Search Results for author:
Found 56 papers, 13 papers with code
Visual Prompt Tuning for Few-Shot Text Classification
In few-shot text classification, a feasible paradigm for deploying VL-PTMs is to align the input samples and their category names via the text encoders.
Future Aware Pricing and Matching for Sustainable On-demand Ride Pooling
Traditionally, both these challenges have been studied individually and using myopic approaches (considering only current requests), without considering the impact of current matching on addressing future requests.
Solving Constrained Reinforcement Learning through Augmented State and Reward Penalties
Constrained Reinforcement Learning has been employed to enforce safety constraints on policy through the use of expected cost constraints.
Chat2Map: Efficient Scene Mapping from Multi-Ego Conversations
Can conversational videos captured from multiple egocentric viewpoints reveal the map of a scene in a cost-efficient way?
Multi-Modal Experience Inspired AI Creation
To model such human capabilities, in this paper, we define and solve a novel AI creation problem based on human experiences.
Joint Beamforming Coordination and User Selection for CoMP Enabled NR-U Networks
In this work, we introduce a CoMP based NR-U network, particularly for 6G enabled massive IoT scenarios.
PReGAN: Answer Oriented Passage Ranking with Weakly Supervised GAN
Beyond topical relevance, passage ranking for open-domain factoid question answering also requires a passage to contain an answer (answerability).
Correction of out-of-focus microscopic images by deep learning
Results To solve the out-of-focus issue in microscopy, we developed a Cycle Generative Adversarial Network (CycleGAN) based model and a multi-component weighted loss function.
Hyperlink-induced Pre-training for Passage Retrieval in Open-domain Question Answering
To alleviate the data scarcity problem in training question answering systems, recent works propose additional intermediate pre-training for dense passage retrieval (DPR).
MetaDT: Meta Decision Tree for Interpretable Few-Shot Learning
At last, a two-loop optimization mechanism is incorporated into our framework for a fast adaptation of the decision tree with few examples.
KMIR: A Benchmark for Evaluating Knowledge Memorization, Identification and Reasoning Abilities of Language Models
However, to figure out whether PLMs can be reliable knowledge sources and used as alternative knowledge bases (KBs), we need to further explore some critical features of PLMs.
Model Calibration of the Liquid Mercury Spallation Target using Evolutionary Neural Networks and Sparse Polynomial Expansions
Given that some of the calibrated parameters that show a good agreement with the experimental data can be nonphysical mercury properties, we need a more advanced two-phase flow model to capture bubble dynamics and mercury cavitation.
Deep Learning for Computational Cytology: A Survey
Computational cytology is a critical, rapid-developing, yet challenging topic in the field of medical image computing which analyzes the digitized cytology image by computer-aided technologies for cancer screening.
Egocentric Deep Multi-Channel Audio-Visual Active Speaker Localization
We propose a novel end-to-end deep learning approach that is able to give robust voice activity detection and localization results.
Ranked #1 on
Active Speaker Localization
on EasyCom
Joint Video Summarization and Moment Localization by Cross-Task Sample Transfer
To address it, this work explores a new solution for video summarization by transferring samples from a correlated task (i. e., video moment localization) equipped with abundant training data.
Semi-asynchronous Hierarchical Federated Learning for Cooperative Intelligent Transportation Systems
Cooperative Intelligent Transport System (C-ITS) is a promising network to provide safety, efficiency, sustainability, and comfortable services for automated vehicles and road infrastructures by taking advantages from participants.
Towards More Effective and Economic Sparsely-Activated Model
To increase the number of activated experts without an increase in computational cost, we propose SAM (Switch and Mixture) routing, an efficient hierarchical routing mechanism that activates multiple experts in a same device (GPU).
Ego4D: Around the World in 3,000 Hours of Egocentric Video
We introduce Ego4D, a massive-scale egocentric video dataset and benchmark suite.
Towards Efficient NLP: A Standard Evaluation and A Strong Baseline
ELUE is dedicated to depict the Pareto Frontier for various language understanding tasks, such that it can tell whether and how much a method achieves Pareto improvement.
YES SIR!Optimizing Semantic Space of Negatives with Self-Involvement Ranker
Finally, supervisory signal in rear compressor is computed based on condition probability and thus can control sample dynamic and further enhance the model performance.
Contrastive Learning of User Behavior Sequence for Context-Aware Document Ranking
To learn a more robust representation of the user behavior sequence, we propose a method based on contrastive learning, which takes into account the possible variations in user's behavior sequences.
Pre-training for Ad-hoc Retrieval: Hyperlink is Also You Need
In this paper, we propose to leverage the large-scale hyperlinks and anchor texts to pre-train the language model for ad-hoc retrieval.
Millimeter-Wave NR-U and WiGig Coexistence: Joint User Grouping, Beam Coordination and Power Control
Our aim for the proposed coexistence network is to maximize the spectral efficiency while ensuring the strict NR-U delay requirement and the WiGig transmission performance in real time environments.
Proactive Retrieval-based Chatbots based on Relevant Knowledge and Goals
The final response is selected according to the predicted knowledge, the goal to achieve, and the context.
Graph-Embedded Multi-Agent Learning for Smart Reconfigurable THz MIMO-NOMA Networks
With the accelerated development of immersive applications and the explosive increment of internet-of-things (IoT) terminals, 6G would introduce terahertz (THz) massive multiple-input multiple-output non-orthogonal multiple access (MIMO-NOMA) technologies to meet the ultra-high-speed transmission and massive connectivity requirements.
Answer Complex Questions: Path Ranker Is All You Need
Currently, the most popular method for open-domain Question Answering (QA) adopts "Retriever and Reader" pipeline, where the retriever extracts a list of candidate documents from a large set of documents followed by a ranker to rank the most relevant documents and the reader extracts answer from the candidates.
EasyCom: An Augmented Reality Dataset to Support Algorithms for Easy Communication in Noisy Environments
In this work, we describe, evaluate and release a dataset that contains over 5 hours of multi-modal data useful for training and testing algorithms for the application of improving conversations for an AR glasses wearer.
Ranked #1 on
Speech Enhancement
on EasyCom
Early Exiting with Ensemble Internal Classifiers
In this paper, we show that a novel objective function for the training of the ensemble internal classifiers can be naturally induced from the perspective of ensemble learning and information theory.
Emotion Eliciting Machine: Emotion Eliciting Conversation Generation based on Dual Generator
Then we propose a dual encoder-decoder structure to model the generation of responses in both positive and negative side based on the changes of the user's emotion status in the conversation.
A Semi-Supervised Classification Method of Apicomplexan Parasites and Host Cell Using Contrastive Learning Strategy
A common shortfall of supervised learning for medical imaging is the greedy need for human annotations, which is often expensive and time-consuming to obtain.
Egocentric Pose Estimation from Human Vision Span
Existing approaches either use a narrow field of view front facing camera that barely captures the wearer, or an extruded head-mounted top-down camera for maximal wearer visibility.
Residual-Aided End-to-End Learning of Communication System without Known Channel
However, the gradient vanishing and overfitting problems of GAN will result in the serious performance degradation of E2E learning of communication system.
Market2Dish: Health-aware Food Recommendation
With the rising incidence of some diseases, such as obesity and diabetes, a healthy diet is arousing increasing attention.
Variance Reduction for Deep Q-Learning using Stochastic Recursive Gradient
Deep Q-learning algorithms often suffer from poor gradient estimations with an excessive variance, resulting in unstable training and poor sampling efficiency.
Learning Differential Diagnosis of Skin Conditions with Co-occurrence Supervision using Graph Convolutional Networks
Skin conditions are reported the 4th leading cause of nonfatal disease burden worldwide.
Real-time 3D Deep Multi-Camera Tracking
Our DMCT consists of 1) a fast and novel perspective-aware Deep GroudPoint Network, 2) a fusion procedure for ground-plane occupancy heatmap estimation, 3) a novel Deep Glimpse Network for person detection and 4) a fast and accurate online tracker.
Review of data analysis in vision inspection of power lines with an in-depth discussion of deep learning technology
With the aim of providing a comprehensive overview for researchers who are interested in developing a deep-learning-based analysis system for power lines inspection data, this paper conducts a thorough review of the current literature and identifies the challenges for future research.
Overcoming Long-term Catastrophic Forgetting through Adversarial Neural Pruning and Synaptic Consolidation
It is due to two facts: first, as the model learns more tasks, the intersection of the low-error parameter subspace satisfying for these tasks becomes smaller or even does not exist; second, when the model learns a new task, the cumulative error keeps increasing as the model tries to protect the parameter configuration of previous tasks from interference.
Evaluation of Three Deep Learning Models for Early Crop Classification Using Sentinel-1A Imagery Time Series—A Case Study in Zhanjiang, China
First, we trained 1D CNNs, LSTM RNNs, and GRU RNNs based on the full images’ time series to attain three classifiers with optimal architectures and hyper-parameters.
Inertial nonconvex alternating minimizations for the image deblurring
In image processing, Total Variation (TV) regularization models are commonly used to recover blurred images.
Heavy-ball Algorithms Always Escape Saddle Points
In this paper, we answer a question: can the nonconvex heavy-ball algorithms with random initialization avoid saddle points?
Real-time Multiple People Hand Localization in 4D Point Clouds
Different from the traditional multiple view approaches, which find key points in 2D and then triangulate to recover the 3D locations, our method directly processes the dynamic 3D data that involve both clutter and crowd.
Iteratively reweighted penalty alternating minimization methods with continuation for image deblurring
In this paper, we consider a class of nonconvex problems with linear constraints appearing frequently in the area of image processing.
Ego-Downward and Ambient Video based Person Location Association
To provide a possible solution to this problem, this paper proposes a camera system with both ego-downward and third-static view to perform localization and tracking in a learning approach.
Non-ergodic Convergence Analysis of Heavy-Ball Algorithms
For objective functions satisfying a relaxed strongly convex condition, the linear convergence is established under weaker assumptions on the step size and inertial parameter than made in the existing literature.
A Detection and Segmentation Architecture for Skin Lesion Segmentation on Dermoscopy Images
This report summarises our method and validation results for the ISIC Challenge 2018 - Skin Lesion Analysis Towards Melanoma Detection - Task 1: Lesion Segmentation.
Action4D: Real-time Action Recognition in the Crowd and Clutter
In this paper, we propose a real-time action recognition method, Action4D, which gives reliable and accurate results in the real-world settings.
Long short-term memory networks in memristor crossbars
Recent breakthroughs in recurrent deep neural networks with long short-term memory (LSTM) units has led to major advances in artificial intelligence.
Emerging Technologies Applied Physics
Densely Dilated Spatial Pooling Convolutional Network using benign loss functions for imbalanced volumetric prostate segmentation
Meanwhile, we adopt DSC loss and Jaccard loss functions to train our DDSP ConNet.
A convergence framework for inexact nonconvex and nonsmooth algorithms and its applications to several iterations
In fact, a lot of classical inexact nonconvex and nonsmooth algorithms allow these three conditions.
Iteratively Linearized Reweighted Alternating Direction Method of Multipliers for a Class of Nonconvex Problems
The traditional alternating direction method of multipliers encounters troubles in both mathematics and computations in solving the nonconvex and nonsmooth subproblem.
Research on Bi-mode Biometrics Based on Deep Learning
In view of the fact that biological characteristics have excellent independent distinguishing characteristics, biometric identification technology involves almost all the relevant areas of human distinction.
Detangling People: Individuating Multiple Close People and Their Body Parts via Region Assembly
In addition, we demonstrate its impact on a proxemics recognition task, which demands a precise representation of "whose body part is where" in crowded images.
Seeing Invisible Poses: Estimating 3D Body Pose from Egocentric Video
We propose to infer the "invisible pose" of a person behind the egocentric camera.
Matching Bags of Regions in RGBD images
We study the new problem of matching regions between a pair of RGBD images given a large set of overlapping region proposals.
A Linear Approach to Matching Cuboids in RGBD Images
We propose a novel linear method to match cuboids in indoor scenes using RGBD images from Kinect.
