Search Results for author:
Found 19 papers, 4 papers with code
A Novel Automatic Real-time Motion Tracking Method for Magnetic Resonance Imaging-guided Radiotherapy: Leveraging the Enhanced Tracking-Learning-Detection Framework with Automatic Segmentation
Moreover, the ETLD+ICV yielded a dice global score of more than 82% for all subjects, demonstrating the proposed method's extensibility and precise target volume coverage.
On the Trade-off between Flatness and Optimization in Distributed Learning
This paper proposes a theoretical framework to evaluate and compare the performance of gradient-descent algorithms for distributed learning in relation to their behavior around local minima in nonconvex environments.
Hierarchical Fashion Design with Multi-stage Diffusion Models
Cross-modal fashion synthesis and editing offer intelligent support to fashion designers by enabling the automatic generation and local modification of design drafts. While current diffusion models demonstrate commendable stability and controllability in image synthesis, they still face significant challenges in generating fashion design from abstract design elements and fine-grained editing. Abstract sensory expressions, \eg office, business, and party, form the high-level design concepts, while measurable aspects like sleeve length, collar type, and pant length are considered the low-level attributes of clothing. Controlling and editing fashion images using lengthy text descriptions poses a difficulty. In this paper, we propose HieraFashDiff, a novel fashion design method using the shared multi-stage diffusion model encompassing high-level design concepts and low-level clothing attributes in a hierarchical structure. Specifically, we categorized the input text into different levels and fed them in different time step to the diffusion model according to the criteria of professional clothing designers. HieraFashDiff allows designers to add low-level attributes after high-level prompts for interactive editing incrementally. In addition, we design a differentiable loss function in the sampling process with a mask to keep non-edit areas. Comprehensive experiments performed on our newly conducted Hierarchical fashion dataset, demonstrate that our proposed method outperforms other state-of-the-art competitors.
AdaFuse: Adaptive Medical Image Fusion Based on Spatial-Frequential Cross Attention
Specifically, we propose the cross-attention fusion (CAF) block, which adaptively fuses features of two modalities in the spatial and frequency domains by exchanging key and query values, and then calculates the cross-attention scores between the spatial and frequency features to further guide the spatial-frequential information fusion.
Decentralized Adversarial Training over Graphs
The vulnerability of machine learning models to adversarial attacks has been attracting considerable attention in recent years.
Multi-Agent Adversarial Training Using Diffusion Learning
This work focuses on adversarial learning over graphs.
Boosting Neural Networks to Decompile Optimized Binaries
They formulate the decompilation process as a translation problem between LPL and HPL, aiming to reduce the human cost required to develop decompilation tools and improve their generalizability.
Nesting Forward Automatic Differentiation for Memory-Efficient Deep Neural Network Training
An activation function is an element-wise mathematical function and plays a crucial role in deep neural networks (DNN).
Optimal Regularized Online Allocation by Adaptive Re-Solving
This paper introduces a dual-based algorithm framework for solving the regularized online resource allocation problems, which have potentially non-concave cumulative rewards, hard resource constraints, and a non-separable regularizer.
Online Network Utility Maximization: Algorithm, Competitive Analysis, and Applications
In addition, since worst-case scenarios rarely occur in practice, we devise an adaptive implementation of our algorithm to improve its average-case performance and validate its effectiveness via simulations.
Data Structures and Algorithms
Automatic Comic Generation with Stylistic Multi-page Layouts and Emotion-driven Text Balloon Generation
Finally, as opposed to using the same type of balloon as in previous works, we propose an emotion-aware balloon generation method to create different types of word balloons by analyzing the emotion of subtitles and audios.
Night-time Scene Parsing with a Large Real Dataset
Although huge progress has been made on scene analysis in recent years, most existing works assume the input images to be in day-time with good lighting conditions.
An end-to-end Generative Retrieval Method for Sponsored Search Engine --Decoding Efficiently into a Closed Target Domain
In this paper, we present a generative retrieval method for sponsored search engine, which uses neural machine translation (NMT) to generate keywords directly from query.
Look Deeper into Depth: Monocular Depth Estimation with Semantic Booster and Attention-Driven Loss
Monocular depth estimation benefits greatly from learning based techniques.
Task-driven Webpage Saliency
Inspired by the observation that given a specific task, human attention is strongly correlated with certain semantic components on a webpage (e. g., images, buttons and input boxes), our network explicitly disentangles saliency prediction into two independent sub-tasks: task-specific attention shift prediction and task-free saliency prediction.
Deep Speaker: an End-to-End Neural Speaker Embedding System
We present Deep Speaker, a neural speaker embedding system that maps utterances to a hypersphere where speaker similarity is measured by cosine similarity.
Dataset and Neural Recurrent Sequence Labeling Model for Open-Domain Factoid Question Answering
While question answering (QA) with neural network, i. e. neural QA, has achieved promising results in recent years, lacking of large scale real-word QA dataset is still a challenge for developing and evaluating neural QA system.
Deep Recurrent Models with Fast-Forward Connections for Neural Machine Translation
On the WMT'14 English-to-French task, we achieve BLEU=37. 7 with a single attention model, which outperforms the corresponding single shallow model by 6. 2 BLEU points.
Ranked #38 on
Machine Translation
on WMT2014 English-French
A Robust Panel Extraction Method for Manga
Automatically extracting frames/panels from digital comic pages is crucial for techniques that facilitate comic reading on mobile devices with limited display areas.
