Search Results for author:
Found 37 papers, 13 papers with code
Clustering Driven Deep Autoencoder for Video Anomaly Detection
Because of the ambiguous definition of anomaly and the complexity of real data, anomaly detection in videos is one of the most challenging problems in intelligent video surveillance.
Foot In The Door: Understanding Large Language Model Jailbreaking via Cognitive Psychology
Our research provides a psychological explanation of the jailbreak prompts.
TR-DETR: Task-Reciprocal Transformer for Joint Moment Retrieval and Highlight Detection
Finally, a task cooperation module is constructed to refine the retrieval pipeline and the highlight score prediction process by utilizing the reciprocity between MR and HD.
Nonrigid Object Contact Estimation With Regional Unwrapping Transformer
Based on this representation, our Regional Unwrapping Transformer (RUFormer) learns the correlation priors across regions from monocular inputs and predicts corresponding contact and deformed transformations.
Reconstructing Interacting Hands with Interaction Prior from Monocular Images
Our key idea is to first construct a two-hand interaction prior and recast the interaction reconstruction task as the conditional sampling from the prior.
Implicit Obstacle Map-driven Indoor Navigation Model for Robust Obstacle Avoidance
Robust obstacle avoidance is one of the critical steps for successful goal-driven indoor navigation tasks. Due to the obstacle missing in the visual image and the possible missed detection issue, visual image-based obstacle avoidance techniques still suffer from unsatisfactory robustness.
Self-Deception: Reverse Penetrating the Semantic Firewall of Large Language Models
Inspired by the attack that penetrates traditional firewalls through reverse tunnels, we introduce a "self-deception" attack that can bypass the semantic firewall by inducing LLM to generate prompts that facilitate jailbreak.
Few-shot Class-incremental Audio Classification Using Stochastic Classifier
It is generally assumed that number of classes is fixed in current audio classification methods, and the model can recognize pregiven classes only.
Low-Complexity Acoustic Scene Classification Using Data Augmentation and Lightweight ResNet
This subtask focuses on classifying audio samples of multiple devices with a low-complexity model, where two main difficulties need to be overcome.
Few-shot Class-incremental Audio Classification Using Dynamically Expanded Classifier with Self-attention Modified Prototypes
Labeled support samples and unlabeled query samples are used to train the prototype adaptation network and update the classifier, since they are informative for audio classification.
Stochastic Biological System-of-Systems Modelling for iPSC Culture
Large-scale manufacturing of induced pluripotent stem cells (iPSCs) is essential for cell therapies and regenerative medicines.
Stochastic Molecular Reaction Queueing Network Modeling for In Vitro Transcription Process
To facilitate a rapid response to pandemic threats, this paper focuses on developing a mechanistic simulation model for in vitro transcription (IVT) process, a crucial step in mRNA vaccine manufacturing.
Structure-Function Dynamics Hybrid Modeling: RNA Degradation
RNA structure and functional dynamics play fundamental roles in controlling biological systems.
Metabolic Regulatory Network Kinetic Modeling with Multiple Isotopic Tracers for iPSCs
In this paper, a metabolic kinetic model was developed to characterize underlying mechanisms of iPSC culture process, which can predict cell response to environmental perturbation and support process control.
HMDO: Markerless Multi-view Hand Manipulation Capture with Deformable Objects
We construct the first markerless deformable interaction dataset recording interactive motions of the hands and deformable objects, called HMDO (Hand Manipulation with Deformable Objects).
Deep Boosting Robustness of DNN-based Image Watermarking via DBMark
In this paper, we propose DBMARK, a novel end-to-end digital image watermarking framework to deep boost the robustness of DNN-based image watermarking.
Variance Reduction based Experience Replay for Policy Optimization
For reinforcement learning on complex stochastic systems where many factors dynamically impact the output trajectories, it is desirable to effectively leverage the information from historical samples collected in previous iterations to accelerate policy optimization.
From Discovery to Production: Challenges and Novel Methodologies for Next Generation Biomanufacturing
The increasingly pressing demand of novel drugs (e. g., gene therapies for personalized cancer care, ever evolving vaccines) with unprecedented levels of personalization, has put a remarkable pressure on the traditionally long time required by the pharma R&D and manufacturing to go from design to production of new products.
Variance Reduction based Partial Trajectory Reuse to Accelerate Policy Gradient Optimization
Built on our previous study on green simulation assisted policy gradient (GS-PG) focusing on trajectory-based reuse, in this paper, we consider infinite-horizon Markov Decision Processes and create a new importance sampling based policy gradient optimization approach to support dynamic decision making.
Sequential Importance Sampling for Hybrid Model Bayesian Inference to Support Bioprocess Mechanism Learning and Robust Control
Driven by the critical needs of biomanufacturing 4. 0, we introduce a probabilistic knowledge graph hybrid model characterizing the risk- and science-based understanding of bioprocess mechanisms.
Stability-driven Contact Reconstruction From Monocular Color Images
Our key idea is to reconstruct the contact pattern directly from monocular images, and then utilize the physical stability criterion in the simulation to optimize it.
Optical Flow for Video Super-Resolution: A Survey
Video super-resolution is currently one of the most active research topics in computer vision as it plays an important role in many visual applications.
Opportunities of Hybrid Model-based Reinforcement Learning for Cell Therapy Manufacturing Process Control
Driven by the key challenges of cell therapy manufacturing, including high complexity, high uncertainty, and very limited process observations, we propose a hybrid model-based reinforcement learning (RL) to efficiently guide process control.
Variance Reduction based Experience Replay for Policy Optimization
For reinforcement learning on complex stochastic systems, it is desirable to effectively leverage the information from historical samples collected in previous iterations to accelerate policy optimization.
Reinforcement Learning Assisted Oxygen Therapy for COVID-19 Patients Under Intensive Care
We developed a machine learning algorithm, based on a deep Reinforcement Learning (RL), for continuous management of oxygen flow rate for critical ill patients under intensive care, which can identify the optimal personalized oxygen flow rate with strong potentials to reduce mortality rate relative to the current clinical practice.
Policy Optimization in Dynamic Bayesian Network Hybrid Models of Biomanufacturing Processes
Biopharmaceutical manufacturing is a rapidly growing industry with impact in virtually all branches of medicines.
Multi-Attribute Enhancement Network for Person Search
Visual character attributes play a key role in retrieving the query person, which has been explored in Re-ID but has been ignored in Person Search.
Optimizing Biomanufacturing Harvesting Decisions under Limited Historical Data
We adopt a Bayesian approach to update the unknown parameters of the growth-rate distributions, and use the resulting posterior distributions to characterize the impact of model risk on fermentation output variability.
Personalized Multimorbidity Management for Patients with Type 2 Diabetes Using Reinforcement Learning of Electronic Health Records
Comorbid chronic conditions are common among people with type 2 diabetes.
Green Simulation Assisted Reinforcement Learning with Model Risk for Biomanufacturing Learning and Control
Biopharmaceutical manufacturing faces critical challenges, including complexity, high variability, lengthy lead time, and limited historical data and knowledge of the underlying system stochastic process.
Global-Local Metamodel Assisted Two-Stage Optimization via Simulation
To integrate strategic, tactical and operational decisions, the two-stage optimization has been widely used to guide dynamic decision making.
Interpretable Biomanufacturing Process Risk and Sensitivity Analyses for Quality-by-Design and Stability Control
While biomanufacturing plays a significant role in supporting the economy and ensuring public health, it faces critical challenges, including complexity, high variability, lengthy lead time, and very limited process data, especially for personalized new cell and gene biotherapeutics.
TeraVR empowers precise reconstruction of complete 3-D neuronal morphology in the whole brain
Neuron morphology is recognized as a key determinant of cell type, yet the quantitative profiling of a mammalian neuron’s complete three-dimensional (3-D) morphology remains arduous when the neuron has complex arborization and long projection.
PrivLogit: Efficient Privacy-preserving Logistic Regression by Tailoring Numerical Optimizers
Leveraging this new method, we propose two new secure protocols for conducting logistic regression in a privacy-preserving and distributed manner.
A novel transfer learning method based on common space mapping and weighted domain matching
We map the data of two domains to one single common space, and learn a classifier in this common space.
Semi-supervised structured output prediction by local linear regression and sub-gradient descent
The existing semi-supervise structured output prediction methods learn a global predictor for all the data points in a data set, which ignores the differences of local distributions of the data set, and the effects to the structured output prediction.
Supporting Regularized Logistic Regression Privately and Efficiently
As one of the most popular statistical and machine learning models, logistic regression with regularization has found wide adoption in biomedicine, social sciences, information technology, and so on.
