Xu Yang
YOU?
Author Swipe
View article: The value of using deep learning to predict proliferative hepatocellular carcinoma based on multiphasic magnetic resonance imaging
The value of using deep learning to predict proliferative hepatocellular carcinoma based on multiphasic magnetic resonance imaging Open
The hybrid model showed potential for predicting PHCC, which may assist clinicians in making personalized treatment decisions.
View article: Association Between Healing Hurt People Hospital-Based Violence Intervention Program Participation and Trauma-Related Psychological Symptoms for Violent Injury Survivors
Association Between Healing Hurt People Hospital-Based Violence Intervention Program Participation and Trauma-Related Psychological Symptoms for Violent Injury Survivors Open
This study's findings constitute descriptive (ie, not causal) evidence, which suggests that HHP may be associated with improvements in trauma-related psychological symptoms. When randomized control trials are not feasible, future research …
View article: Transforming Visual Scene Graphs to Image Captions
Transforming Visual Scene Graphs to Image Captions Open
We propose to Transform Scene Graphs (TSG) into more descriptive captions. In TSG, we apply multi-head attention (MHA) to design the Graph Neural Network (GNN) for embedding scene graphs. After embedding, different graph embeddings contain…
View article: Flow-Induced Motion and Energy Conversion of the Cir-T-Att Oscillator in a Flow Field with a High Reynolds Number
Flow-Induced Motion and Energy Conversion of the Cir-T-Att Oscillator in a Flow Field with a High Reynolds Number Open
The present study aims to systematically investigate the effects of a high Reynolds number on the flow-induced motion and energy conversion of the Cir-T-Att oscillator. Experiments are conducted in six Reynolds number ranges (2.89 × 104~6.…
View article: Auto-Parsing Network for Image Captioning and Visual Question Answering
Auto-Parsing Network for Image Captioning and Visual Question Answering Open
We propose an Auto-Parsing Network (APN) to discover and exploit the input data's hidden tree structures for improving the effectiveness of the Transformer-based vision-language systems. Specifically, we impose a Probabilistic Graphical Mo…
View article: Potential Analysis of the Attention-Based LSTM Model in Ultra-Short-Term Forecasting of Building HVAC Energy Consumption
Potential Analysis of the Attention-Based LSTM Model in Ultra-Short-Term Forecasting of Building HVAC Energy Consumption Open
Predicting system energy consumption accurately and adjusting dynamic operating parameters of the HVAC system in advance is the basis of realizing the model predictive control (MPC). In recent years, the LSTM network had made remarkable ac…
View article: Towards Unbiased Visual Emotion Recognition via Causal Intervention
Towards Unbiased Visual Emotion Recognition via Causal Intervention Open
Although much progress has been made in visual emotion recognition, researchers have realized that modern deep networks tend to exploit dataset characteristics to learn spurious statistical associations between the input and the target. Su…
View article: Frequency division denoising algorithm based on VIF adaptive 2D-VMD ultrasound image
Frequency division denoising algorithm based on VIF adaptive 2D-VMD ultrasound image Open
Ultrasound imaging has developed into an indispensable imaging technology in medical diagnosis and treatment applications due to its unique advantages, such as safety, affordability, and convenience. With the development of data informatio…
View article: Causal Attention for Vision-Language Tasks
Causal Attention for Vision-Language Tasks Open
We present a novel attention mechanism: Causal Attention (CATT), to remove the ever-elusive confounding effect in existing attention-based vision-language models. This effect causes harmful bias that misleads the attention module to focus …
View article: Practices of Hydro-Meteorological Support During Construction Period of Largehydropower Project
Practices of Hydro-Meteorological Support During Construction Period of Largehydropower Project Open
The hydrological and meteorological hydro-meteorological support is one important part of the hydropower construction. Accidents caused by flood and rainstorm during construction will be reduced effectively with the help of reliable hydrol…
View article: Finding It at Another Side: A Viewpoint-Adapted Matching Encoder for Change Captioning
Finding It at Another Side: A Viewpoint-Adapted Matching Encoder for Change Captioning Open
Change Captioning is a task that aims to describe the difference between images with natural language. Most existing methods treat this problem as a difference judgment without the existence of distractors, such as viewpoint changes. Howev…
View article: Deconfounded Image Captioning: A Causal Retrospect
Deconfounded Image Captioning: A Causal Retrospect Open
Dataset bias in vision-language tasks is becoming one of the main problems which hinders the progress of our community. Existing solutions lack a principled analysis about why modern image captioners easily collapse into dataset bias. In t…
View article: Learning to Collocate Neural Modules for Image Captioning
Learning to Collocate Neural Modules for Image Captioning Open
We do not speak word by word from scratch; our brain quickly structures a pattern like \textsc{sth do sth at someplace} and then fill in the detailed descriptions. To render existing encoder-decoder image captioners such human-like reasoni…
View article: Unpaired Image Captioning via Scene Graph Alignments
Unpaired Image Captioning via Scene Graph Alignments Open
Most of current image captioning models heavily rely on paired image-caption datasets. However, getting large scale image-caption paired data is labor-intensive and time-consuming. In this paper, we present a scene graph-based approach for…
View article: Auto-Encoding Scene Graphs for Image Captioning
Auto-Encoding Scene Graphs for Image Captioning Open
We propose Scene Graph Auto-Encoder (SGAE) that incorporates the language inductive bias into the encoder-decoder image captioning framework for more human-like captions. Intuitively, we humans use the inductive bias to compose collocation…
View article: Shuffle-Then-Assemble: Learning Object-Agnostic Visual Relationship Features
Shuffle-Then-Assemble: Learning Object-Agnostic Visual Relationship Features Open
Due to the fact that it is prohibitively expensive to completely annotate visual relationships, i.e., the (obj1, rel, obj2) triplets, relationship models are inevitably biased to object classes of limited pairwise patterns, leading to poor…
View article: Experimental Investigation on Soft Galloping and Hard Galloping of Triangular Prisms
Experimental Investigation on Soft Galloping and Hard Galloping of Triangular Prisms Open
The studies currently on soft galloping (SG) and hard galloping (HG) are scarce. In this study, SG and HG of spring-mounted triangular prisms in a water channel are investigated experimentally. A power take-off system (PTO), a spring syste…