Search Results for author:
Found 107 papers, 22 papers with code
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.
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.
Ranked #7 on
Facial Attribute Classification
on LFWA
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
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 #63 on
Fine-Grained Image Classification
on CUB-200-2011
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+
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
Beyond Frontal Faces: Improving Person Recognition Using Multiple Cues
We explore the task of recognizing peoples' identities in photo albums in an unconstrained setting.
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.
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.
Fine-grained pose prediction, normalization, and recognition
Pose variation and subtle differences in appearance are key challenges to fine-grained classification.
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).
AutoScaler: Scale-Attention Networks for Visual Correspondence
We propose AutoScaler, a scale-attention network to explicitly optimize this trade-off in visual correspondence tasks.
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.
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.
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.
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.
Screening of Fungi for the Application of Self-Healing Concrete
Therefore, a screening of different species of fungi has been conducted in this study.
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.
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.
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.
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 Synthia Novel View Synthesis
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 #5 on
Face Alignment
on AFLW-19
(NME_box (%, Full) metric)
Context-Aware Zero-Shot Recognition
We present a novel problem setting in zero-shot learning, zero-shot object recognition and detection in the context.
Online Learning for Supervised Dimension Reduction
The purpose of this paper is to propose new online learning approaches for supervised dimension reduction.
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.
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.
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)
3D Anchor-Free Lesion Detector on Computed Tomography Scans
The anchor mechanism is removed and lesions are formalized as single keypoints.
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.
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.
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.
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.
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.
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
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.
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.
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.
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.
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.
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.
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.
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
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.
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.
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
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
FaD-VLP: Fashion Vision-and-Language Pre-training towards Unified Retrieval and Captioning
Additionally, these works have mainly been restricted to multimodal understanding tasks.
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.
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.
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.
Ranked #4 on
Unsupervised Monocular Depth Estimation
on KITTI-C
Monocular Depth Estimation
Unsupervised Monocular Depth Estimation
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
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.
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.
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.
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.
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.
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.
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.
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.
Ranked #10 on
3D Human Pose Estimation
on MPI-INF-3DHP
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.
Channel-Aware Distillation Transformer for Depth Estimation on Nano Drones
Autonomous navigation of drones using computer vision has achieved promising performance.
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.
Fusing Structural and Functional Connectivities using Disentangled VAE for Detecting MCI
In this paper, a novel hierarchical structural-functional connectivity fusing (HSCF) model is proposed to construct brain structural-functional connectivity matrices and predict abnormal brain connections based on functional magnetic resonance imaging (fMRI) and diffusion tensor imaging (DTI).
Line Spectrum Estimation and Detection with Few-bit ADCs: Theoretical Analysis and Generalized NOMP Algorithm
As radar systems will be equipped with thousands of antenna elements and wide bandwidth, the associated costs and power consumption become exceedingly high, primarily attributed to the high-precision (e. g., 10-12 bits) analog-to-digital converters (ADCs).
Symbol-level Integrated Sensing and Communication enabled Multiple Base Stations Cooperative Sensing
This work may provide a guideline for the design of multi-BS cooperative sensing system to exploit the widely deployed networked mobile communication system.
Joint Power Control and Data Size Selection for Over-the-Air Computation Aided Federated Learning
For parameter aggregating in FL, over-the-air computation is a spectrum-efficient solution, which allows all mobile devices to transmit their parameter-mapped signals concurrently to a BS.
Federated Learning Robust to Byzantine Attacks: Achieving Zero Optimality Gap
In this paper, we propose a robust aggregation method for federated learning (FL) that can effectively tackle malicious Byzantine attacks.
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.
Event-Driven Imaging in Turbid Media: A Confluence of Optoelectronics and Neuromorphic Computation
In this paper a new optical-computational method is introduced to unveil images of targets whose visibility is severely obscured by light scattering in dense, turbid media.
You Only Look at Once for Real-time and Generic Multi-Task
In this study, we present an adaptive, real-time, and lightweight multi-task model designed to concurrently address object detection, drivable area segmentation, and lane line segmentation tasks.
Ranked #3 on
Lane Detection
on BDD100K val
Adaptive Digital Twin for UAV-Assisted Integrated Sensing, Communication, and Computation Networks
In this paper, we study a digital twin (DT)-empowered integrated sensing, communication, and computation network.
Exploring the Limits of ChatGPT in Software Security Applications
Large language models (LLMs) have undergone rapid evolution and achieved remarkable results in recent times.
Preference Poisoning Attacks on Reward Model Learning
In addition, we observe that the simpler and more scalable rank-by-distance approaches are often competitive with the best, and on occasion significantly outperform gradient-based methods.
Bidirectional Autoregressive Diffusion Model for Dance Generation
To make the generated dance motion smoother, a local information decoder is built for local motion enhancement.
A New Era in LLM Security: Exploring Security Concerns in Real-World LLM-based Systems
Large Language Model (LLM) systems are inherently compositional, with individual LLM serving as the core foundation with additional layers of objects such as plugins, sandbox, and so on.
DiffMOT: A Real-time Diffusion-based Multiple Object Tracker with Non-linear Prediction
In Multiple Object Tracking, objects often exhibit non-linear motion of acceleration and deceleration, with irregular direction changes.
Automatic and Universal Prompt Injection Attacks against Large Language Models
Large Language Models (LLMs) excel in processing and generating human language, powered by their ability to interpret and follow instructions.
SecGPT: An Execution Isolation Architecture for LLM-Based Systems
These LLM apps leverage the de facto natural language-based automated execution paradigm of LLMs: that is, apps and their interactions are defined in natural language, provided access to user data, and allowed to freely interact with each other and the system.
Don't Listen To Me: Understanding and Exploring Jailbreak Prompts of Large Language Models
Building on the insights from the user study, we also developed a system using AI as the assistant to automate the process of jailbreak prompt generation.
Maximum Likelihood Estimation on Stochastic Blockmodels for Directed Graph Clustering
This paper studies the directed graph clustering problem through the lens of statistics, where we formulate clustering as estimating underlying communities in the directed stochastic block model (DSBM).
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.
