Search Results for author:
Found 89 papers, 17 papers with code
Rethinking the Defocus Blur Detection Problem and A Real-Time Deep DBD Model
In this work, we propose novel perspectives on the DBD problem and design convenient approach to build a real-time cost-effective DBD model.
Learning and Verification of Task Structure in Instructional Videos
We introduce a new pre-trained video model, VideoTaskformer, focused on representing the semantics and structure of instructional videos.
Channel-Aware Distillation Transformer for Depth Estimation on Nano Drones
Autonomous navigation of drones using computer vision has achieved promising performance.
Que2Engage: Embedding-based Retrieval for Relevant and Engaging Products at Facebook Marketplace
In this paper we presents Que2Engage, a search EBR system built towards bridging the gap between retrieval and ranking for end-to-end optimizations.
HSTFormer: Hierarchical Spatial-Temporal Transformers for 3D Human Pose Estimation
To mitigate this issue, we propose Hierarchical Spatial-Temporal transFormers (HSTFormer) to capture multi-level joints' spatial-temporal correlations from local to global gradually for accurate 3D HPE.
Artificial intelligence for diagnosing and predicting survival of patients with renal cell carcinoma: Retrospective multi-center study
The OSrisk for the prediction of 5-year survival status achieved AUC of 0. 784 (0. 746-0. 819) in the TCGA cohort, which was further verified in the independent General cohort and the CPTAC cohort, with AUC of 0. 774 (0. 723-0. 820) and 0. 702 (0. 632-0. 765), respectively.
Performance Analysis and Enhancement of Beamforming Training in 802.11ad
Since the derived BF training efficiency is an implicit function, to reveal the relationship between system parameters and BF training performance, we also derive an approximate expression of BF training efficiency.
Beef up mmWave Dense Cellular Networks with D2D-Assisted Cooperative Edge Caching
In this paper, we propose a device-to-device (D2D) assisted cooperative edge caching (DCEC) policy for millimeter (mmWave) dense networks, which cooperatively utilizes the cache resource of users and SBSs in proximity.
RIATIG: Reliable and Imperceptible Adversarial Text-to-Image Generation With Natural Prompts
The field of text-to-image generation has made remarkable strides in creating high-fidelity and photorealistic images.
Revisiting the Stack-Based Inverse Tone Mapping
In this paper, we revisit the stack-based ITM approaches and propose a novel method to reconstruct HDR radiance from a single image, which only needs to estimate two exposure images.
SlowLiDAR: Increasing the Latency of LiDAR-Based Detection Using Adversarial Examples
LiDAR-based perception is a central component of autonomous driving, playing a key role in tasks such as vehicle localization and obstacle detection.
Cost-Effective Two-Stage Network Slicing for Edge-Cloud Orchestrated Vehicular Networks
Since the problem is NP-hard due to coupled network planning and network operation stages, we develop a Two timescAle netWork Slicing (TAWS) algorithm by collaboratively integrating reinforcement learning (RL) and optimization methods, which can jointly make network planning and operation decisions.
CGOF++: Controllable 3D Face Synthesis with Conditional Generative Occupancy Fields
Capitalizing on the recent advances in image generation models, existing controllable face image synthesis methods are able to generate high-fidelity images with some levels of controllability, e. g., controlling the shapes, expressions, textures, and poses of the generated face images.
Tell Me What Happened: Unifying Text-guided Video Completion via Multimodal Masked Video Generation
Inspired by this, we introduce a novel task, text-guided video completion (TVC), which requests the model to generate a video from partial frames guided by an instruction.
Ranked #3 on
Video Prediction
on BAIR Robot Pushing
Lite-Mono: A Lightweight CNN and Transformer Architecture for Self-Supervised Monocular Depth Estimation
Self-supervised monocular depth estimation that does not require ground truth for training has attracted attention in recent years.
Prior-enhanced Temporal Action Localization using Subject-aware Spatial Attention
Temporal action localization (TAL) aims to detect the boundary and identify the class of each action instance in a long untrimmed video.
FaD-VLP: Fashion Vision-and-Language Pre-training towards Unified Retrieval and Captioning
Additionally, these works have mainly been restricted to multimodal understanding tasks.
Reward Delay Attacks on Deep Reinforcement Learning
We find that this mitigation remains insufficient to ensure robustness to attacks that delay, but preserve the order, of rewards.
Accurate and Robust Lesion RECIST Diameter Prediction and Segmentation with Transformers
To the best of our knowledge, it is the first time to use keypoint regression for RECIST diameter prediction.
PieTrack: An MOT solution based on synthetic data training and self-supervised domain adaptation
In order to cope with the increasing demand for labeling data and privacy issues with human detection, synthetic data has been used as a substitute and showing promising results in human detection and tracking tasks.
Controllable 3D Face Synthesis with Conditional Generative Occupancy Fields
Capitalizing on the recent advances in image generation models, existing controllable face image synthesis methods are able to generate high-fidelity images with some levels of controllability, e. g., controlling the shapes, expressions, textures, and poses of the generated face images.
FadMan: Federated Anomaly Detection across Multiple Attributed Networks
The proposed algorithm FadMan is a vertical federated learning framework for public node aligned with many private nodes of different features, and is validated on two tasks correlated anomaly detection on multiple attributed networks and anomaly detection on an attributeless network using five real-world datasets.
Stability of China's Stock Market: Measure and Forecast by Ricci Curvature on Network
As far as we know, this is the first paper to apply Ricci curvature to forecast the systemic stability of domestic stock market, and our results show that Ricci curvature has good explanatory power for the market stability and can be a good indicator to judge the future risk and volatility of the domestic market.
D3PG: Dirichlet DDPG for Task Partitioning and Offloading With Constrained Hybrid Action Space in Mobile-Edge Computing
Mobile-edge computing (MEC) has been regarded as a promising paradigm to reduce service latency for data processing in the Internet of Things (IoT) by provisioning computing resources at the network edges.
Mobile Wireless Rechargeable UAV Networks: Challenges and Solutions
Unmanned aerial vehicles (UAVs) can help facilitate cost-effective and flexible service provisioning in future smart cities.
Hierarchical BERT for Medical Document Understanding
Other than the ICD code assignment, we conduct a variety of other NLU tasks on a large commercial dataset named as TrialTrove, to showcase MDBERT's strength in delivering different levels of semantics.
LoopITR: Combining Dual and Cross Encoder Architectures for Image-Text Retrieval
In this work, we propose LoopITR, which combines them in the same network for joint learning.
Towards Tailored Models on Private AIoT Devices: Federated Direct Neural Architecture Search
To further adapt to both various data distributions and different types of devices with heterogeneous embedded hardware platforms, inspired by meta-learning, a Cluster Federated Direct Neural Architecture Search (CFDNAS) framework is proposed to achieve device-aware NAS, in the sense that each device can learn a tailored deep learning model for its particular data distribution and hardware constraint.
CommerceMM: Large-Scale Commerce MultiModal Representation Learning with Omni Retrieval
We introduce CommerceMM - a multimodal model capable of providing a diverse and granular understanding of commerce topics associated to the given piece of content (image, text, image+text), and having the capability to generalize to a wide range of tasks, including Multimodal Categorization, Image-Text Retrieval, Query-to-Product Retrieval, Image-to-Product Retrieval, etc.
A Knowledge-Based Decision Support System for In Vitro Fertilization Treatment
To improve the IVF success rate, we propose a knowledge-based decision support system that can provide medical advice on the treatment protocol and medication adjustment for each patient visit during IVF treatment cycle.
Smart Director: An Event-Driven Directing System for Live Broadcasting
To our best knowledge, our system is the first end-to-end automated directing system for multi-camera sports broadcasting, completely driven by the semantic understanding of sports events.
Counteracting Dark Web Text-Based CAPTCHA with Generative Adversarial Learning for Proactive Cyber Threat Intelligence
In this study, we propose a novel framework for automated breaking of dark web CAPTCHA to facilitate dark web data collection.
Joint Task Offloading and Resource Allocation for IoT Edge Computing with Sequential Task Dependency
To solve this challenging problem, we decompose it as a one-dimensional search of task offloading decision problem and a non-convex optimization problem with task offloading decision given.
PROVES: Establishing Image Provenance using Semantic Signatures
Modern AI tools, such as generative adversarial networks, have transformed our ability to create and modify visual data with photorealistic results.
Learning to Solve an Order Fulfillment Problem in Milliseconds with Edge-Feature-Embedded Graph Attention
Such a problem is computationally hard to address by exact mathematical programming methods.
Frequency-Constrained Resilient Scheduling of Microgrid: A Distributionally Robust Approach
In order to prevent the potential frequency instability due to the high Power Electronics (PE) penetration under an unintentional islanding event, this paper presents a novel microgrid scheduling model which explicitly models the system frequency dynamics as well as the long/short term uncertainty associated with renewable energy resources and load.
Enabling Long-Term Cooperation in Cross-Silo Federated Learning: A Repeated Game Perspective
We show that enforced by a punishment strategy, such a cooperative strategy is a subgame perfect Nash equilibrium (SPNE) of the infinitely repeated game, under which some clients who are free riders at the NE of the stage game choose to be (partial) contributors.
Deriving Autism Spectrum Disorder Functional Networks from RS-FMRI Data using Group ICA and Dictionary Learning
Fourth, we generate three corresponding masks based on the 20 selected ROIs from group ICA, the 20 ROIs selected from dictionary learning, and the 40 combined ROIs selected from both.
AI-Native Network Slicing for 6G Networks
Then, network slicing solutions are studied to support emerging AI services by constructing AI instances and performing efficient resource management, i. e., slicing for AI.
Connecting What to Say With Where to Look by Modeling Human Attention Traces
Learning the grounding of each word is challenging, due to noise in the human-provided traces and the presence of words that cannot be meaningfully visually grounded.
Topology Learning Aided False Data Injection Attack without Prior Topology Information
False Data Injection (FDI) attacks against powersystem state estimation are a growing concern for operators. Previously, most works on FDI attacks have been performedunder the assumption of the attacker having full knowledge ofthe underlying system without clear justification.
Range decreasing group homomorphisms and holomorphic maps between generalized loop spaces
$\mathcal{F}^{0}(V, M)$ be the component of $\mathcal{F}(V, \mathcal{G})$ resp.
Complex Variables Functional Analysis Representation Theory 58D15, 46T25, 22E66, 58C10, 32H02
Newtonalized Orthogonal Matching Pursuit for Linear Frequency Modulated Pulse Frequency Agile Radar
The linear frequency modulated (LFM) frequency agile radar (FAR) can synthesize a wide signal bandwidth through coherent processing while keeping the bandwidth of each pulse narrow.
Binary Black-box Evasion Attacks Against Deep Learning-based Static Malware Detectors with Adversarial Byte-Level Language Model
Recently, deep learning-based static anti-malware detectors have achieved success in identifying unseen attacks without requiring feature engineering and dynamic analysis.
Joint Task Offloading and Resource Allocation for IoT Edge Computing with Sequential Task Dependency
To solve this challenging problem, we decompose it as a one-dimensional search of task offloading decision problem and a non-convex optimization problem with task offloading decision given.
Edge-computing
Information Theory
Information Theory
DeepSlicing: Deep Reinforcement Learning Assisted Resource Allocation for Network Slicing
Network slicing enables multiple virtual networks run on the same physical infrastructure to support various use cases in 5G and beyond.
Computation Offloading in Beyond 5G Networks: A Distributed Learning Framework and Applications
Facing the trend of merging wireless communications and multi-access edge computing (MEC), this article studies computation offloading in the beyond fifth-generation networks.
Energy and Information Management of Electric Vehicular Network: A Survey
In this paper, we provide a comprehensive survey on the deployment and management of EVN considering all three aspects of energy flow, data communication, and computation.
Robust Visual Object Tracking with Two-Stream Residual Convolutional Networks
Inspired by the human "visual tracking" capability which leverages motion cues to distinguish the target from the background, we propose a Two-Stream Residual Convolutional Network (TS-RCN) for visual tracking, which successfully exploits both appearance and motion features for model update.
Sparse Oblique Decision Tree for Power System Security Rules Extraction and Embedding
Data-driven techniques provide a promising way to identify security rules that can be embedded in economic dispatch model to keep power system operating states secure.
A Spatially Constrained Deep Convolutional Neural Network for Nerve Fiber Segmentation in Corneal Confocal Microscopic Images using Inaccurate Annotations
Most state-of-the-art deep learning methods require a large number of accurately annotated examples for model training.
DeepEDN: A Deep Learning-based Image Encryption and Decryption Network for Internet of Medical Things
Specifically, in DeepEDN, the Cycle-Generative Adversarial Network (Cycle-GAN) is employed as the main learning network to transfer the medical image from its original domain into the target domain.
3D Aggregated Faster R-CNN for General Lesion Detection
This classifier branch is equipped with Feature Aggregation and Local Magnification Layers to enhance the classifier branch.
Enjoy the Untrusted Cloud: A Secure, Scalable and Efficient SQL-like Query Framework for Outsourcing Data
On one hand, such work lacks of supporting scalable access control over multiple data users.
Cryptography and Security Databases Distributed, Parallel, and Cluster Computing
Mini Lesions Detection on Diabetic Retinopathy Images via Large Scale CNN Features
We analyze the lesion-vs-image scale carefully and propose a large-size feature pyramid network (LFPN) to preserve more image details for mini lesion instance detection.
Bounding Regression Errors in Data-driven Power Grid Steady-state Models
Results identify how the bounds decrease with additional power grid physical knowledge or more training data.
Embedding Lithium-ion Battery Scrapping Criterion and Degradation Model in Optimal Operation of Peak-shaving Energy Storage
A new battery life model with scrapping parameters is then derived using this criterion.
Fast mmwave Beam Alignment via Correlated Bandit Learning
Beam alignment (BA) is to ensure the transmitter and receiver beams are accurately aligned to establish a reliable communication link in millimeter-wave (mmwave) systems.
AFP-Net: Realtime Anchor-Free Polyp Detection in Colonoscopy
Though challenging, with the great advances in object detection techniques, automated polyp detection still demonstrates a great potential in reducing the false negative rate while maintaining a high precision.
3D Anchor-Free Lesion Detector on Computed Tomography Scans
The anchor mechanism is removed and lesions are formalized as single keypoints.
Dynamic Kernel Distillation for Efficient Pose Estimation in Videos
Existing video-based human pose estimation methods extensively apply large networks onto every frame in the video to localize body joints, which suffer high computational cost and hardly meet the low-latency requirement in realistic applications.
Ranked #3 on
2D Human Pose Estimation
on JHMDB (2D poses only)
Weakly Supervised Body Part Segmentation with Pose based Part Priors
The core idea is first converting the sparse weak labels such as keypoints to the initial estimate of body part masks, and then iteratively refine the part mask predictions.
Gridless Multisnapshot Variational Line Spectral Estimation from Coarsely Quantized Samples
Due to the increasing demand for low power and higher sampling rates, low resolution quantization for data acquisition has drawn great attention recently.
Finding Needles in a Moving Haystack: Prioritizing Alerts with Adversarial Reinforcement Learning
We then use these in a double-oracle framework to obtain an approximate equilibrium of the game, which in turn yields a robust stochastic policy for the defender.
Online Learning for Supervised Dimension Reduction
The purpose of this paper is to propose new online learning approaches for supervised dimension reduction.
Context-Aware Zero-Shot Recognition
We present a novel problem setting in zero-shot learning, zero-shot object recognition and detection in the context.
Laplace Landmark Localization
Our method claims state-of-the-art on all of the 300W benchmarks and ranks second-to-best on the Annotated Facial Landmarks in the Wild (AFLW) dataset.
Ranked #4 on
Face Alignment
on AFLW-19
(NME_box (%, Full) metric)
Multi-view to Novel view: Synthesizing Novel Views with Self-Learned Confidence
We address the task of multi-view novel view synthesis, where we are interested in synthesizing a target image with an arbitrary camera pose from given source images.
Ranked #1 on
Novel View Synthesis
on KITTI Novel View Synthesis
Visual Attention Model for Name Tagging in Multimodal Social Media
Everyday billions of multimodal posts containing both images and text are shared in social media sites such as Snapchat, Twitter or Instagram.
Overlapping Sliced Inverse Regression for Dimension Reduction
The new algorithm, called overlapping sliced inverse regression (OSIR), is able to estimate the effective dimension reduction space and determine the number of effective factors more accurately.
An Aggressive Genetic Programming Approach for Searching Neural Network Structure Under Computational Constraints
In this paper, we study how to design a genetic programming approach for optimizing the structure of a CNN for a given task under limited computational resources yet without imposing strong restrictions on the search space.
Screening of Fungi for the Application of Self-Healing Concrete
Therefore, a screening of different species of fungi has been conducted in this study.
NITE: A Neural Inductive Teaching Framework for Domain Specific NER
In domain-specific NER, due to insufficient labeled training data, deep models usually fail to behave normally.
Improving Robustness of ML Classifiers against Realizable Evasion Attacks Using Conserved Features
A conventional approach to evaluate ML robustness to such attacks, as well as to design robust ML, is by considering simplified feature-space models of attacks, where the attacker changes ML features directly to effect evasion, while minimizing or constraining the magnitude of this change.
Interactions of Fungi with Concrete: Significant Importance for Bio-Based Self-Healing Concrete
The goal of this study is to explore a new self-healing concept in which fungi are used as a self-healing agent to promote calcium mineral precipitation to fill the cracks in concrete.
Deep Reinforcement Learning-based Image Captioning with Embedding Reward
The policy network serves as a local guidance by providing the confidence of predicting the next word according to the current state.
AutoScaler: Scale-Attention Networks for Visual Correspondence
We propose AutoScaler, a scale-attention network to explicitly optimize this trade-off in visual correspondence tasks.
A Hierarchical Distributed Processing Framework for Big Image Data
The proposed ICP framework consists of two mechanisms, i. e. SICP (Static ICP) and DICP (Dynamic ICP).
Fine-grained pose prediction, normalization, and recognition
Pose variation and subtle differences in appearance are key challenges to fine-grained classification.
Compact Bilinear Pooling
Bilinear models has been shown to achieve impressive performance on a wide range of visual tasks, such as semantic segmentation, fine grained recognition and face recognition.
Sparse learning of maximum likelihood model for optimization of complex loss function
In this paper, we study the problem of optimizing the complex performance measure directly to obtain a predictive model.
Beyond Frontal Faces: Improving Person Recognition Using Multiple Cues
We explore the task of recognizing peoples' identities in photo albums in an unconstrained setting.
Deep Domain Confusion: Maximizing for Domain Invariance
Recent reports suggest that a generic supervised deep CNN model trained on a large-scale dataset reduces, but does not remove, dataset bias on a standard benchmark.
Ranked #6 on
Domain Adaptation
on Office-Caltech
Do Convnets Learn Correspondence?
Convolutional neural nets (convnets) trained from massive labeled datasets have substantially improved the state-of-the-art in image classification and object detection.
Ranked #4 on
Keypoint Detection
on Pascal3D+
Part-based R-CNNs for Fine-grained Category Detection
Semantic part localization can facilitate fine-grained categorization by explicitly isolating subtle appearance differences associated with specific object parts.
Ranked #62 on
Fine-Grained Image Classification
on CUB-200-2011
Deformable Part Descriptors for Fine-grained Recognition and Attribute Prediction
Recognizing objects in fine-grained domains can be extremely challenging due to the subtle differences between subcategories.
Ranked #25 on
Fine-Grained Image Classification
on CUB-200-2011
PANDA: Pose Aligned Networks for Deep Attribute Modeling
We propose a method for inferring human attributes (such as gender, hair style, clothes style, expression, action) from images of people under large variation of viewpoint, pose, appearance, articulation and occlusion.
DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
We evaluate whether features extracted from the activation of a deep convolutional network trained in a fully supervised fashion on a large, fixed set of object recognition tasks can be re-purposed to novel generic tasks.
