Search Results for author:
Found 99 papers, 21 papers with code
MMEKG: Multi-modal Event Knowledge Graph towards Universal Representation across Modalities
Events are fundamental building blocks of real-world happenings.
LST-Net: Learning a Convolutional Neural Network with a Learnable Sparse Transform
The 2D convolutional (Conv2d) layer is the fundamental element to a deep convolutional neural network (CNN).
UrbanVLP: A Multi-Granularity Vision-Language Pre-Trained Foundation Model for Urban Indicator Prediction
Urban indicator prediction aims to infer socio-economic metrics in diverse urban landscapes using data-driven methods.
Tri-Perspective View Decomposition for Geometry-Aware Depth Completion
Depth completion is a vital task for autonomous driving, as it involves reconstructing the precise 3D geometry of a scene from sparse and noisy depth measurements.
Spatio-Temporal Fluid Dynamics Modeling via Physical-Awareness and Parameter Diffusion Guidance
This paper proposes a two-stage framework named ST-PAD for spatio-temporal fluid dynamics modeling in the field of earth sciences, aiming to achieve high-precision simulation and prediction of fluid dynamics through spatio-temporal physics awareness and parameter diffusion guidance.
Data is all you need: Finetuning LLMs for Chip Design via an Automated design-data augmentation framework
Our 13B model (ChipGPT-FT) has a pass rate improvement compared with GPT-3. 5 in Verilog generation and outperforms in EDA script (i. e., SiliconCompiler) generation with only 200 EDA script data.
DynST: Dynamic Sparse Training for Resource-Constrained Spatio-Temporal Forecasting
In this paper, we introduce for the first time the concept of spatio-temporal data dynamic sparse training and are committed to adaptively, dynamically filtering important sensor distributions.
Spatio-Temporal Field Neural Networks for Air Quality Inference
The air quality inference problem aims to utilize historical data from a limited number of observation sites to infer the air quality index at an unknown location.
FineDiffusion: Scaling up Diffusion Models for Fine-grained Image Generation with 10,000 Classes
The class-conditional image generation based on diffusion models is renowned for generating high-quality and diverse images.
CaT-GNN: Enhancing Credit Card Fraud Detection via Causal Temporal Graph Neural Networks
Credit card fraud poses a significant threat to the economy.
Dueling Over Dessert, Mastering the Art of Repeated Cake Cutting
Alice cuts the cake at a point of her choice, while Bob chooses the left piece or the right piece, leaving the remainder for Alice.
Two Trades is not Baffled: Condensing Graph via Crafting Rational Gradient Matching
Training on large-scale graphs has achieved remarkable results in graph representation learning, but its cost and storage have raised growing concerns.
MolTC: Towards Molecular Relational Modeling In Language Models
Molecular Relational Learning (MRL), aiming to understand interactions between molecular pairs, plays a pivotal role in advancing biochemical research.
Modeling Spatio-temporal Dynamical Systems with Neural Discrete Learning and Levels-of-Experts
In this paper, we address the issue of modeling and estimating changes in the state of the spatio-temporal dynamical systems based on a sequence of observations like video frames.
EXGC: Bridging Efficiency and Explainability in Graph Condensation
Graph representation learning on vast datasets, like web data, has made significant strides.
Two Heads Are Better Than One: Boosting Graph Sparse Training via Semantic and Topological Awareness
Specifically, GST initially constructs a topology & semantic anchor at a low training cost, followed by performing dynamic sparse training to align the sparse graph with the anchor.
SwapNet: Efficient Swapping for DNN Inference on Edge AI Devices Beyond the Memory Budget
To this end, we develop SwapNet, an efficient DNN block swapping middleware for edge AI devices.
Earthfarseer: Versatile Spatio-Temporal Dynamical Systems Modeling in One Model
Efficiently modeling spatio-temporal (ST) physical processes and observations presents a challenging problem for the deep learning community.
TMT-VIS: Taxonomy-aware Multi-dataset Joint Training for Video Instance Segmentation
What we possess are numerous isolated filed-specific datasets, thus, it is appealing to jointly train models across the aggregation of datasets to enhance data volume and diversity.
Attend Who is Weak: Enhancing Graph Condensation via Cross-Free Adversarial Training
We seminally propose the concept of Shock Absorber (a type of perturbation) that enhances the robustness and stability of the original graphs against changes in an adversarial training fashion.
To be or not to be? an exploration of continuously controllable prompt engineering
In response, we introduce ControlPE (Continuously Controllable Prompt Engineering).
OpsEval: A Comprehensive IT Operations Benchmark Suite for Large Language Models
Information Technology (IT) Operations (Ops), particularly Artificial Intelligence for IT Operations (AIOps), is the guarantee for maintaining the orderly and stable operation of existing information systems.
Causal-Story: Local Causal Attention Utilizing Parameter-Efficient Tuning For Visual Story Synthesis
The current state-of-the-art method combines the features of historical captions, historical frames, and the current captions as conditions for generating the current frame.
Towards Vehicle-to-everything Autonomous Driving: A Survey on Collaborative Perception
Specifically, we analyze the performance changes of different methods under different bandwidths, providing a deep insight into the performance-bandwidth trade-off issue.
AltNeRF: Learning Robust Neural Radiance Field via Alternating Depth-Pose Optimization
Neural Radiance Fields (NeRF) have shown promise in generating realistic novel views from sparse scene images.
The Snowflake Hypothesis: Training Deep GNN with One Node One Receptive field
Despite Graph Neural Networks demonstrating considerable promise in graph representation learning tasks, GNNs predominantly face significant issues with over-fitting and over-smoothing as they go deeper as models of computer vision realm.
Deep learning radiomics for assessment of gastroesophageal varices in people with compensated advanced chronic liver disease
Validation analysis revealed that the AUCs of DLRP were 0. 91 for GEV (95% CI 0. 90 to 0. 93, p < 0. 05) and 0. 88 for HRV (95% CI 0. 86 to 0. 89, p < 0. 01), which were significantly and robustly better than canonical risk indicators, including the value of LSM and SSM.
Safety Guaranteed Control for Spacecraft Inspection Mission
In order to address this issue, we propose a control strategy based on control barrier functions, summarized as "safety check on kinematics" and "velocity tracking on dynamics" approach.
Variable Radiance Field for Real-Life Category-Specifc Reconstruction from Single Image
Our key contributions are: (1) We parameterize the geometry and appearance of the object using a multi-scale global feature extractor, which avoids frequent point-wise feature retrieval and camera dependency.
Adaptive Compatible Performance Control for Spacecraft Attitude Control under Motion Constraints with Guaranteed Accuracy
To tackle this problem, we propose a modified framework called Compatible Performance Control (CPC), which integrates the Prescribed Performance Control (PPC) scheme with a contradiction detection and alleviation strategy.
Composite Triggered Intermittent Control for Constrained Spacecraft Attitude Tracking
Further, the basic intermittent attitude controller is extended to a "constrained version" by introducing a strictly bounded virtual control law and an input saturation compensation auxiliary system.
ConES: Concept Embedding Search for Parameter Efficient Tuning Large Vision Language Models
To achieve this, we propose a Concept Embedding Search (ConES) approach by optimizing prompt embeddings -- without the need of the text encoder -- to capture the 'concept' of the image modality through a variety of task objectives.
Deep Learning Applications Based on WISE Infrared Data: Classification of Stars, Galaxies and Quasars
The Wide-field Infrared Survey Explorer (WISE) has detected hundreds of millions of sources over the entire sky.
ArtGPT-4: Towards Artistic-understanding Large Vision-Language Models with Enhanced Adapter
However, a grand challenge of exploiting LLMs for multimodal learning is the size of pre-trained LLMs which are always with billions of parameters.
Siamese DETR
In this work, we present Siamese DETR, a Siamese self-supervised pretraining approach for the Transformer architecture in DETR.
Explore the Power of Synthetic Data on Few-shot Object Detection
To construct a representative synthetic training dataset, we maximize the diversity of the selected images via a sample-based and cluster-based method.
FedREP: A Byzantine-Robust, Communication-Efficient and Privacy-Preserving Framework for Federated Learning
Based on ConSpar, we further propose a novel FL framework called FedREP, which is Byzantine-robust, communication-efficient and privacy-preserving.
An Effective Crop-Paste Pipeline for Few-shot Object Detection
Specifically, we first discover the base images which contain the FP of novel categories and select a certain amount of samples from them for the base and novel categories balance.
Oriented Object Detection in Optical Remote Sensing Images using Deep Learning: A Survey
Given the rapid development of this field, this paper aims to provide a comprehensive survey of recent advances in oriented object detection.
DesNet: Decomposed Scale-Consistent Network for Unsupervised Depth Completion
Unsupervised depth completion aims to recover dense depth from the sparse one without using the ground-truth annotation.
Event-Triggered Intermittent Prescribed Performance Control for Spacecraft Attitude Reorientation
The prescribed performance control (PPC) scheme is often employed for the control with guaranteed performance.
ALT: Boosting Deep Learning Performance by Breaking the Wall between Graph and Operator Level Optimizations
Deep learning models rely on highly optimized tensor libraries for efficient inference on heterogeneous hardware.
R$^2$F: A General Retrieval, Reading and Fusion Framework for Document-level Natural Language Inference
Document-level natural language inference (DOCNLI) is a new challenging task in natural language processing, aiming at judging the entailment relationship between a pair of hypothesis and premise documents.
Real2Sim2Real Transfer for Control of Cable-driven Robots via a Differentiable Physics Engine
This strategy is based on a differentiable physics engine that can be trained given limited data from a real robot.
6N-DoF Pose Tracking for Tensegrity Robots
To ensure that the pose estimates of rigid elements are physically feasible, i. e., they are not resulting in collisions between rods or with the environment, physical constraints are introduced during the optimization.
Network Traffic Anomaly Detection Method Based on Multi scale Residual Feature
To address the problem that traditional network traffic anomaly detection algorithms do not suffi-ciently mine potential features in long time domain, an anomaly detection method based on mul-ti-scale residual features of network traffic is proposed.
ERGO: Event Relational Graph Transformer for Document-level Event Causality Identification
In this paper, we propose a novel Event Relational Graph TransfOrmer (ERGO) framework for DECI, which improves existing state-of-the-art (SOTA) methods upon two aspects.
Few-shot Forgery Detection via Guided Adversarial Interpolation
Notably, our method is also validated to be robust to choices of majority and minority forgery approaches.
Multi-Modal Masked Pre-Training for Monocular Panoramic Depth Completion
To deal with the PDC task, we train a deep network that takes both depth and image as inputs for the dense panoramic depth recovery.
Towards Robust 2D Convolution for Reliable Visual Recognition
2D convolution (Conv2d), which is responsible for extracting features from the input image, is one of the key modules of a convolutional neural network (CNN).
Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine Synergy
This work thus proposes a novel active learning framework for realistic dataset annotation.
Ranked #1 on
Image Classification
on Food-101
(using extra training data)
A Recurrent Differentiable Engine for Modeling Tensegrity Robots Trainable with Low-Frequency Data
A model of NASA's icosahedron SUPERballBot on MuJoCo is used as the ground truth system to collect training data.
Prompt for Extraction? PAIE: Prompting Argument Interaction for Event Argument Extraction
We have conducted extensive experiments on three benchmarks, including both sentence- and document-level EAE.
Exploring Forensic Dental Identification with Deep Learning
In this work, we pioneer to study deep learning for dental forensic identification based on panoramic radiographs.
INTERN: A New Learning Paradigm Towards General Vision
Enormous waves of technological innovations over the past several years, marked by the advances in AI technologies, are profoundly reshaping the industry and the society.
Pitch Preservation In Singing Voice Synthesis
For the phoneme encoder, based on the analysis that same phonemes corresponding to varying pitches can produce similar pronunciations, this encoder is followed by an adversarially trained pitch classifier to enforce the identical phonemes with different pitches mapping into the same phoneme feature space.
X2Teeth: 3D Teeth Reconstruction from a Single Panoramic Radiograph
Different from single object reconstruction from photos, this task has the unique challenge of constructing multiple objects at high resolutions.
Domain Adaptation for Underwater Image Enhancement
However, these methods ignore the significant domain gap between the synthetic and real data (i. e., interdomain gap), and thus the models trained on synthetic data often fail to generalize well to real underwater scenarios.
Regularizing Nighttime Weirdness: Efficient Self-supervised Monocular Depth Estimation in the Dark
Monocular depth estimation aims at predicting depth from a single image or video.
FPB: Feature Pyramid Branch for Person Re-Identification
In this paper, we propose a lightweight Feature Pyramid Branch (FPB) to extract features from different layers of networks and aggregate them in a bidirectional pyramid structure.
Ranked #6 on
Person Re-Identification
on CUHK03 labeled
RigNet: Repetitive Image Guided Network for Depth Completion
However, blurry guidance in the image and unclear structure in the depth still impede the performance of the image guided frameworks.
Ranked #2 on
Depth Completion
on KITTI Depth Completion
Cascading Bandit under Differential Privacy
This paper studies \emph{differential privacy (DP)} and \emph{local differential privacy (LDP)} in cascading bandits.
A mm-Wave Patch Antenna with Broad Bandwidth and a Wide Angular Range
The wide half power beamwidth is achieved by suitably designed parasitic patches for the first resonant mode.
Conservative Contextual Combinatorial Cascading Bandit
We propose the novel \emph{conservative contextual combinatorial cascading bandit ($C^4$-bandit)}, a cascading online learning game which incorporates the conservative mechanism.
GaitSet: Cross-view Gait Recognition through Utilizing Gait as a Deep Set
In this paper, we present a novel perspective that utilizes gait as a deep set, which means that a set of gait frames are integrated by a global-local fused deep network inspired by the way our left- and right-hemisphere processes information to learn information that can be used in identification.
Atlas-aware ConvNetfor Accurate yet Robust Anatomical Segmentation
Second, we can largely boost the robustness of existing ConvNets, proved by: (i) testing on scans with synthetic pathologies, and (ii) training and evaluation on scans of different scanning setups across datasets.
Detecting and quantifying entanglement on near-term quantum devices
Firstly, it decomposes a positive map into a combination of quantum operations implementable on near-term quantum devices.
Quantum Physics Strongly Correlated Electrons
Exploring Instance-Level Uncertainty for Medical Detection
The ability of deep learning to predict with uncertainty is recognized as key for its adoption in clinical routines.
Sim2Sim Evaluation of a Novel Data-Efficient Differentiable Physics Engine for Tensegrity Robots
The results indicate that only 0. 25\% of ground truth data are needed to train a policy that works on the ground truth system when the differentiable engine is used for training against training the policy directly on the ground truth system.
Spring-Rod System Identification via Differentiable Physics Engine
We propose a novel differentiable physics engine for system identification of complex spring-rod assemblies.
What Have We Achieved on Text Summarization?
Deep learning has led to significant improvement in text summarization with various methods investigated and improved ROUGE scores reported over the years.
Single-Sideband Time-Modulated Phased Array With 2-bit Phased Shifters
The timemodulated module is implemented by adding periodic phase modulation to 2-bit phase shifters, which is simpler without performance loss compared to existing SSB time-modulated method.
Accurate Anchor Free Tracking
Specifically, a target object is defined by a bounding box center, tracking offset, and object size.
A First Principles Approach for Data-Efficient System Identification of Spring-Rod Systems via Differentiable Physics Engines
We propose a novel differentiable physics engine for system identification of complex spring-rod assemblies.
Sequential Weakly Labeled Multi-Activity Localization and Recognition on Wearable Sensors using Recurrent Attention Networks
Recently, several attention mechanisms are proposed to handle the weakly labeled human activity data, which do not require accurate data annotation.
A non-cooperative meta-modeling game for automated third-party calibrating, validating, and falsifying constitutive laws with parallelized adversarial attacks
The evaluation of constitutive models, especially for high-risk and high-regret engineering applications, requires efficient and rigorous third-party calibration, validation and falsification.
Oral-3D: Reconstructing the 3D Bone Structure of Oral Cavity from 2D Panoramic X-ray
In this paper, we propose a framework, named Oral-3D, to reconstruct the 3D oral cavity from a single PX image and prior information of the dental arch.
Adapting Object Detectors with Conditional Domain Normalization
Then this domain-vector is used to encode the features from another domain through a conditional normalization, resulting in different domains' features carrying the same domain attribute.
Ranked #1 on
Unsupervised Domain Adaptation
on SIM10K to BDD100K
T-Net: Learning Feature Representation with Task-specific Supervision for Biomedical Image Analysis
The encoder-decoder network is widely used to learn deep feature representations from pixel-wise annotations in biomedical image analysis.
Towards the standardization of quantum state verification using optimal strategies
We experimentally obtain the scaling parameter of $r=-0. 88\pm$0. 03 and $-0. 78\pm$0. 07 for nonadaptive and adaptive strategies, respectively.
Quantum Physics Optics
Effective Scaling of Blockchain Beyond Consensus Innovations and Moore's Law
As an emerging technology, blockchain has achieved great success in numerous application scenarios, from intelligent healthcare to smart cities.
Cryptography and Security Distributed, Parallel, and Cluster Computing 68M14 C.2.2
CompareNet: Anatomical Segmentation Network with Deep Non-local Label Fusion
Label propagation is a popular technique for anatomical segmentation.
Reconstruction-Aware Imaging System Ranking by use of a Sparsity-Driven Numerical Observer Enabled by Variational Bayesian Inference
In this work, a sparsity-driven observer (SDO) that can be employed to optimize hardware by use of a stochastic object model describing object sparsity is described and investigated.
Time-sync Video Tag Extraction Using Semantic Association Graph
Finally, we gain the weight of each word by combining Semantic Weight (SW) and Inverse Document Frequency (IDF).
Code-Switching for Enhancing NMT with Pre-Specified Translation
Leveraging user-provided translation to constrain NMT has practical significance.
Attention-based Convolutional Neural Network for Weakly Labeled Human Activities Recognition with Wearable Sensors
Unlike images or videos data which can be easily labeled by human being, sensor data annotation is a time-consuming process.
A cooperative game for automated learning of elasto-plasticity knowledge graphs and models with AI-guided experimentation
We introduce a multi-agent meta-modeling game to generate data, knowledge, and models that make predictions on constitutive responses of elasto-plastic materials.
Meta-modeling game for deriving theoretical-consistent, micro-structural-based traction-separation laws via deep reinforcement learning
This paper presents a new meta-modeling framework to employ deep reinforcement learning (DRL) to generate mechanical constitutive models for interfaces.
Ricean K-factor Estimation based on Channel Quality Indicator in OFDM Systems using Neural Network
Ricean channel model is widely used in wireless communications to characterize the channels with a line-of-sight path.
Expressway visibility estimation based on image entropy and piecewise stationary time series analysis
We assume fog and haze cause blurred images and that fog and haze can be considered as a piecewise stationary signal.
Scene Graph Generation from Objects, Phrases and Region Captions
Object detection, scene graph generation and region captioning, which are three scene understanding tasks at different semantic levels, are tied together: scene graphs are generated on top of objects detected in an image with their pairwise relationship predicted, while region captioning gives a language description of the objects, their attributes, relations, and other context information.
Ranked #2 on
Object Detection
on Visual Genome
Crafting GBD-Net for Object Detection
The effectiveness of GBD-Net is shown through experiments on three object detection datasets, ImageNet, Pascal VOC2007 and Microsoft COCO.
