Search Results for author:
Found 92 papers, 33 papers with code
Caption-Supervised Face Recognition: Training a State-of-the-Art Face Model without Manual Annotation
Captioned images are widely available on the web, while the captions often contain the names of the subjects in the images.
SemanticAdv: Generating Adversarial Examples via Attribute-conditioned Image Editing
Deep neural networks (DNNs) have achieved great successes in various vision applications due to their strong expressive power.
面向垂直领域的阅读理解数据增强方法(Method for reading comprehension data enhancement in vertical field)
阅读理解问答系统是利用语义理解等自然语言处理技术, 根据输入问题, 对非结构化文档数据进行分析, 生成一个答案, 具有很高的研究和应用价值。在垂直领域应用过程中, 阅读理解问答数据标注成本高且用户问题表达复杂多样, 使得阅读理解问答系统准确率低、鲁棒性差。针对这一问题, 本文提出一种面向垂直领域的阅读理解问答数据的增强方法, 该方法基于真实用户问题, 构造阅读理解训练数据, 一方面降低标注成本, 另一方面增加训练数据多样性, 提升模型的准确率和鲁棒性。本文用汽车领域数据对该方法进行实验验证, 其结果表明该方法对垂直领域阅读理解模型的准确率和鲁棒性均能有效提升。
RenderMe-360: A Large Digital Asset Library and Benchmarks Towards High-fidelity Head Avatars
It is a large-scale digital library for head avatars with three key attributes: 1) High Fidelity: all subjects are captured by 60 synchronized, high-resolution 2K cameras in 360 degrees.
NeRF$^\textbf{2}$: Neural Radio-Frequency Radiance Fields
Inspired by the great success of using a neural network to describe the optical field in computer vision, we propose a neural radio-frequency radiance field, NeRF$^\textbf{2}$, which represents a continuous volumetric scene function that makes sense of an RF signal's propagation.
Boundary-aware Backward-Compatible Representation via Adversarial Learning in Image Retrieval
For traditional model upgrades, the old model will not be replaced by the new one until the embeddings of all the images in the database are re-computed by the new model, which takes days or weeks for a large amount of data.
Towards Medical Artificial General Intelligence via Knowledge-Enhanced Multimodal Pretraining
In MOTOR, we combine two kinds of basic medical knowledge, i. e., general and specific knowledge, in a complementary manner to boost the general pretraining process.
Search-Map-Search: A Frame Selection Paradigm for Action Recognition
To overcome the limitations of existing methods, we propose a Search-Map-Search learning paradigm which combines the advantages of heuristic search and supervised learning to select the best combination of frames from a video as one entity.
ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model
However, the performance on more diverse motions remains unsatisfactory.
SynBody: Synthetic Dataset with Layered Human Models for 3D Human Perception and Modeling
Synthetic data has emerged as a promising source for 3D human research as it offers low-cost access to large-scale human datasets.
Zolly: Zoom Focal Length Correctly for Perspective-Distorted Human Mesh Reconstruction
As it is hard to calibrate single-view RGB images in the wild, existing 3D human mesh reconstruction (3DHMR) methods either use a constant large focal length or estimate one based on the background environment context, which can not tackle the problem of the torso, limb, hand or face distortion caused by perspective camera projection when the camera is close to the human body.
SHERF: Generalizable Human NeRF from a Single Image
To this end, we propose a bank of 3D-aware hierarchical features, including global, point-level, and pixel-aligned features, to facilitate informative encoding.
BEVHeight: A Robust Framework for Vision-based Roadside 3D Object Detection
In essence, instead of predicting the pixel-wise depth, we regress the height to the ground to achieve a distance-agnostic formulation to ease the optimization process of camera-only perception methods.
Ranked #1 on
3D Object Detection
on DAIR-V2X-I
On-Device Unsupervised Image Segmentation
What's more, for a larger size image in the BBBC005 dataset, the existing approach cannot be accommodated to Raspberry PI due to out of memory; on the other hand, SegHDC can obtain segmentation results within 3 minutes while achieving a 0. 9587 IoU score.
Web Photo Source Identification based on Neural Enhanced Camera Fingerprint
With the growing popularity of smartphone photography in recent years, web photos play an increasingly important role in all walks of life.
Dynamic Storyboard Generation in an Engine-based Virtual Environment for Video Production
Amateurs working on mini-films and short-form videos usually spend lots of time and effort on the multi-round complicated process of setting and adjusting scenes, plots, and cameras to deliver satisfying video shots.
OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generation
Recent advances in modeling 3D objects mostly rely on synthetic datasets due to the lack of large-scale realscanned 3D databases.
Label-Efficient Interactive Time-Series Anomaly Detection
Time-series anomaly detection is an important task and has been widely applied in the industry.
Development of A Real-time POCUS Image Quality Assessment and Acquisition Guidance System
Point-of-care ultrasound (POCUS) is one of the most commonly applied tools for cardiac function imaging in the clinical routine of the emergency department and pediatric intensive care unit.
TransVCL: Attention-enhanced Video Copy Localization Network with Flexible Supervision
Previous methods typically start from frame-to-frame similarity matrix generated by cosine similarity between frame-level features of the input video pair, and then detect and refine the boundaries of copied segments on similarity matrix under temporal constraints.
DCVQE: A Hierarchical Transformer for Video Quality Assessment
Inspired by our observation on the actions of human annotation, we put forward a Divide and Conquer Video Quality Estimator (DCVQE) for NR-VQA.
A Keypoint Based Enhancement Method for Audio Driven Free View Talking Head Synthesis
Then we used keypoint decomposition to extract video synthesis controlling parameters from the backend output and the source image.
Benchmarking and Analyzing 3D Human Pose and Shape Estimation Beyond Algorithms
Experiments with 10 backbones, ranging from CNNs to transformers, show the knowledge learnt from a proximity task is readily transferable to human mesh recovery.
Hierarchical Temporal Transformer for 3D Hand Pose Estimation and Action Recognition from Egocentric RGB Videos
Understanding dynamic hand motions and actions from egocentric RGB videos is a fundamental yet challenging task due to self-occlusion and ambiguity.
CAMO-MOT: Combined Appearance-Motion Optimization for 3D Multi-Object Tracking with Camera-LiDAR Fusion
As such, we propose a novel camera-LiDAR fusion 3D MOT framework based on the Combined Appearance-Motion Optimization (CAMO-MOT), which uses both camera and LiDAR data and significantly reduces tracking failures caused by occlusion and false detection.
MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model
Instead of a deterministic language-motion mapping, MotionDiffuse generates motions through a series of denoising steps in which variations are injected.
Ranked #6 on
Motion Synthesis
on KIT Motion-Language
Federated Self-Supervised Contrastive Learning and Masked Autoencoder for Dermatological Disease Diagnosis
Self-supervised learning (SSL) methods, contrastive learning (CL) and masked autoencoders (MAE), can leverage the unlabeled data to pre-train models, followed by fine-tuning with limited labels.
Mix-Teaching: A Simple, Unified and Effective Semi-Supervised Learning Framework for Monocular 3D Object Detection
Besides, by leveraging full training set and the additional 48K raw images of KITTI, it can further improve the MonoFlex by +4. 65% improvement on AP@0. 7 for car detection, reaching 18. 54% AP@0. 7, which ranks the 1st place among all monocular based methods on KITTI test leaderboard.
Not All Models Are Equal: Predicting Model Transferability in a Self-challenging Fisher Space
It is challenging because the ground-truth model ranking for each task can only be generated by fine-tuning the pre-trained models on the target dataset, which is brute-force and computationally expensive.
Learn to Predict How Humans Manipulate Large-sized Objects from Interactive Motions
We also observe that an object's intrinsic physical properties are useful for the object motion prediction, and thus design a set of object dynamic descriptors to encode such intrinsic properties.
RT-DNAS: Real-time Constrained Differentiable Neural Architecture Search for 3D Cardiac Cine MRI Segmentation
Accurately segmenting temporal frames of cine magnetic resonance imaging (MRI) is a crucial step in various real-time MRI guided cardiac interventions.
Data Imputation for Multivariate Time Series Sensor Data with Large Gaps of Missing Data
Imputation of missing sensor-collected data is often an important step prior to machine learning and statistical data analysis.
AvatarCLIP: Zero-Shot Text-Driven Generation and Animation of 3D Avatars
Our key insight is to take advantage of the powerful vision-language model CLIP for supervising neural human generation, in terms of 3D geometry, texture and animation.
HuMMan: Multi-Modal 4D Human Dataset for Versatile Sensing and Modeling
4D human sensing and modeling are fundamental tasks in vision and graphics with numerous applications.
Practical Stereo Matching via Cascaded Recurrent Network with Adaptive Correlation
With the advent of convolutional neural networks, stereo matching algorithms have recently gained tremendous progress.
DeciWatch: A Simple Baseline for 10x Efficient 2D and 3D Pose Estimation
This paper proposes a simple baseline framework for video-based 2D/3D human pose estimation that can achieve 10 times efficiency improvement over existing works without any performance degradation, named DeciWatch.
Ranked #1 on
2D Human Pose Estimation
on JHMDB (2D poses only)
A Large-scale Comprehensive Dataset and Copy-overlap Aware Evaluation Protocol for Segment-level Video Copy Detection
In this paper, we introduce VCSL (Video Copy Segment Localization), a new comprehensive segment-level annotated video copy dataset.
The Larger The Fairer? Small Neural Networks Can Achieve Fairness for Edge Devices
Results show that FaHaNa can identify a series of neural networks with higher fairness and accuracy on a dermatology dataset.
Visual-Tactile Sensing for Real-time Liquid Volume Estimation in Grasping
We propose a deep visuo-tactile model for realtime estimation of the liquid inside a deformable container in a proprioceptive way. We fuse two sensory modalities, i. e., the raw visual inputs from the RGB camera and the tactile cues from our specific tactile sensor without any extra sensor calibrations. The robotic system is well controlled and adjusted based on the estimation model in real time.
Federated Contrastive Learning for Dermatological Disease Diagnosis via On-device Learning
The recently developed self-supervised learning approach, contrastive learning (CL), can leverage the unlabeled data to pre-train a model, after which the model is fine-tuned on limited labeled data for dermatological disease diagnosis.
Automated Architecture Search for Brain-inspired Hyperdimensional Computing
On the Clintox dataset, which tries to learn features from developed drugs that passed/failed clinical trials for toxicity reasons, the searched HDC architecture obtains the state-of-the-art ROC-AUC scores, which are 0. 80% higher than the manually designed HDC and 9. 75% higher than conventional neural networks.
SkiM: Skipping Memory LSTM for Low-Latency Real-Time Continuous Speech Separation
We adopt the time-domain speech separation method and the recently proposed Graph-PIT to build a super low-latency online speech separation model, which is very important for the real application.
SmoothNet: A Plug-and-Play Network for Refining Human Poses in Videos
With a simple yet effective motion-aware fully-connected network, SmoothNet improves the temporal smoothness of existing pose estimators significantly and enhances the estimation accuracy of those challenging frames as a side-effect.
SimiGrad: Fine-Grained Adaptive Batching for Large Scale Training using Gradient Similarity Measurement
In this paper, we propose a fully automated and lightweight adaptive batching methodology to enable fine-grained batch size adaption (e. g., at a mini-batch level) that can achieve state-of-the-art performance with record breaking batch sizes.
BSC: Block-based Stochastic Computing to Enable Accurate and Efficient TinyML
Unlike ML on the edge, TinyML with a limited energy supply has higher demands on low-power execution.
Dense Representative Tooth Landmark/axis Detection Network on 3D Model
Results show that our method can produce tooth landmarks with high accuracy.
Robust Event Classification Using Imperfect Real-world PMU Data
Specifically, the data preprocessing step addresses the data quality issues of PMU measurements (e. g., bad data and missing data); in the fine-grained event data extraction step, a model-free event detection method is developed to accurately localize the events from the inaccurate event timestamps in the event logs; and the feature engineering step constructs the event features based on the patterns of different event types, in order to improve the performance and the interpretability of the event classifiers.
Detecting Gender Bias in Transformer-based Models: A Case Study on BERT
In this paper, we propose a novel gender bias detection method by utilizing attention map for transformer-based models.
Playing for 3D Human Recovery
Specifically, we contribute GTA-Human, a large-scale 3D human dataset generated with the GTA-V game engine, featuring a highly diverse set of subjects, actions, and scenarios.
iShape: A First Step Towards Irregular Shape Instance Segmentation
In this paper, we introduce a brand new dataset to promote the study of instance segmentation for objects with irregular shapes.
Ranked #1 on
Instance Segmentation
on iShape
Can Noise on Qubits Be Learned in Quantum Neural Network? A Case Study on QuantumFlow
Specifically, this paper targets quantum neural network (QNN), and proposes to learn the errors in the training phase, so that the identified QNN model can be resilient to noise.
Learning Skeletal Graph Neural Networks for Hard 3D Pose Estimation
While the average prediction accuracy has been improved significantly over the years, the performance on hard poses with depth ambiguity, self-occlusion, and complex or rare poses is still far from satisfactory.
Ranked #17 on
Skeleton Based Action Recognition
on NTU RGB+D
(using extra training data)
Distributed Attention for Grounded Image Captioning
We study the problem of weakly supervised grounded image captioning.
Geometry Uncertainty Projection Network for Monocular 3D Object Detection
In this paper, we propose a Geometry Uncertainty Projection Network (GUP Net) to tackle the error amplification problem at both inference and training stages.
3D Object Detection From Monocular Images
Depth Estimation
+2
DISP6D: Disentangled Implicit Shape and Pose Learning for Scalable 6D Pose Estimation
Scalable 6D pose estimation for rigid objects from RGB images aims at handling multiple objects and generalizing to novel objects.
IPS300+: a Challenging Multimodal Dataset for Intersection Perception System
Through an IPS (Intersection Perception System) installed at the diagonal of the intersection, this paper proposes a high-quality multimodal dataset for the intersection perception task.
Lite-FPN for Keypoint-based Monocular 3D Object Detection
3D object detection with a single image is an essential and challenging task for autonomous driving.
Refer-it-in-RGBD: A Bottom-up Approach for 3D Visual Grounding in RGBD Images
Grounding referring expressions in RGBD image has been an emerging field.
The Age of Correlated Features in Supervised Learning based Forecasting
In these applications, a neural network is trained to predict a time-varying target (e. g., solar power), based on multiple correlated features (e. g., temperature, humidity, and cloud coverage).
Solving the Travelling Thief Problem based on Item Selection Weight and Reverse Order Allocation
The Travelling Thief Problem (TTP) is a challenging combinatorial optimization problem that attracts many scholars.
Edge Computing Assisted Autonomous Flight for UAV: Synergies between Vision and Communications
By proposing a framework of Edge Computing Assisted Autonomous Flight (ECAAF), we illustrate that vision and communications can interact with and assist each other with the aid of edge computing and offloading, and further speed up the UAV mission completion.
Edge-computing
Trajectory Planning
Networking and Internet Architecture
Robotics
Systems and Control
Systems and Control
CoEdge: Cooperative DNN Inference with Adaptive Workload Partitioning over Heterogeneous Edge Devices
CoEdge utilizes available computation and communication resources at the edge and dynamically partitions the DNN inference workload adaptive to devices' computing capabilities and network conditions.
Event Cause Analysis in Distribution Networks using Synchro Waveform Measurements
This paper presents a machine learning method for event cause analysis to enhance situational awareness in distribution networks.
Deep Neural Network based Wide-Area Event Classification in Power Systems
This paper presents a wide-area event classification in transmission power grids.
E-Tree Learning: A Novel Decentralized Model Learning Framework for Edge AI
In this paper, we propose a novel decentralized model learning approach, namely E-Tree, which makes use of a well-designed tree structure imposed on the edge devices.
Mapping in a cycle: Sinkhorn regularized unsupervised learning for point cloud shapes
We propose an unsupervised learning framework with the pretext task of finding dense correspondences between point cloud shapes from the same category based on the cycle-consistency formulation.
Learn to Propagate Reliably on Noisy Affinity Graphs
Recent works have shown that exploiting unlabeled data through label propagation can substantially reduce the labeling cost, which has been a critical issue in developing visual recognition models.
Standing on the Shoulders of Giants: Hardware and Neural Architecture Co-Search with Hot Start
To tackle this issue, HotNAS builds a chain of tools to design hardware to support compression, based on which a global optimizer is developed to automatically co-search all the involved search spaces.
Learning to Cluster Faces via Confidence and Connectivity Estimation
With the vertex confidence and edge connectivity, we can naturally organize more relevant vertices on the affinity graph and group them into clusters.
Co-Exploration of Neural Architectures and Heterogeneous ASIC Accelerator Designs Targeting Multiple Tasks
Neural Architecture Search (NAS) has demonstrated its power on various AI accelerating platforms such as Field Programmable Gate Arrays (FPGAs) and Graphic Processing Units (GPUs).
Deep Human Answer Understanding for Natural Reverse QA
This study focuses on a reverse question answering (QA) procedure, in which machines proactively raise questions and humans supply the answers.
Blockchain for Future Smart Grid: A Comprehensive Survey
In this paper, we aim to provide a comprehensive survey on application of blockchain in smart grid.
Cryptography and Security Distributed, Parallel, and Cluster Computing Networking and Internet Architecture Social and Information Networks Systems and Control Systems and Control
Device-Circuit-Architecture Co-Exploration for Computing-in-Memory Neural Accelerators
In this paper, we are the first to bring the computing-in-memory architecture, which can easily transcend the memory wall, to interplay with the neural architecture search, aiming to find the most efficient neural architectures with high network accuracy and maximized hardware efficiency.
Practical Low Latency Proof of Work Consensus
Bitcoin is the first fully-decentralized permissionless blockchain protocol to achieve a high level of security, but at the expense of poor throughput and latency.
Distributed, Parallel, and Cluster Computing Cryptography and Security Networking and Internet Architecture
Hardware/Software Co-Exploration of Neural Architectures
We propose a novel hardware and software co-exploration framework for efficient neural architecture search (NAS).
A Pvalue-guided Anomaly Detection Approach Combining Multiple Heterogeneous Log Parser Algorithms on IIoT Systems
In this paper, we use blockchain to prevent logs from being tampered with and propose a pvalue-guided anomaly detection approach.
Cryptography and Security
Sparse Solutions of a Class of Constrained Optimization Problems
Specifically, without any condition on the matrix $A$, we provide upper bounds in cardinality and infinity norm for the optimal solutions, and show that all optimal solutions must be on the boundary of the feasible set when $0<p<1$.
SemanticAdv: Generating Adversarial Examples via Attribute-conditional Image Editing
In this paper, we aim to explore the impact of semantic manipulation on DNNs predictions by manipulating the semantic attributes of images and generate "unrestricted adversarial examples".
AUTOHOME-ORCA at SemEval-2019 Task 8: Application of BERT for Fact-Checking in Community Forums
In order to address this task, we propose a system based on the BERT model with meta information of questions.
Adaptive Intelligent Secondary Control of Microgrids Using a Biologically-Inspired Reinforcement Learning
In this paper, a biologically-inspired adaptive intelligent secondary controller is developed for microgrids to tackle system dynamics uncertainties, faults, and/or disturbances.
Learning to Cluster Faces on an Affinity Graph
Face recognition sees remarkable progress in recent years, and its performance has reached a very high level.
Accuracy vs. Efficiency: Achieving Both through FPGA-Implementation Aware Neural Architecture Search
In addition, with a performance abstraction model to analyze the latency of neural architectures without training, our framework can quickly prune architectures that do not satisfy the specification, leading to higher efficiency.
RPC: A Large-Scale Retail Product Checkout Dataset
The main challenge of this problem comes from the large scale and the fine-grained nature of the product categories as well as the difficulty for collecting training images that reflect the realistic checkout scenarios due to continuous update of the products.
A Fast Globally Linearly Convergent Algorithm for the Computation of Wasserstein Barycenters
When the support points of the barycenter are pre-specified, this problem can be modeled as a linear programming (LP) problem whose size can be extremely large.
Feature Fusion through Multitask CNN for Large-scale Remote Sensing Image Segmentation
In recent years, Fully Convolutional Networks (FCN) has been widely used in various semantic segmentation tasks, including multi-modal remote sensing imagery.
TreeSegNet: Adaptive Tree CNNs for Subdecimeter Aerial Image Segmentation
For the task of subdecimeter aerial imagery segmentation, fine-grained semantic segmentation results are usually difficult to obtain because of complex remote sensing content and optical conditions.
Accelerated Training for Massive Classification via Dynamic Class Selection
Massive classification, a classification task defined over a vast number of classes (hundreds of thousands or even millions), has become an essential part of many real-world systems, such as face recognition.
Proximal Gradient Method with Extrapolation and Line Search for a Class of Nonconvex and Nonsmooth Problems
To solve this class of problems, we propose a proximal gradient method with extrapolation and line search (PGels).
DeepUNet: A Deep Fully Convolutional Network for Pixel-level Sea-Land Segmentation
Semantic segmentation is a fundamental research in remote sensing image processing.
On Scalable Inference with Stochastic Gradient Descent
In many applications involving large dataset or online updating, stochastic gradient descent (SGD) provides a scalable way to compute parameter estimates and has gained increasing popularity due to its numerical convenience and memory efficiency.
A Non-monotone Alternating Updating Method for A Class of Matrix Factorization Problems
Finally, we conduct some numerical experiments using real datasets to compare our method with some existing efficient methods for non-negative matrix factorization and matrix completion.
Minimum $n$-Rank Approximation via Iterative Hard Thresholding
Additionally, combining an effective heuristic for determining $n$-rank, we can also apply the proposed algorithm to solve MnRA when $n$-rank is unknown in advance.
