Search Results for author:
Found 26 papers, 10 papers with code
Motor Imagery Classification for Asynchronous EEG-Based Brain-Computer Interfaces
Motor imagery (MI) based brain-computer interfaces (BCIs) enable the direct control of external devices through the imagined movements of various body parts.
T-TIME: Test-Time Information Maximization Ensemble for Plug-and-Play BCIs
Significance: To our knowledge, this is the first work on test time adaptation for calibration-free EEG-based BCIs, making plug-and-play BCIs possible.
Channel Reflection: Knowledge-Driven Data Augmentation for EEG-Based Brain-Computer Interfaces
A brain-computer interface (BCI) enables direct communication between the human brain and external devices.
Gated Parametric Neuron for Spike-based Audio Recognition
Compared with the LIF neuron, the GPN has two distinguishing advantages: 1) it copes well with the vanishing gradients by improving the flow of gradient propagation; and, 2) it learns spatio-temporal heterogeneous neuronal parameters automatically.
Federated Motor Imagery Classification for Privacy-Preserving Brain-Computer Interfaces
Training an accurate classifier for EEG-based brain-computer interface (BCI) requires EEG data from a large number of users, whereas protecting their data privacy is a critical consideration.
User-wise Perturbations for User Identity Protection in EEG-Based BCIs
After adding the proposed perturbations to EEG training data, the user identity information in the data becomes unlearnable, while the BCI task information remains unaffected.
Channel-aware Contrastive Conditional Diffusion for Multivariate Probabilistic Time Series Forecasting
Then, we devise an ad-hoc denoising-based temporal contrastive learning to explicitly amplify the predictive mutual information between past observations and future forecasts.
Data Imputation using Large Language Model to Accelerate Recommendation System
We evaluate our LLM-based imputation method across various tasks within the recommendation system domain, including single classification, multi-classification, and regression compared to traditional data imputation methods.
Enhance Image-to-Image Generation with LLaVA-generated Prompts
We observe a significant improvement in the visual coherence between the generated and input images compared to traditional methods.
Regional Style and Color Transfer
This paper presents a novel contribution to the field of regional style transfer.
DiffPLF: A Conditional Diffusion Model for Probabilistic Forecasting of EV Charging Load
Accordingly, we devise a novel Diffusion model termed DiffPLF for Probabilistic Load Forecasting of EV charging, which can explicitly approximate the predictive load distribution conditioned on historical data and related covariates.
CLIP as RNN: Segment Countless Visual Concepts without Training Endeavor
Existing open-vocabulary image segmentation methods require a fine-tuning step on mask labels and/or image-text datasets.
Large Foundation Models for Power Systems
Foundation models, such as Large Language Models (LLMs), can respond to a wide range of format-free queries without any task-specific data collection or model training, creating various research and application opportunities for the modeling and operation of large-scale power systems.
DiffCharge: Generating EV Charging Scenarios via a Denoising Diffusion Model
Recent proliferation of electric vehicle (EV) charging events has brought prominent stress over power grid operation.
Facial Affect Analysis: Learning from Synthetic Data & Multi-Task Learning Challenges
Facial affect analysis remains a challenging task with its setting transitioned from lab-controlled to in-the-wild situations.
The surprising impact of mask-head architecture on novel class segmentation
Under this family, we study Mask R-CNN and discover that instead of its default strategy of training the mask-head with a combination of proposals and groundtruth boxes, training the mask-head with only groundtruth boxes dramatically improves its performance on novel classes.
Low-Resource Machine Translation Training Curriculum Fit for Low-Resource Languages
We conduct an empirical study of neural machine translation (NMT) for truly low-resource languages, and propose a training curriculum fit for cases when both parallel training data and compute resource are lacking, reflecting the reality of most of the world's languages and the researchers working on these languages.
Confidence Trigger Detection: Accelerating Real-time Tracking-by-detection Systems
Real-time object tracking necessitates a delicate balance between speed and accuracy, a challenge exacerbated by the computational demands of deep learning methods.
Unsupervised Video Object Segmentation with Distractor-Aware Online Adaptation
Unsupervised video object segmentation is a crucial application in video analysis without knowing any prior information about the objects.
Design Pseudo Ground Truth with Motion Cue for Unsupervised Video Object Segmentation
Experimental results on DAVIS and FBMS show that the proposed method outperforms state-of-the-art unsupervised segmentation methods on various benchmark datasets.
Interpretable Convolutional Neural Networks via Feedforward Design
To construct convolutional layers, we develop a new signal transform, called the Saab (Subspace Approximation with Adjusted Bias) transform.
Unsupervised Video Object Segmentation with Motion-based Bilateral Networks
First, we propose a motion-based bilateral network to estimate the background based on the motion pattern of non-object regions.
Ranked #3 on
Video Salient Object Detection
on MCL
(using extra training data)
Instance Embedding Transfer to Unsupervised Video Object Segmentation
We propose a method for unsupervised video object segmentation by transferring the knowledge encapsulated in image-based instance embedding networks.
Multiple Instance Curriculum Learning for Weakly Supervised Object Detection
When supervising an object detector with weakly labeled data, most existing approaches are prone to trapping in the discriminative object parts, e. g., finding the face of a cat instead of the full body, due to lacking the supervision on the extent of full objects.
A Taught-Obesrve-Ask (TOA) Method for Object Detection with Critical Supervision
Being inspired by child's learning experience - taught first and followed by observation and questioning, we investigate a critically supervised learning methodology for object detection in this work.
Semantic Segmentation with Reverse Attention
Recent development in fully convolutional neural network enables efficient end-to-end learning of semantic segmentation.
Ranked #102 on
Semantic Segmentation
on NYU Depth v2
