Search Results for author:
Found 79 papers, 34 papers with code
Rˆ3Net:Relation-embedded Representation Reconstruction Network for Change Captioning
In this paper, we propose a Relation-embedded Representation Reconstruction Network (Rˆ3Net) to explicitly distinguish the real change from the large amount of clutter and irrelevant changes.
Norm Tweaking: High-performance Low-bit Quantization of Large Language Models
On GLM-130B and OPT-66B, our method even achieves the same level of accuracy at 2-bit quantization as their float ones.
Separate and Locate: Rethink the Text in Text-based Visual Question Answering
To tackle these problems, we propose a novel method named Separate and Locate (SaL) that explores text contextual cues and designs spatial position embedding to construct spatial relations between OCR texts.
FPTQ: Fine-grained Post-Training Quantization for Large Language Models
In this study, we propose a novel W4A8 post-training quantization method for the available open-sourced LLMs, which combines the advantages of both two recipes.
Predator-prey survival pressure is sufficient to evolve swarming behaviors
The comprehension of how local interactions arise in global collective behavior is of utmost importance in both biological and physical research.
CATS: A Pragmatic Chinese Answer-to-Sequence Dataset with Large Scale and High Quality
To alleviate these limitations, in this paper, we present CATS, a pragmatic Chinese answer-to-sequence dataset with large scale and high quality.
Protective Self-Adaptive Pruning to Better Compress DNNs
Adaptive network pruning approach has recently drawn significant attention due to its excellent capability to identify the importance and redundancy of layers and filters and customize a suitable pruning solution.
Neighborhood Contrastive Transformer for Change Captioning
Change captioning is to describe the semantic change between a pair of similar images in natural language.
Plan-then-Seam: Towards Efficient Table-to-Text Generation
Table-to-text generation aims at automatically generating text to help people conveniently obtain salient information in tables.
Decoupling-and-Aggregating for Image Exposure Correction
To this end, we inject the addition/difference operation into the convolution process and devise a Contrast Aware (CA) unit and a Detail Aware (DA) unit to facilitate the statistical and structural regularities modeling.
Hard Sample Aware Network for Contrastive Deep Graph Clustering
Moreover, under the guidance of the carefully collected high-confidence clustering information, our proposed weight modulating function will first recognize the positive and negative samples and then dynamically up-weight the hard sample pairs while down-weighting the easy ones.
Learning to Dub Movies via Hierarchical Prosody Models
Given a piece of text, a video clip and a reference audio, the movie dubbing (also known as visual voice clone V2C) task aims to generate speeches that match the speaker's emotion presented in the video using the desired speaker voice as reference.
Make RepVGG Greater Again: A Quantization-aware Approach
The tradeoff between performance and inference speed is critical for practical applications.
BEV-Locator: An End-to-end Visual Semantic Localization Network Using Multi-View Images
Then a cross-model transformer associates the BEV features and semantic map queries.
Graph-to-Text Generation with Dynamic Structure Pruning
Most graph-to-text works are built on the encoder-decoder framework with cross-attention mechanism.
YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications
The YOLO community has prospered overwhelmingly to enrich its use in a multitude of hardware platforms and abundant scenarios.
Ranked #15 on
Object Detection
on COCO-O
EpiGNN: Exploring Spatial Transmission with Graph Neural Network for Regional Epidemic Forecasting
Epidemic forecasting is the key to effective control of epidemic transmission and helps the world mitigate the crisis that threatens public health.
Energy and Spectrum Efficient Federated Learning via High-Precision Over-the-Air Computation
Guided by FL convergence analysis, we formulate a joint transmission probability and local computing control optimization, aiming to minimize the overall energy consumption (i. e., iterative local computing + multi-round communications) of mobile devices in FL.
Entity-enhanced Adaptive Reconstruction Network for Weakly Supervised Referring Expression Grounding
Second, most previous weakly supervised REG methods ignore the discriminative location and context of the referent, causing difficulties in distinguishing the target from other same-category objects.
DSPNet: Towards Slimmable Pretrained Networks based on Discriminative Self-supervised Learning
However, when facing various resource budgets in real-world applications, it costs a huge computation burden to pretrain multiple networks of various sizes one by one.
Multiple Kernel Clustering with Dual Noise Minimization
As a representative, late fusion MKC first decomposes the kernels into orthogonal partition matrices, then learns a consensus one from them, achieving promising performance recently.
Cross-Architecture Knowledge Distillation
However, most existing knowledge distillation methods only consider homologous-architecture distillation, such as distilling knowledge from CNN to CNN.
Adaptive Structural Similarity Preserving for Unsupervised Cross Modal Hashing
We introduce structural semantic metrics based on graph adjacency relations during the semantic reconstruction and correlation mining stage and meanwhile align the structure semantics in the hash space with an asymmetric binary optimization process.
Local Sample-weighted Multiple Kernel Clustering with Consensus Discriminative Graph
Multiple kernel clustering (MKC) is committed to achieving optimal information fusion from a set of base kernels.
Automatic Relation-aware Graph Network Proliferation
However, the currently used graph search space overemphasizes learning node features and neglects mining hierarchical relational information.
Ranked #1 on
Link Prediction
on TSP/HCP Benchmark set
IR-GAN: Image Manipulation with Linguistic Instruction by Increment Reasoning
Conditional image generation is an active research topic including text2image and image translation.
Unsupervised Coherent Video Cartoonization with Perceptual Motion Consistency
Furthermore, we devise the spatio-temporal correlative map as a style-independent, global-aware regularization on the perceptual motion consistency.
FaceVerse: a Fine-grained and Detail-controllable 3D Face Morphable Model from a Hybrid Dataset
In the coarse module, we generate a base parametric model from large-scale RGB-D images, which is able to predict accurate rough 3D face models in different genders, ages, etc.
Open-Vocabulary One-Stage Detection with Hierarchical Visual-Language Knowledge Distillation
Open-vocabulary object detection aims to detect novel object categories beyond the training set.
Ranked #17 on
Open Vocabulary Object Detection
on MSCOCO
Few Shot Generative Model Adaption via Relaxed Spatial Structural Alignment
A feasible solution is to start with a GAN well-trained on a large scale source domain and adapt it to the target domain with a few samples, termed as few shot generative model adaption.
Modality-Adaptive Mixup and Invariant Decomposition for RGB-Infrared Person Re-Identification
RGB-infrared person re-identification is an emerging cross-modality re-identification task, which is very challenging due to significant modality discrepancy between RGB and infrared images.
Debiased Batch Normalization via Gaussian Process for Generalizable Person Re-Identification
In this paper, we propose a novel Debiased Batch Normalization via Gaussian Process approach (GDNorm) for generalizable person re-identification, which models the feature statistic estimation from BN layers as a dynamically self-refining Gaussian process to alleviate the bias to unseen domain for improving the generalization.
Generalizable Person Re-identification
Representation Learning
Fast-R2D2: A Pretrained Recursive Neural Network based on Pruned CKY for Grammar Induction and Text Representation
We propose to use a top-down parser as a model-based pruning method, which also enables parallel encoding during inference.
Recursive Least-Squares Estimator-Aided Online Learning for Visual Tracking
In this paper, we propose a simple yet effective recursive least-squares estimator-aided online learning approach for few-shot online adaptation without requiring offline training.
Calibrated Feature Decomposition for Generalizable Person Re-Identification
The calibrated person representation is subtly decomposed into the identity-relevant feature, domain feature, and the remaining entangled one.
Domain Generalization
Generalizable Person Re-identification
R$^3$Net:Relation-embedded Representation Reconstruction Network for Change Captioning
In this paper, we propose a Relation-embedded Representation Reconstruction Network (R$^3$Net) to explicitly distinguish the real change from the large amount of clutter and irrelevant changes.
Edge-featured Graph Neural Architecture Search
Recently, researchers study neural architecture search (NAS) to reduce the dependence of human expertise and explore better GNN architectures, but they over-emphasize entity features and ignore latent relation information concealed in the edges.
Multi-Modulation Network for Audio-Visual Event Localization
We propose a novel MultiModulation Network (M2N) to learn the above correlation and leverage it as semantic guidance to modulate the related auditory, visual, and fused features.
Improving Encoder by Auxiliary Supervision Tasks for Table-to-Text Generation
However, it is hard for a vanilla encoder to capture these.
Ranked #1 on
Table-to-Text Generation
on RotoWire
Fast Batch Nuclear-norm Maximization and Minimization for Robust Domain Adaptation
Due to the domain discrepancy in visual domain adaptation, the performance of source model degrades when bumping into the high data density near decision boundary in target domain.
Structured Multi-Level Interaction Network for Video Moment Localization via Language Query
In particular, for cross-modal interaction, we interact the sentence-level query with the whole moment while interact the word-level query with content and boundary, as in a coarse-to-fine manner.
TreeBERT: A Tree-Based Pre-Trained Model for Programming Language
In this paper, we present TreeBERT, a tree-based pre-trained model for improving programming language-oriented generation tasks.
Improving Semiconductor Device Modeling for Electronic Design Automation by Machine Learning Techniques
The inherent flexibility of our approach allows easy adaptation to various tasks, thus making it highly relevant to many applications of the semiconductor industry.
Comparing Representations in Tracking for Event Camera-based SLAM
This paper investigates two typical image-type representations for event camera-based tracking: time surface (TS) and event map (EM).
Rethinking Graph Neural Architecture Search from Message-passing
Inspired by the strong searching capability of neural architecture search (NAS) in CNN, this paper proposes Graph Neural Architecture Search (GNAS) with novel-designed search space.
Dissecting Energy Budget of a Gamma-Ray Burst Fireball
The jet composition and radiative efficiency of GRBs are poorly constrained from the data.
High Energy Astrophysical Phenomena
Manipulating the anisotropic phase separation in strained VO2 epitaxial films by nanoscale ion-implantation
Manipulating the strain induced poly-domains and phase transition in correlated oxide material are important for high performance devices fabrication.
Materials Science Strongly Correlated Electrons
Towards Energy Efficient Federated Learning over 5G+ Mobile Devices
The continuous convergence of machine learning algorithms, 5G and beyond (5G+) wireless communications, and artificial intelligence (AI) hardware implementation hastens the birth of federated learning (FL) over 5G+ mobile devices, which pushes AI functions to mobile devices and initiates a new era of on-device AI applications.
To Talk or to Work: Flexible Communication Compression for Energy Efficient Federated Learning over Heterogeneous Mobile Edge Devices
Recent advances in machine learning, wireless communication, and mobile hardware technologies promisingly enable federated learning (FL) over massive mobile edge devices, which opens new horizons for numerous intelligent mobile applications.
Energy Efficient Federated Learning over Heterogeneous Mobile Devices via Joint Design of Weight Quantization and Wireless Transmission
To address these challenges, in this paper, we attempt to take FL into the design of future wireless networks and develop a novel joint design of wireless transmission and weight quantization for energy efficient FL over mobile devices.
Learning Better Representation for Tables by Self-Supervised Tasks
Secondly, the target texts in training dataset may contain redundant information or facts do not exist in the input tables.
TDRE: A Tensor Decomposition Based Approach for Relation Extraction
Extracting entity pairs along with relation types from unstructured texts is a fundamental subtask of information extraction.
Selective Information Passing for MR/CT Image Segmentation
However, not all the feature maps transmitted by those connections contribute positively to the network performance.
Artificial Lateral Line Based Relative State Estimation for Two Adjacent Robotic Fish
Then four typical regression methods, including random forest algorithm, support vector regression, back propagation neural network, and multiple linear regression method are used for establishing regression models between the ALLS-measured HPVs and the relative states.
Delay-Aware Multi-Agent Reinforcement Learning for Cooperative and Competitive Environments
We also test the proposed algorithm in traffic scenarios that require coordination of all autonomous vehicles to show the practical value of delay-awareness.
Delay-Aware Model-Based Reinforcement Learning for Continuous Control
Action delays degrade the performance of reinforcement learning in many real-world systems.
Adversarial Evaluation of Autonomous Vehicles in Lane-Change Scenarios
Results show that the adversarial scenarios generated by our method significantly degrade the performance of the tested vehicles.
Real-world Person Re-Identification via Degradation Invariance Learning
Person re-identification (Re-ID) in real-world scenarios usually suffers from various degradation factors, e. g., low-resolution, weak illumination, blurring and adverse weather.
Secret Sharing based Secure Regressions with Applications
Nowadays, the utilization of the ever expanding amount of data has made a huge impact on web technologies while also causing various types of security concerns.
Parsing-based View-aware Embedding Network for Vehicle Re-Identification
Vehicle Re-Identification is to find images of the same vehicle from various views in the cross-camera scenario.
State-Relabeling Adversarial Active Learning
In this paper, we propose a state relabeling adversarial active learning model (SRAAL), that leverages both the annotation and the labeled/unlabeled state information for deriving the most informative unlabeled samples.
Towards Discriminability and Diversity: Batch Nuclear-norm Maximization under Label Insufficient Situations
We find by theoretical analysis that the prediction discriminability and diversity could be separately measured by the Frobenius-norm and rank of the batch output matrix.
Secure Social Recommendation based on Secret Sharing
It is well known that social information, which is rich on social platforms such as Facebook, are useful to recommender systems.
Meta-Learning PAC-Bayes Priors in Model Averaging
In this paper, we mainly consider the scenario in which we have a common model set used for model averaging instead of selecting a single final model via a model selection procedure to account for this model's uncertainty to improve the reliability and accuracy of inferences.
Low rank tensor completion with sparse regularization in a transformed domain
While the sparse regularizer is imposed by a $\ell_{1}$-norm in a discrete cosine transformation (DCT) domain, which can better employ the local sparse property of completed data.
Thick-Net: Parallel Network Structure for Sequential Modeling
Recurrent neural networks have been widely used in sequence learning tasks.
Machine Discovery of Partial Differential Equations from Spatiotemporal Data
The study presents a general framework for discovering underlying Partial Differential Equations (PDEs) using measured spatiotemporal data.
Knowledge-guided Pairwise Reconstruction Network for Weakly Supervised Referring Expression Grounding
Weakly supervised referring expression grounding (REG) aims at localizing the referential entity in an image according to linguistic query, where the mapping between the image region (proposal) and the query is unknown in the training stage.
Adaptive Reconstruction Network for Weakly Supervised Referring Expression Grounding
It builds the correspondence between image region proposal and query in an adaptive manner: adaptive grounding and collaborative reconstruction.
Image Classification base on PCA of Multi-view Deep Representation
In the age of information explosion, image classification is the key technology of dealing with and organizing a large number of image data.
Fast OBDD Reordering using Neural Message Passing on Hypergraph
Ordered binary decision diagrams (OBDDs) are an efficient data structure for representing and manipulating Boolean formulas.
A Self-Attentive Model with Gate Mechanism for Spoken Language Understanding
In this work, we propose a novel self-attentive model with gate mechanism to fully utilize the semantic correlation between slot and intent.
An Ontology-Based Artificial Intelligence Model for Medicine Side-Effect Prediction: Taking Traditional Chinese Medicine as An Example
In this work, an ontology-based model for AI-assisted medicine side-effect (SE) prediction is developed, where three main components, including the drug model, the treatment model, and the AI-assisted prediction model, of proposed model are presented.
Combinatorial Pure Exploration with Continuous and Separable Reward Functions and Its Applications (Extended Version)
Each decision has a reward according to the distributions of arms.
A Graph Regularized Deep Neural Network for Unsupervised Image Representation Learning
Deep Auto-Encoder (DAE) has shown its promising power in high-level representation learning.
Logical Parsing from Natural Language Based on a Neural Translation Model
Under our learning policy, the Seq2Seq model can learn mappings gradually with noises.
Image Prediction for Limited-angle Tomography via Deep Learning with Convolutional Neural Network
The qualitative and quantitative evaluations of experimental results indicate that the proposed method show a stable and prospective performance on artifacts reduction and detail recovery for limited angle tomography.
Maximum Cohesive Grid of Superpixels for Fast Object Localization
For this purpose, we aim at constructing maximum cohesive SP-grid, which is composed of real nodes, i. e. SPs, and dummy nodes that are meaningless in the image with only position-taking function in the grid.
