Search Results for author:
Found 85 papers, 29 papers with code
VAGeo: View-specific Attention for Cross-View Object Geo-Localization
In object-level, according to the characteristics of different viewpoints of ground and drone query images, viewpoint-specific positional codings are designed to more accurately identify the click-point object of the query image in the VSPE module.
Event-based Video Person Re-identification via Cross-Modality and Temporal Collaboration
To make full use of the information in the event stream, we propose a Cross-Modality and Temporal Collaboration (CMTC) network for event-based video person ReID.
Toward Scalable Multirobot Control: Fast Policy Learning in Distributed MPC
The control policies are successively updated in a receding-horizon manner, enabling fast and efficient policy learning with the closed-loop stability guarantee.
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
Acceleration for Deep Reinforcement Learning using Parallel and Distributed Computing: A Survey
Deep reinforcement learning has led to dramatic breakthroughs in the field of artificial intelligence for the past few years.
Exploring Differences between Human Perception and Model Inference in Audio Event Recognition
By comparing human annotations with the predictions of ensemble pre-trained models, this paper uncovers a significant gap between human perception and model inference in both semantic identification and existence detection of audio events.
Findings of the 2024 Mandarin Stuttering Event Detection and Automatic Speech Recognition Challenge
The StutteringSpeech Challenge focuses on advancing speech technologies for people who stutter, specifically targeting Stuttering Event Detection (SED) and Automatic Speech Recognition (ASR) in Mandarin.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Benchmarking Chinese Knowledge Rectification in Large Language Models
While Large Language Models (LLMs) exhibit remarkable generative capabilities, they are not without flaws, particularly in the form of hallucinations.
A Survey of Mamba
In this survey, we therefore conduct an in-depth investigation of recent Mamba-associated studies, covering three main aspects: the advancements of Mamba-based models, the techniques of adapting Mamba to diverse data, and the applications where Mamba can excel.
Multiple Instance Verification
We explore multiple-instance verification, a problem setting where a query instance is verified against a bag of target instances with heterogeneous, unknown relevancy.
Similarity Distance-Based Label Assignment for Tiny Object Detection
Although there are some effective label assignment strategies for tiny objects, most of them focus on reducing the sensitivity to the bounding boxes to increase the number of positive samples and have some fixed hyperparameters need to set.
Overview of the CAIL 2023 Argument Mining Track
We give a detailed overview of the CAIL 2023 Argument Mining Track, one of the Chinese AI and Law Challenge (CAIL) 2023 tracks.
AS-70: A Mandarin stuttered speech dataset for automatic speech recognition and stuttering event detection
The rapid advancements in speech technologies over the past two decades have led to human-level performance in tasks like automatic speech recognition (ASR) for fluent speech.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
SRC-Net: Bi-Temporal Spatial Relationship Concerned Network for Change Detection
The bi-temporal spatial relationships between features at the same location at different times play a key role in this process.
Building change detection for remote sensing images
Change Detection
Adaptive Advantage-Guided Policy Regularization for Offline Reinforcement Learning
Empirically, we conduct a series of experiments on the D4RL benchmark, where A2PR demonstrates state-of-the-art performance.
Can LLMs Solve longer Math Word Problems Better?
This study pioneers the exploration of Context Length Generalizability (CoLeG), the ability of LLMs to solve long MWPs.
DTCM: Deep Transformer Capsule Mutual Distillation for Multivariate Time Series Classification
This article proposes a dual-network-based feature extractor, perceptive capsule network (PCapN), for multivariate time series classification (MTSC), including a local feature network (LFN) and a global relation network (GRN).
Linear-Time Graph Neural Networks for Scalable Recommendations
In this paper, we propose a Linear-Time Graph Neural Network (LTGNN) to scale up GNN-based recommender systems to achieve comparable scalability as classic MF approaches while maintaining GNNs' powerful expressiveness for superior prediction accuracy.
Can We Verify Step by Step for Incorrect Answer Detection?
Chain-of-Thought (CoT) prompting has marked a significant advancement in enhancing the reasoning capabilities of large language models (LLMs).
In-context Learning with Retrieved Demonstrations for Language Models: A Survey
Language models, especially pre-trained large language models, have showcased remarkable abilities as few-shot in-context learners (ICL), adept at adapting to new tasks with just a few demonstrations in the input context.
ICMC-ASR: The ICASSP 2024 In-Car Multi-Channel Automatic Speech Recognition Challenge
To promote speech processing and recognition research in driving scenarios, we build on the success of the Intelligent Cockpit Speech Recognition Challenge (ICSRC) held at ISCSLP 2022 and launch the ICASSP 2024 In-Car Multi-Channel Automatic Speech Recognition (ICMC-ASR) Challenge.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
A Comprehensive Study of Knowledge Editing for Large Language Models
In this paper, we first define the knowledge editing problem and then provide a comprehensive review of cutting-edge approaches.
Ranked #1 on
knowledge editing
on zsRE
(using extra training data)
Enhancing Optimization Through Innovation: The Multi-Strategy Improved Black Widow Optimization Algorithm (MSBWOA)
This paper introduces a Multi-Strategy Improved Black Widow Optimization Algorithm (MSBWOA), designed to enhance the performance of the standard Black Widow Algorithm (BW) in solving complex optimization problems.
EPNet: An Efficient Pyramid Network for Enhanced Single-Image Super-Resolution with Reduced Computational Requirements
Single-image super-resolution (SISR) has seen significant advancements through the integration of deep learning.
Continual Learning through Networks Splitting and Merging with Dreaming-Meta-Weighted Model Fusion
Differently, we propose a continual learning method named Split2MetaFusion which can achieve better trade-off by employing a two-stage strategy: splitting and meta-weighted fusion.
Density-Guided Dense Pseudo Label Selection For Semi-supervised Oriented Object Detection
Therefore, we propose Density-Guided Dense Pseudo Label Selection (DDPLS) for semi-supervised oriented object detection.
Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology View
This paper probes the collaboration mechanisms among contemporary NLP systems by melding practical experiments with theoretical insights.
TaskLAMA: Probing the Complex Task Understanding of Language Models
Our experiments reveal that LLMs are able to decompose complex tasks into individual steps effectively, with a relative improvement of 15% to 280% over the best baseline.
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.
Learning to Branch in Combinatorial Optimization with Graph Pointer Networks
The proposed model, which combines the graph neural network and the pointer mechanism, can effectively map from the solver state to the branching variable decisions.
MuseCoco: Generating Symbolic Music from Text
In contrast, symbolic music offers ease of editing, making it more accessible for users to manipulate specific musical elements.
Learning Task-preferred Inference Routes for Gradient De-conflict in Multi-output DNNs
By designing the learnable task-specific importance variables, DR-MGF evaluates the importance of filters for different tasks.
Dr.ICL: Demonstration-Retrieved In-context Learning
In-context learning (ICL), teaching a large language model (LLM) to perform a task with few-shot demonstrations rather than adjusting the model parameters, has emerged as a strong paradigm for using LLMs.
StereoVAE: A lightweight stereo matching system through embedded GPUs
We present a lightweight system for stereo matching through embedded GPUs.
Schema-adaptable Knowledge Graph Construction
This necessitates a system that can handle evolving schema automatically to extract information for KGC.
Prokaryotic genome editing based on the subtype I-B-Svi CRISPR-Cas system
Type I CRISPR-Cas systems are the most common among six types of CRISPR-Cas systems, however, non-self-targeting genome editing based on a single Cas3 of type I CRISPR-Cas systems has not been reported.
How to Unleash the Power of Large Language Models for Few-shot Relation Extraction?
Scaling language models have revolutionized widespread NLP tasks, yet little comprehensively explored few-shot relation extraction with large language models.
RSFNet: A White-Box Image Retouching Approach using Region-Specific Color Filters
Therefore, there is a need for white-box approaches that produce satisfying results and enable users to conveniently edit their images simultaneously.
Ranked #3 on
Image Enhancement
on MIT-Adobe 5k
(PSNR on proRGB metric)
Neural Koopman Pooling: Control-Inspired Temporal Dynamics Encoding for Skeleton-Based Action Recognition
Besides, we also show that our Koopman pooling framework can be easily extended to one-shot action recognition when combined with Dynamic Mode Decomposition.
MasQCLIP for Open-Vocabulary Universal Image Segmentation
We present a new method for open-vocabulary universal image segmentation, which is capable of performing instance, semantic, and panoptic segmentation under a unified framework.
Ranked #1 on
Panoptic Segmentation
on ADE20K
LAMBADA: Backward Chaining for Automated Reasoning in Natural Language
Remarkable progress has been made on automated reasoning with natural text, by using Language Models (LMs) and methods such as Chain-of-Thought and Selection-Inference.
Towards Realistic Low-resource Relation Extraction: A Benchmark with Empirical Baseline Study
This paper presents an empirical study to build relation extraction systems in low-resource settings.
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
Deep Learning for Visual Speech Analysis: A Survey
Visual speech, referring to the visual domain of speech, has attracted increasing attention due to its wide applications, such as public security, medical treatment, military defense, and film entertainment.
Scientific and Technological Information Oriented Semantics-adversarial and Media-adversarial Cross-media Retrieval
In light of this, we propose a scientific and technological information oriented Semantics-adversarial and Media-adversarial Cross-media Retrieval method (SMCR) to find an effective common subspace.
RDP-Net: Region Detail Preserving Network for Change Detection
Moreover, current CNN models are heavy in parameters, which prevents their deployment on edge devices such as UAVs.
Change Detection
Change detection for remote sensing images
+1
DeepKE: A Deep Learning Based Knowledge Extraction Toolkit for Knowledge Base Population
We present an open-source and extensible knowledge extraction toolkit DeepKE, supporting complicated low-resource, document-level and multimodal scenarios in the knowledge base population.
Model-Based Safe Reinforcement Learning with Time-Varying State and Control Constraints: An Application to Intelligent Vehicles
Also, few works have addressed the safe RL algorithm design under time-varying safety constraints.
WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognition
In this paper, we present WenetSpeech, a multi-domain Mandarin corpus consisting of 10000+ hours high-quality labeled speech, 2400+ hours weakly labeled speech, and about 10000 hours unlabeled speech, with 22400+ hours in total.
Ranked #6 on
Speech Recognition
on WenetSpeech
Learning Practically Feasible Policies for Online 3D Bin Packing
In this problem, the items are delivered to the agent without informing the full sequence information.
Robust Tube-based Model Predictive Control with Koopman Operators--Extended Version
The finite data-driven approximation of Koopman operators results in a class of linear predictors, useful for formulating linear model predictive control (MPC) of nonlinear dynamical systems with reduced computational complexity.
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.
Weakly-supervised 3D Human Pose Estimation with Cross-view U-shaped Graph Convolutional Network
Instead, exploiting multi-view information is a practical way to achieve absolute 3D human pose estimation.
Monocular 3D Human Pose Estimation
Weakly-supervised 3D Human Pose Estimation
+1
A LiDAR Assisted Control Module with High Precision in Parking Scenarios for Autonomous Driving Vehicle
For example, humans are good at interactive tasks (while autonomous driving systems usually do not), but we are often incompetent for tasks with strict precision demands.
Multi-objective Feature Selection with Missing Data in Classification
Databases with missing data are likely to be unreliable.
The Multi-speaker Multi-style Voice Cloning Challenge 2021
The challenge consists of two tracks, namely few-shot track and one-shot track, where the participants are required to clone multiple target voices with 100 and 5 samples respectively.
INTERSPEECH 2021 ConferencingSpeech Challenge: Towards Far-field Multi-Channel Speech Enhancement for Video Conferencing
The ConferencingSpeech 2021 challenge is proposed to stimulate research on far-field multi-channel speech enhancement for video conferencing.
CKNet: A Convolutional Neural Network Based on Koopman Operator for Modeling Latent Dynamics from Pixels
In this paper, a novel Koopman-based deep convolutional network, called CKNet, is proposed to identify latent dynamics from raw pixels.
StablePose: Learning 6D Object Poses from Geometrically Stable Patches
According to the theory of geometric stability analysis, a minimal set of three planar/cylindrical patches are geometrically stable and determine the full 6DoFs of the object pose.
Galaxy Clusters from the DESI Legacy Imaging Surveys. I. Cluster Detection
Based on the photometric redshift catalog of Zou H. et al. (2019), we apply a fast clustering algorithm to identify 540, 432 galaxy clusters at $z\lesssim1$ in the DESI legacy imaging surveys, which cover a sky area of about 20, 000 deg$^2$.
Astrophysics of Galaxies Cosmology and Nongalactic Astrophysics
Identifiability of Bifactor Models
The bifactor model and its extensions are multidimensional latent variable models, under which each item measures up to one subdimension on top of the primary dimension(s).
Statistics Theory Applications Statistics Theory
RTFN: A Robust Temporal Feature Network for Time Series Classification
Most of the existing feature networks pay more attention to local features rather than the relationships among them.
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.
Multi-View Spectral Clustering with High-Order Optimal Neighborhood Laplacian Matrix
Multi-view spectral clustering can effectively reveal the intrinsic cluster structure among data by performing clustering on the learned optimal embedding across views.
RTFN: Robust Temporal Feature Network
The temporal feature networks are built to extract basic features from input data while the attentional LSTM networks are devised to capture complicated shapelets and relationships to enrich features.
SymmetryNet: Learning to Predict Reflectional and Rotational Symmetries of 3D Shapes from Single-View RGB-D Images
We propose an end-to-end deep neural network which is able to predict both reflectional and rotational symmetries of 3D objects present in the input RGB-D image.
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.
Deep Neural Networks with Koopman Operators for Modeling and Control of Autonomous Vehicles
Furthermore, a data-driven model predictive controller with the learned Koopman model is designed for path tracking control of autonomous vehicles.
LSTM Networks for Music Generation
The paper presents a method of the music generation based on LSTM (Long Short-Term Memory), contrasts the effects of different network structures on the music generation and introduces other methods used by some researchers.
PointNet on FPGA for Real-Time LiDAR Point Cloud Processing
LiDAR sensors have been widely used in many autonomous vehicle modalities, such as perception, mapping, and localization.
Drosophila-Inspired 3D Moving Object Detection Based on Point Clouds
3D moving object detection is one of the most critical tasks in dynamic scene analysis.
Person Re-Identification via Active Hard Sample Mining
To alleviate such a problem, we present an active hard sample mining framework via training an effective re-ID model with the least labeling efforts.
Asymptotic proximal point methods: finding the global minima with linear convergence for a class of multiple minima problems
We propose and analyze asymptotic proximal point (APP) methods to find the global minimizer for a class of nonconvex, nonsmooth, or even discontinuous multiple minima functions.
Optimization and Control Numerical Analysis Numerical Analysis 65K05, 68Q25, 90C26, 90C56
Can speed up the convergence rate of stochastic gradient methods to $\mathcal{O}(1/k^2)$ by a gradient averaging strategy?
In this paper we consider the question of whether it is possible to apply a gradient averaging strategy to improve on the sublinear convergence rates without any increase in storage.
Stochastic gradient-free descents
In this paper we propose stochastic gradient-free methods and accelerated methods with momentum for solving stochastic optimization problems.
Robust Learning-based Predictive Control for Discrete-time Nonlinear Systems with Unknown Dynamics and State Constraints
Robust model predictive control (MPC) is a well-known control technique for model-based control with constraints and uncertainties.
Contraction methods for continuous optimization
Motivated by the grid search method and Bayesian optimization, we introduce the concept of contractibility and its applications in model-based optimization.
Optimization and Control Computational Complexity Numerical Analysis Numerical Analysis 65K05, 68Q15, 90C26, 90C56
A Dual-level Model Predictive Control Scheme for Multi-timescale Dynamical Systems--Extended Version
So far, many control algorithms have been developed for singularly perturbed systems.
Coordinated Path Following Control of Fixed-wing Unmanned Aerial Vehicles
At the coordination level, we prove that even with speed constraints, the proposed control law can make sure the path following errors reduce to zero, while the desired arc distances converge to the desired value.
BiRA-Net: Bilinear Attention Net for Diabetic Retinopathy Grading
Diabetic retinopathy (DR) is a common retinal disease that leads to blindness.
Sparse residual tree and forest
The hierarchical parallel SRT algorithm is based on both tree decomposition and adaptive radial basis function (RBF) explorations, whereby for each child a sparse and proper RBF refinement is added to the approximation by minimizing the norm of the residual inherited from its parent.
Baidu Apollo Auto-Calibration System - An Industry-Level Data-Driven and Learning based Vehicle Longitude Dynamic Calibrating Algorithm
Since manual calibration is not sustainable once entering into mass production stage for industrial purposes, we here introduce a machine-learning based auto-calibration system for autonomous driving vehicles.
Visual Saliency Based on Scale-Space Analysis in the Frequency Domain
First, we consider saliency detection as a frequency domain analysis problem.
Beyond Random Walk and Metropolis-Hastings Samplers: Why You Should Not Backtrack for Unbiased Graph Sampling
In this paper, we propose non-backtracking random walk with re-weighting (NBRW-rw) and MH algorithm with delayed acceptance (MHDA) which are theoretically guaranteed to achieve, at almost no additional cost, not only unbiased graph sampling but also higher efficiency (smaller asymptotic variance of the resulting unbiased estimators) than the SRW-rw and the MH algorithm, respectively.
Methodology Data Structures and Algorithms Networking and Internet Architecture Social and Information Networks Data Analysis, Statistics and Probability Physics and Society
