Search Results for author:
Found 78 papers, 20 papers with code
Learning a Rotation Invariant Detector with Rotatable Bounding Box
The existing methods are not robust to angle varies of the objects because of the use of traditional bounding box, which is a rotation variant structure for locating rotated objects.
EVA2.0: Investigating Open-Domain Chinese Dialogue Systems with Large-Scale Pre-Training
Large-scale pre-training has shown remarkable performance in building open-domain dialogue systems.
Prototype-based Cross-Modal Object Tracking
In particular, we design a multi-modal prototype to represent target information by multi-kind samples, including a fixed sample from the first frame and two representative samples from different modalities.
Cross-Modal Object Tracking via Modality-Aware Fusion Network and A Large-Scale Dataset
Visual tracking often faces challenges such as invalid targets and decreased performance in low-light conditions when relying solely on RGB image sequences.
Reinforcement Learning with Prior Policy Guidance for Motion Planning of Dual-Arm Free-Floating Space Robot
However, due to the increase in planning dimension and the intensification of system dynamics coupling, the motion planning of dual-arm free-floating space robots remains an open challenge.
RJUA-QA: A Comprehensive QA Dataset for Urology
We introduce RJUA-QA, a novel medical dataset for question answering (QA) and reasoning with clinical evidence, contributing to bridge the gap between general large language models (LLMs) and medical-specific LLM applications.
AugmentedCode: Examining the Effects of Natural Language Resources in Code Retrieval Models
Code retrieval is allowing software engineers to search codes through a natural language query, which relies on both natural language processing and software engineering techniques.
Attribute-Based Progressive Fusion Network for RGBT Tracking
RGBT tracking usually suffers from various challenging factors of fast motion, scale variation, illumination variation, thermal crossover and occlusion, to name a few.
Ranked #3 on
Rgb-T Tracking
on GTOT
Adaptive Confidence Multi-View Hashing for Multimedia Retrieval
Furthermore, an adaptive confidence multi-view network is employed to measure the confidence of each view and then fuse multi-view features through a weighted summation.
A Systematic Investigation of KB-Text Embedding Alignment at Scale
Knowledge bases (KBs) and text often contain complementary knowledge: KBs store structured knowledge that can support long range reasoning, while text stores more comprehensive and timely knowledge in an unstructured way.
BERT-Sort: A Zero-shot MLM Semantic Encoder on Ordinal Features for AutoML
One of the common data pre-processing operations implemented in AutoML systems is to encode categorical features as numerical features.
Ranked #1 on
AutoML
on OrdinalDataset
Optimal LED Spectral Multiplexing for NIR2RGB Translation
The industry practice for night video surveillance is to use auxiliary near-infrared (NIR) LED diodes, usually centered at 850nm or 940nm, for scene illumination.
Global Balanced Experts for Federated Long-Tailed Learning
In particular, a proxy is derived from the accumulated gradients uploaded by the clients after local training, and is shared by all clients as the class prior for re-balance training.
BadLabel: A Robust Perspective on Evaluating and Enhancing Label-noise Learning
To address the challenge posed by BadLabel, we further propose a robust LNL method that perturbs the labels in an adversarial manner at each epoch to make the loss values of clean and noisy labels again distinguishable.
Investigate the Essence of Long-Tailed Recognition from a Unified Perspective
Specifically, we demonstrate that long-tailed recognition suffers from both sample number and category similarity.
Graph Contrastive Topic Model
Based on it, we propose the graph contrastive topic model (GCTM), which conducts graph contrastive learning (GCL) using informative positive and negative samples that are generated by the graph-based sampling strategy leveraging in-depth correlation and irrelevance among documents and words.
Random Forests of Interaction Trees for Estimating Individualized Treatment Effects in Randomized Trials
Assessing heterogeneous treatment effects has become a growing interest in advancing precision medicine.
Hybrid Dirac Semimetal in CaAgBi Materials Family
Based on their formation mechanisms, Dirac points in three-dimensional systems can be classified as accidental or essential.
Materials Science
TreeGAN: Syntax-Aware Sequence Generation with Generative Adversarial Networks
To address these issues, we study the problem of syntax-aware sequence generation with GANs, in which a collection of real sequences and a set of pre-defined grammatical rules are given to both discriminator and generator.
Auto-tuning Neural Network Quantization Framework for Collaborative Inference Between the Cloud and Edge
By analyzing the characteristics of layers in DNNs, an auto-tuning neural network quantization framework for collaborative inference is proposed.
Background subtraction on depth videos with convolutional neural networks
Background subtraction is a significant component of computer vision systems.
The localization of single pulse in VLBI observation
The combination of cross spectrum based detection and the localization proposed in this work then provide a thorough solution for searching single pulse in VLBI observation.
Instrumentation and Methods for Astrophysics
DENet: A Universal Network for Counting Crowd with Varying Densities and Scales
Counting people or objects with significantly varying scales and densities has attracted much interest from the research community and yet it remains an open problem.
Hyperspectral Image Classification Based on Adaptive Sparse Deep Network
Sparse model is widely used in hyperspectral image classification. However, different of sparsity and regularization parameters has great influence on the classification results. In this paper, a novel adaptive sparse deep network based on deep architecture is proposed, which can construct the optimal sparse representation and regularization parameters by deep network. Firstly, a data flow graph is designed to represent each update iteration based on Alternating Direction Method of Multipliers (ADMM) algorithm. Forward network and Back-Propagation network are deduced. All parameters are updated by gradient descent in Back-Propagation. Then we proposed an Adaptive Sparse Deep Network. Comparing with several traditional classifiers or other algorithm for sparse model, experiment results indicate that our method achieves great improvement in HSI classification.
Intelligent Resource Scheduling for Co-located Latency-critical Services: A Multi-Model Collaborative Learning Approach
More importantly, we observe that there are "resource cliffs" in the scheduling exploration space.
PDANet: Pyramid Density-aware Attention Net for Accurate Crowd Counting
For this purpose, a classifier evaluates the density level of the input features and then passes them to the corresponding high and low crowded DAD modules.
LANCE: Efficient Low-Precision Quantized Winograd Convolution for Neural Networks Based on Graphics Processing Units
Accelerating deep convolutional neural networks has become an active topic and sparked an interest in academia and industry.
Identification of splicing edges in tampered image based on Dichromatic Reflection Model
Therefore we present a novel optic-physical method to discriminate splicing edges from natural edges in a tampered image.
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.
W-net: Simultaneous segmentation of multi-anatomical retinal structures using a multi-task deep neural network
To further prove the generalization property of the proposed method, we applied the trained model on the DRIONS-DB dataset for OD segmentation and on the MESSIDOR dataset for exudate segmentation.
Challenge-Aware RGBT Tracking
RGB and thermal source data suffer from both shared and specific challenges, and how to explore and exploit them plays a critical role to represent the target appearance in RGBT tracking.
Ranked #6 on
Rgb-T Tracking
on GTOT
Semi-Supervised Active Learning for COVID-19 Lung Ultrasound Multi-symptom Classification
Ultrasound (US) is a non-invasive yet effective medical diagnostic imaging technique for the COVID-19 global pandemic.
Fusion-Catalyzed Pruning for Optimizing Deep Learning on Intelligent Edge Devices
The increasing computational cost of deep neural network models limits the applicability of intelligent applications on resource-constrained edge devices.
Topological Transformations in Pentagonal 2D Materials Induced by Stone-Wales Defects
We discover two distinct topological pathways through which the pentagonal Cairo tiling (P5), a structural model for single-layer $AB_2$ pyrite materials, respectively transforms into a crystalline rhombus-hexagon (C46) tiling and random rhombus-pentagon-hexagon (R456) tilings, by continuously introducing the Stone-Wales (SW) topological defects.
Soft Condensed Matter Disordered Systems and Neural Networks Materials Science
A molecular dynamics simulation study on the frustrated Lewis pairs in ionic liquids
Spatial distribution function (SDF) results show that toluene formed a continuum solvation shell, which hinders the interactions of (tBu)3P and B(C6F5)3 , while [Cnmim][NTf2] leave a relatively large empty space, which is accessible by (tBu3)P molecules, resulting in a higher probability of Lewis acids and bases interactions.
Chemical Physics
Efficient electrochemical reduction of CO2 to CO by soft functional materials
This work provides a new strategy to design novel ILs for high efficiency electrochemical reduction of CO2 to CO.
Materials Science
Theory of polymer diffusion in polymer-nanoparticle mixtures: effect of nanoparticle concentration and polymer length
The dynamics of polymer-nanoparticle (NP) mixtures, which involves multiple scales and system-specific variables, has posed a long-standing challenge on its theoretical description.
Soft Condensed Matter
An Interpretable Mapping from a Communication System to a Neural Network for Optimal Transceiver-Joint Equalization
In this paper, we propose a scheme that utilizes the optimization ability of artificial intelligence (AI) for optimal transceiver-joint equalization in compensating for the optical filtering impairments caused by wavelength selective switches (WSS).
Pinpointing the Memory Behaviors of DNN Training
The training of deep neural networks (DNNs) is usually memory-hungry due to the limited device memory capacity of DNN accelerators.
An LSTM-Aided Hybrid Random Access Scheme for 6G Machine Type Communication Networks
In this paper, an LSTM-aided hybrid random access scheme (LSTMH-RA) is proposed to support diverse quality of service (QoS) requirements in 6G machine-type communication (MTC) networks, where massive MTC (mMTC) devices and ultra-reliable low latency communications (URLLC) devices coexist.
Extending Isolation Forest for Anomaly Detection in Big Data via K-Means
Moreover, we evaluate our proposed model on the live streaming data and find that our proposed system can be used for real-time anomaly detection in the industrial setup.
Few-Shot Partial-Label Learning
Partial-label learning (PLL) generally focuses on inducing a noise-tolerant multi-class classifier by training on overly-annotated samples, each of which is annotated with a set of labels, but only one is the valid label.
Memory Approximate Message Passing
Approximate message passing (AMP) is a low-cost iterative parameter-estimation technique for certain high-dimensional linear systems with non-Gaussian distributions.
A Dialogue-based Information Extraction System for Medical Insurance Assessment
In the Chinese medical insurance industry, the assessor's role is essential and requires significant efforts to converse with the claimant.
MetaMIML: Meta Multi-Instance Multi-Label Learning
Multi-Instance Multi-Label learning (MIML) models complex objects (bags), each of which is associated with a set of interrelated labels and composed with a set of instances.
Cross-modal Zero-shot Hashing by Label Attributes Embedding
Cross-modal hashing (CMH) is one of the most promising methods in cross-modal approximate nearest neighbor search.
Cross-Modal Object Tracking: Modality-Aware Representations and A Unified Benchmark
To promote the research and development of cross-modal object tracking, we propose a new algorithm, which learns the modality-aware target representation to mitigate the appearance gap between RGB and NIR modalities in the tracking process.
Open-Set Crowdsourcing using Multiple-Source Transfer Learning
First, OSCrowd integrates crowd theme related datasets into a large source domain to facilitate partial transfer learning to approximate the label space inference of these tasks.
Sufficient-Statistic Memory AMP
Given an arbitrary MAMP, we can construct an SS-MAMP by damping, which not only ensures the convergence of the state evolution, but also preserves the orthogonality, i. e., its dynamics can be correctly described by state evolution.
Dynamic Virtual Network Embedding Algorithm based on Graph Convolution Neural Network and Reinforcement Learning
Simulation experiments verified that the dynamic VNE algorithm based on RL and GCNN has good basic VNE characteristics.
Space-Air-Ground Integrated Multi-domain Network Resource Orchestration based on Virtual Network Architecture: a DRL Method
Based on virtual network architecture and deep reinforcement learning (DRL), we model SAGIN's heterogeneous resource orchestration as a multi-domain virtual network embedding (VNE) problem, and propose a SAGIN cross-domain VNE algorithm.
Capacity Optimality of OAMP in Coded Large Unitarily Invariant Systems
Under the assumptions that the state evolution for joint OAMP and FEC decoding is correct and the replica method is reliable, we analyze the achievable rate of OAMP.
Sufficient Statistic Memory Approximate Message Passing
Approximate message passing (AMP) type algorithms have been widely used in the signal reconstruction of certain large random linear systems.
High Speed Rotation Estimation with Dynamic Vision Sensors
By designing a series of signal processing algorithms bespoke for dynamic vision sensing on mobile devices, EV-Tach is able to extract the rotational speed accurately from the event stream produced by dynamic vision sensing on rotary targets.
Multimodal Graph Learning for Deepfake Detection
We evaluate the effectiveness of our method through extensive experiments on widely-used benchmarks and demonstrate that our method outperforms the state-of-the-art detectors in terms of generalization ability and robustness against unknown disturbances.
Parameter-Efficient Transformer with Hybrid Axial-Attention for Medical Image Segmentation
To this end, we propose a parameter-efficient transformer to explore intrinsic inductive bias via position information for medical image segmentation.
Cross-Modal Mutual Learning for Cued Speech Recognition
To our knowledge, this is the first work on ACSR for Mandarin Chinese.
Mitigation of Spatial Nonstationarity with Vision Transformers
However, there is a paucity of demonstrated best practice and general guidance on mitigation of spatial nonstationarity with deep learning in the geospatial context.
Algebra of L-banded Matrices
Damping is commonly employed to ensure the convergence of iterative algorithms.
Context Matters: A Strategy to Pre-train Language Model for Science Education
However, the ideal type of data to contextualize pre-trained language model and improve the performance in automatically scoring student written responses remains unclear.
Prescribed Time Time-varying Output Formation Tracking for Uncertain Heterogeneous Multi-agent Systems
The time-varying output formation tracking for the heterogeneous multi-agent systems (MAS) is investigated in this paper.
Spatio-Temporal Structure Consistency for Semi-supervised Medical Image Classification
Experiments on two medical image datasets (i. e., ISIC 2018 challenge and ChestX-ray14) show that our method outperforms state-of-the-art SSL methods.
Low-Complexity Memory AMP Detector for High-Mobility MIMO-OTFS SCMA Systems
Efficient signal detectors are rather important yet challenging to achieve satisfactory performance for large-scale communication systems.
Prompt Learning to Mitigate Catastrophic Forgetting in Cross-lingual Transfer for Open-domain Dialogue Generation
Dialogue systems for non-English languages have long been under-explored.
Robust Computation Offloading and Trajectory Optimization for Multi-UAV-Assisted MEC: A Multi-Agent DRL Approach
For multiple Unmanned-Aerial-Vehicles (UAVs) assisted Mobile Edge Computing (MEC) networks, we study the problem of combined computation and communication for user equipments deployed with multi-type tasks.
Think-in-Memory: Recalling and Post-thinking Enable LLMs with Long-Term Memory
Memory-augmented Large Language Models (LLMs) have demonstrated remarkable performance in long-term human-machine interactions, which basically relies on iterative recalling and reasoning of history to generate high-quality responses.
TransCDR: a deep learning model for enhancing the generalizability of cancer drug response prediction through transfer learning and multimodal data fusion for drug representation
Although many models have been developed to utilize the representations of drugs and cancer cell lines for predicting cancer drug responses (CDR), their performances can be improved by addressing issues such as insufficient data modality, suboptimal fusion algorithms, and poor generalizability for novel drugs or cell lines.
Efficient Trigger Word Insertion
With the boom in the natural language processing (NLP) field these years, backdoor attacks pose immense threats against deep neural network models.
From Beginner to Expert: Modeling Medical Knowledge into General LLMs
(3) Specifically for multi-choice questions in the medical domain, we propose a novel Verification-of-Choice approach for prompting engineering, which significantly enhances the reasoning ability of LLMs.
Time-Series Contrastive Learning against False Negatives and Class Imbalance
As an exemplary self-supervised approach for representation learning, time-series contrastive learning has exhibited remarkable advancements in contemporary research.
Channel Mapping Based on Interleaved Learning with Complex-Domain MLP-Mixer
For such a channel mapping task, inspired by the intrinsic coupling across the space and frequency domains, this letter proposes to use interleaved learning with partial antenna and subcarrier characteristics to represent the whole MIMO-OFDM channel.
How Can Large Language Models Understand Spatial-Temporal Data?
We tackle the data mismatch by proposing: 1) STG-Tokenizer: This spatial-temporal graph tokenizer transforms intricate graph data into concise tokens capturing both spatial and temporal relationships; 2) STG-Adapter: This minimalistic adapter, consisting of linear encoding and decoding layers, bridges the gap between tokenized data and LLM comprehension.
Computation and Parameter Efficient Multi-Modal Fusion Transformer for Cued Speech Recognition
Cued Speech (CS) is a pure visual coding method used by hearing-impaired people that combines lip reading with several specific hand shapes to make the spoken language visible.
Global Tropical Cyclone Intensity Forecasting with Multi-modal Multi-scale Causal Autoregressive Model
Accurate forecasting of Tropical cyclone (TC) intensity is crucial for formulating disaster risk reduction strategies.
Towards Automatic Evaluation for LLMs' Clinical Capabilities: Metric, Data, and Algorithm
Applying such paradigm, we construct an evaluation benchmark in the field of urology, including a LCP, a SPs dataset, and an automated RAE.
