deep Reinforcement Learning combined with Fictitious Play shows impressive results on many benchmark games, most of which are, however, single-stage.
A Coarse to Fine Framework for Object Detection in High Resolution Image
In this paper, we introduce a simple yet efficient approach that improves accuracy of object detection especially for small objects and large scale variance scene while reducing the computational cost in high resolution image.
Self-triggered Resilient Stabilization of Linear Systems with Quantized Output
If, in addition, the transmission protocols at the controller-to-actuator (C-A) and sensor-to-controller (S-C) channels can be adapted, the self-triggered control architecture can be considerably simplified, leveraging a delicate observer-based deadbeat controller to eliminate the need for running the controller in parallel at the encoder side.
Graph Neural Network-Inspired Kernels for Gaussian Processes in Semi-Supervised Learning
Gaussian processes (GPs) are an attractive class of machine learning models because of their simplicity and flexibility as building blocks of more complex Bayesian models.
GUAP: Graph Universal Attack Through Adversarial Patching
Graph neural networks (GNNs) are a class of effective deep learning models for node classification tasks; yet their predictive capability may be severely compromised under adversarially designed unnoticeable perturbations to the graph structure and/or node data.
High-Frequency Stereo Matching Network
In the field of binocular stereo matching, remarkable progress has been made by iterative methods like RAFT-Stereo and CREStereo.
The Devil is in the Crack Orientation: A New Perspective for Crack Detection
However, the vanilla adaptation of the existing oriented object detection methods to the crack detection tasks will result in limited performance, due to the boundary discontinuity issue and the ambiguities in sub-crack orientation.
TopoSeg: Topology-Aware Nuclear Instance Segmentation
Experiments on three nuclear instance segmentation datasets justify the superiority of TopoSeg, which achieves state-of-the-art performance.
LaPE: Layer-adaptive Position Embedding for Vision Transformers with Independent Layer Normalization
A typical way to introduce position information is adding the absolute Position Embedding (PE) to patch embedding before entering VTs.
Position Embedding Needs an Independent Layer Normalization
By analyzing the input and output of each encoder layer in VTs using reparameterization and visualization, we find that the default PE joining method (simply adding the PE and patch embedding together) operates the same affine transformation to token embedding and PE, which limits the expressiveness of PE and hence constrains the performance of VTs.
Tuning-free Plug-and-Play Hyperspectral Image Deconvolution with Deep Priors
Deconvolution is a widely used strategy to mitigate the blurring and noisy degradation of hyperspectral images~(HSI) generated by the acquisition devices.
Learnable Blur Kernel for Single-Image Defocus Deblurring in the Wild
The proposed method consists of a learnable blur kernel to estimate the defocus map, which is an unsupervised method, and a single-image defocus deblurring generative adversarial network (DefocusGAN) for the first time.
Out-of-Candidate Rectification for Weakly Supervised Semantic Segmentation
Weakly supervised semantic segmentation is typically inspired by class activation maps, which serve as pseudo masks with class-discriminative regions highlighted.
Optical Character Recognition (OCR)
Weakly supervised Semantic Segmentation
+1
From Node Interaction to Hop Interaction: New Effective and Scalable Graph Learning Paradigm
We design a simple yet effective HopGNN framework that can easily utilize existing GNNs to achieve hop interaction.
Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations
Most video-and-language representation learning approaches employ contrastive learning, e. g., CLIP, to project the video and text features into a common latent space according to the semantic similarities of text-video pairs.
Ranked #2 on
Video Retrieval
on LSMDC
(text-to-video Mean Rank metric)
Dual Complementary Dynamic Convolution for Image Recognition
As a powerful engine, vanilla convolution has promoted huge breakthroughs in various computer tasks.
Robust Manifold Nonnegative Tucker Factorization for Tensor Data Representation
Nonnegative Tucker Factorization (NTF) minimizes the euclidean distance or Kullback-Leibler divergence between the original data and its low-rank approximation which often suffers from grossly corruptions or outliers and the neglect of manifold structures of data.
A Unified Pyramid Recurrent Network for Video Frame Interpolation
Cast in a flexible pyramid framework, UPR-Net exploits lightweight recurrent modules for both bi-directional flow estimation and intermediate frame synthesis.
Ranked #2 on
Video Frame Interpolation
on MSU Video Frame Interpolation
(PSNR metric)
SA-MLP: Distilling Graph Knowledge from GNNs into Structure-Aware MLP
Then, we introduce a novel structure-mixing knowledge distillation strategy to enhance the learning ability of MLPs for structure information.
Fuzzy Positive Learning for Semi-supervised Semantic Segmentation
Semi-supervised learning (SSL) essentially pursues class boundary exploration with less dependence on human annotations.
ACSeg: Adaptive Conceptualization for Unsupervised Semantic Segmentation
Recently, self-supervised large-scale visual pre-training models have shown great promise in representing pixel-level semantic relationships, significantly promoting the development of unsupervised dense prediction tasks, e. g., unsupervised semantic segmentation (USS).
Flexible Alignment Super-Resolution Network for Multi-Contrast MRI
To tackle this problem, we propose the Flexible Alignment Super-Resolution Network (FASR-Net) for multi-contrast MRI Super-Resolution.
Toward 3D Spatial Reasoning for Human-like Text-based Visual Question Answering
Under this setting, these 2D spatial reasoning approaches cannot distinguish the fine-grain spatial relations between visual objects and scene texts on the same image plane, thereby impairing the interpretability and performance of TextVQA models.
Deep Hyperspectral and Multispectral Image Fusion with Inter-image Variability
The fusion problem is stated as an optimization problem in the maximum a posteriori framework.
Data-Driven Control of Distributed Event-Triggered Network Systems
The present paper deals with data-driven event-triggered control of a class of unknown discrete-time interconnected systems (a. k. a.
Audio Deepfake Attribution: An Initial Dataset and Investigation
To address the challenges of attribution of continuously emerging unknown audio generation tools in the real world, we propose the Class-Representation Multi-Center Learning (CRML) method for open-set audio deepfake attribution (OSADA).
Pathway to Future Symbiotic Creativity
This report presents a comprehensive view of our vision on the development path of the human-machine symbiotic art creation.
Unsupervised domain adaptation semantic segmentation of high-resolution remote sensing imagery with invariant domain-level prototype memory
This study proposes a novel unsupervised domain adaptation semantic segmentation network (MemoryAdaptNet) for the semantic segmentation of HRS imagery.
OpenMedIA: Open-Source Medical Image Analysis Toolbox and Benchmark under Heterogeneous AI Computing Platforms
In this paper, we present OpenMedIA, an open-source toolbox library containing a rich set of deep learning methods for medical image analysis under heterogeneous Artificial Intelligence (AI) computing platforms.
Neural Optimization Machine: A Neural Network Approach for Optimization
The NN objective function can have arbitrary architectures and activation functions.
Event-triggered Consensus Control of Heterogeneous Multi-agent Systems: Model- and Data-based Analysis
This article deals with model- and data-based consensus control of heterogenous leader-following multi-agent systems (MASs) under an event-triggering transmission scheme.
Locality Guidance for Improving Vision Transformers on Tiny Datasets
Therefore, our locality guidance approach is very simple and efficient, and can serve as a basic performance enhancement method for VTs on tiny datasets.
NDF: Neural Deformable Fields for Dynamic Human Modelling
However, the learned canonical representation is static and the current design of the deformation fields is not able to represent large movements or detailed geometry changes.
Data-driven Self-triggered Control via Trajectory Prediction
Self-triggered control, a well-documented technique for reducing the communication overhead while ensuring desired system performance, is gaining increasing popularity.
A Survey of Decision Making in Adversarial Games
Game theory has by now found numerous applications in various fields, including economics, industry, jurisprudence, and artificial intelligence, where each player only cares about its own interest in a noncooperative or cooperative manner, but without obvious malice to other players.
A Dual-Masked Auto-Encoder for Robust Motion Capture with Spatial-Temporal Skeletal Token Completion
In order to demonstrate the proposed model's capability in dealing with severe data loss scenarios, we contribute a high-accuracy and challenging motion capture dataset of multi-person interactions with severe occlusion.
Using Model-Based Trees with Boosting to Fit Low-Order Functional ANOVA Models
We propose a new algorithm, called GAMI-Tree, that is similar to EBM, but has a number of features that lead to better performance.
Adaptive Random Fourier Features Kernel LMS
We propose the adaptive random Fourier features Gaussian kernel LMS (ARFF-GKLMS).
Shapley Computations Using Surrogate Model-Based Trees
Shapley-related techniques have gained attention as both global and local interpretation tools because of their desirable properties.
$L_2$BN: Enhancing Batch Normalization by Equalizing the $L_2$ Norms of Features
In this paper, we analyze batch normalization from the perspective of discriminability and find the disadvantages ignored by previous studies: the difference in $l_2$ norms of sample features can hinder batch normalization from obtaining more distinguished inter-class features and more compact intra-class features.
Bridging Mean-Field Games and Normalizing Flows with Trajectory Regularization
In this work, we unravel the connections between MFGs and NFs by contextualizing the training of an NF as solving the MFG.
PSP: Million-level Protein Sequence Dataset for Protein Structure Prediction
We provide in addition the benchmark training procedure for SOTA protein structure prediction model on this dataset.
Enhanced Bi-directional Motion Estimation for Video Frame Interpolation
We present a novel simple yet effective algorithm for motion-based video frame interpolation.
Ranked #3 on
Video Frame Interpolation
on MSU Video Frame Interpolation
(LPIPS metric)
Integration of Physics-Based and Data-Driven Models for Hyperspectral Image Unmixing
Spectral unmixing is one of the most important quantitative analysis tasks in hyperspectral data processing.
Universal Deep GNNs: Rethinking Residual Connection in GNNs from a Path Decomposition Perspective for Preventing the Over-smoothing
The performance of GNNs degrades as they become deeper due to the over-smoothing.
Ranked #10 on
Node Classification
on Squirrel
Interpretable Feature Engineering for Time Series Predictors using Attention Networks
Regression problems with time-series predictors are common in banking and many other areas of application.
Joint learning of object graph and relation graph for visual question answering
Modeling visual question answering(VQA) through scene graphs can significantly improve the reasoning accuracy and interpretability.
Performance and Interpretability Comparisons of Supervised Machine Learning Algorithms: An Empirical Study
Overall, XGB and FFNNs were competitive, with FFNNs showing better performance in smooth models and tree-based boosting algorithms performing better in non-smooth models.
Explaining Adverse Actions in Credit Decisions Using Shapley Decomposition
The applicant is then entitled to an explanation for the negative decision.
ViSTA: Vision and Scene Text Aggregation for Cross-Modal Retrieval
Visual appearance is considered to be the most important cue to understand images for cross-modal retrieval, while sometimes the scene text appearing in images can provide valuable information to understand the visual semantics.
Ranked #10 on
Cross-Modal Retrieval
on Flickr30k
(using extra training data)
Training-free Transformer Architecture Search
Recently, Vision Transformer (ViT) has achieved remarkable success in several computer vision tasks.
Exploiting Neighbor Effect: Conv-Agnostic GNNs Framework for Graphs with Heterophily
Moreover, we propose a simple yet effective Conv-Agnostic GNN framework (CAGNNs) to enhance the performance of most GNNs on heterophily datasets by learning the neighbor effect for each node.
Data-Efficient Graph Grammar Learning for Molecular Generation
This is a non-trivial task for neural network-based generative models since the relevant chemical knowledge can only be extracted and generalized from the limited training data.
Prediction of Depression Severity Based on the Prosodic and Semantic Features with Bidirectional LSTM and Time Distributed CNN
For the text modality, we use global vectors for word representation (GloVe) to perform word embeddings and the embeddings are fed into the Bi-LSTM network.
Active Learning for Point Cloud Semantic Segmentation via Spatial-Structural Diversity Reasoning
To deploy SSDR-AL in a more practical scenario, we design a noise-aware iterative labeling strategy to confront the "noisy annotation" problem introduced by the previous "dominant labeling" strategy in superpoints.
Model-Based and Data-Driven Control of Event- and Self-Triggered Discrete-Time LTI Systems
To this end, we begin by presenting a dynamic event-triggering scheme (ETS) based on periodic sampling, and a discrete-time looped-functional approach, through which a model-based stability condition is derived.
Graph-Augmented Normalizing Flows for Anomaly Detection of Multiple Time Series
Anomaly detection is a widely studied task for a broad variety of data types; among them, multiple time series appear frequently in applications, including for example, power grids and traffic networks.
Ranked #3 on
Anomaly Detection
on voraus-AD
Time-Frequency Mask Aware Bi-directional LSTM: A Deep Learning Approach for Underwater Acoustic Signal Separation
In particular, this method breaks through the limitations of the existing methods, not only achieves good results in multivariate separation, but also effectively separates signals when mixed with 40dB Gaussian noise signals.
Attacking c-MARL More Effectively: A Data Driven Approach
In recent years, a proliferation of methods were developed for cooperative multi-agent reinforcement learning (c-MARL).
Memory-based Message Passing: Decoupling the Message for Propogation from Discrimination
Based on the homophily assumption, the current message passing always aggregates features of connected nodes, such as the graph Laplacian smoothing process.
Hyperspectral Image Super-resolution with Deep Priors and Degradation Model Inversion
To overcome inherent hardware limitations of hyperspectral imaging systems with respect to their spatial resolution, fusion-based hyperspectral image (HSI) super-resolution is attracting increasing attention.
Geometry-Aware Guided Loss for Deep Crack Recognition
Despite the substantial progress of deep models for crack recognition, due to the inconsistent cracks in varying sizes, shapes, and noisy background textures, there still lacks the discriminative power of the deeply learned features when supervised by the cross-entropy loss.
Robust Recommendation with Implicit Feedback via Eliminating the Effects of Unexpected Behaviors
In this paper, we propose a Multi-Preferences Model (MPM) to eliminate the effects of unexpected behaviors.
Mean-Square Stability and Stabilizability Analyses of LTI Systems Under Spatially Correlated Multiplicative Perturbations
In this paper, we investigate the mean-square stability and stabilizability problems for linear time-invariant systems under stochastic spatially correlated multiplicative uncertainties.
Distributed Policy Gradient with Variance Reduction in Multi-Agent Reinforcement Learning
This paper studies a distributed policy gradient in collaborative multi-agent reinforcement learning (MARL), where agents over a communication network aim to find the optimal policy to maximize the average of all agents' local returns.
Multi-agent Reinforcement Learning
reinforcement-learning
+2
Learning Representation for Clustering via Prototype Scattering and Positive Sampling
The strengths of ProPos are avoidable class collision issue, uniform representations, well-separated clusters, and within-cluster compactness.
Ranked #4 on
Image Clustering
on ImageNet-10
Traversing the Local Polytopes of ReLU Neural Networks
Our polytope traversing algorithm can be adapted to a wide range of applications related to robustness and interpretability.
Temporal-MPI: Enabling Multi-Plane Images for Dynamic Scene Modelling via Temporal Basis Learning
One of the seminal image-based rendering method, the multi-plane image (MPI), produces high novel-view synthesis quality for static scenes.
Traversing the Local Polytopes of ReLU Neural Networks: A Unified Approach for Network Verification
Although neural networks (NNs) with ReLU activation functions have found success in a wide range of applications, their adoption in risk-sensitive settings has been limited by the concerns on robustness and interpretability.
