Search Results for author:
Found 42 papers, 18 papers with code
HIC-YOLOv5: Improved YOLOv5 For Small Object Detection
Small object detection has been a challenging problem in the field of object detection.
Evaluating Large Language Models for Radiology Natural Language Processing
The rise of large language models (LLMs) has marked a pivotal shift in the field of natural language processing (NLP).
Correlation-Aware Mutual Learning for Semi-supervised Medical Image Segmentation
Our approach is based on a mutual learning strategy that incorporates two modules: the Cross-sample Mutual Attention Module (CMA) and the Omni-Correlation Consistency Module (OCC).
Review of Large Vision Models and Visual Prompt Engineering
This review aims to summarize the methods employed in the computer vision domain for large vision models and visual prompt engineering, exploring the latest advancements in visual prompt engineering.
A Transformer-based representation-learning model with unified processing of multimodal input for clinical diagnostics
During the diagnostic process, clinicians leverage multimodal information, such as chief complaints, medical images, and laboratory-test results.
Attention Paper: How Generative AI Reshapes Digital Shadow Industry?
The rapid development of digital economy has led to the emergence of various black and shadow internet industries, which pose potential risks that can be identified and managed through digital risk management (DRM) that uses different techniques such as machine learning and deep learning.
UniControl: A Unified Diffusion Model for Controllable Visual Generation In the Wild
Visual generative foundation models such as Stable Diffusion show promise in navigating these goals, especially when prompted with arbitrary languages.
ULIP-2: Towards Scalable Multimodal Pre-training for 3D Understanding
Recent advancements in multimodal pre-training methods have shown promising efficacy in 3D representation learning by aligning multimodal features across 3D shapes, their 2D counterparts, and language descriptions.
Ranked #2 on
3D Point Cloud Classification
on ScanObjectNN
(using extra training data)
Prompt Engineering for Healthcare: Methodologies and Applications
This review will introduce the latest advances in prompt engineering in the field of natural language processing (NLP) for the medical domain.
ImpressionGPT: An Iterative Optimizing Framework for Radiology Report Summarization with ChatGPT
The 'Impression' section of a radiology report is a critical basis for communication between radiologists and other physicians, and it is typically written by radiologists based on the 'Findings' section.
Fairness-guided Few-shot Prompting for Large Language Models
Large language models have demonstrated surprising ability to perform in-context learning, i. e., these models can be directly applied to solve numerous downstream tasks by conditioning on a prompt constructed by a few input-output examples.
GlueGen: Plug and Play Multi-modal Encoders for X-to-image Generation
Empirical results show that GlueNet can be trained efficiently and enables various capabilities beyond previous state-of-the-art models: 1) multilingual language models such as XLM-Roberta can be aligned with existing T2I models, allowing for the generation of high-quality images from captions beyond English; 2) GlueNet can align multi-modal encoders such as AudioCLIP with the Stable Diffusion model, enabling sound-to-image generation; 3) it can also upgrade the current text encoder of the latent diffusion model for challenging case generation.
HIVE: Harnessing Human Feedback for Instructional Visual Editing
Incorporating human feedback has been shown to be crucial to align text generated by large language models to human preferences.
Beyond Single Items: Exploring User Preferences in Item Sets with the Conversational Playlist Curation Dataset
Users in consumption domains, like music, are often able to more efficiently provide preferences over a set of items (e. g. a playlist or radio) than over single items (e. g. songs).
Talk the Walk: Synthetic Data Generation for Conversational Music Recommendation
A human evaluation shows that the conversations contain consistent utterances with relevant item sets, nearly matching the quality of small human-collected conversational data for this task.
Vertical Federated Linear Contextual Bandits
In this paper, we investigate a novel problem of building contextual bandits in the vertical federated setting, i. e., contextual information is vertically distributed over different departments.
Use All The Labels: A Hierarchical Multi-Label Contrastive Learning Framework
Current contrastive learning frameworks focus on leveraging a single supervisory signal to learn representations, which limits the efficacy on unseen data and downstream tasks.
AutoMO-Mixer: An automated multi-objective Mixer model for balanced, safe and robust prediction in medicine
Accurately identifying patient's status through medical images plays an important role in diagnosis and treatment.
DeepSSN: a deep convolutional neural network to assess spatial scene similarity
Spatial-query-by-sketch is an intuitive tool to explore human spatial knowledge about geographic environments and to support communication with scene database queries.
Advancing 3D Medical Image Analysis with Variable Dimension Transform based Supervised 3D Pre-training
The difficulties in both data acquisition and annotation substantially restrict the sample sizes of training datasets for 3D medical imaging applications.
Ranked #1 on
Medical Object Detection
on DeepLesion
A Multi-task Deep Feature Selection Method for Brain Imaging Genetics
Though deep learning models can extract the nonlinear relationship, they could not select relevant genetic factors.
SSMD: Semi-Supervised Medical Image Detection with Adaptive Consistency and Heterogeneous Perturbation
Semi-Supervised classification and segmentation methods have been widely investigated in medical image analysis.
A Structure-Aware Relation Network for Thoracic Diseases Detection and Segmentation
Leveraging on constant structure and disease relations extracted from domain knowledge, we propose a structure-aware relation network (SAR-Net) extending Mask R-CNN.
Revisiting 3D Context Modeling with Supervised Pre-training for Universal Lesion Detection in CT Slices
We demonstrate that with the novel pre-training method, the proposed MP3D FPN achieves state-of-the-art detection performance on the DeepLesion dataset (3. 48% absolute improvement in the sensitivity of FPs@0. 5), significantly surpassing the baseline method by up to 6. 06% (in MAP@0. 5) which adopts 2D convolution for 3D context modeling.
Ranked #4 on
Medical Object Detection
on DeepLesion
A method for sharing dynamic geometry information in studies on liquid-based detectors
The liquid-based detectors are widely used in particle and nuclear physics experiments.
Instrumentation and Detectors
Deep Feature Mining via Attention-based BiLSTM-GCN for Human Motor Imagery Recognition
The introduced deep feature mining approach can precisely recognize human motion intents from raw EEG signals, which paves the road to translate the EEG based MI recognition to practical BCI systems.
Deep Homography Estimation for Dynamic Scenes
We then develop a multi-scale neural network and show that when properly trained using our new dataset, this neural network can already handle dynamic scenes to some extent.
Multi-level Similarity Learning for Low-Shot Recognition
Low-shot learning indicates the ability to recognize unseen objects based on very limited labeled training samples, which simulates human visual intelligence.
MVP-Net: Multi-view FPN with Position-aware Attention for Deep Universal Lesion Detection
In this paper, we propose to incorporate domain knowledge in clinical practice into the model design of universal lesion detectors.
Ranked #8 on
Medical Object Detection
on DeepLesion
A Preliminary Study on Data Augmentation of Deep Learning for Image Classification
Deep learning models have a large number of freeparameters that need to be calculated by effective trainingof the models on a great deal of training data to improvetheir generalization performance.
Heterogeneous Memory Enhanced Multimodal Attention Model for Video Question Answering
In this paper, we propose a novel end-to-end trainable Video Question Answering (VideoQA) framework with three major components: 1) a new heterogeneous memory which can effectively learn global context information from appearance and motion features; 2) a redesigned question memory which helps understand the complex semantics of question and highlights queried subjects; and 3) a new multimodal fusion layer which performs multi-step reasoning by attending to relevant visual and textual hints with self-updated attention.
Ranked #29 on
Visual Question Answering (VQA)
on MSRVTT-QA
Dense 3D Facial Reconstruction from a Single Depth Image in Unconstrained Environment
With the increasing demands of applications in virtual reality such as 3D films, virtual Human-Machine Interactions and virtual agents, the analysis of 3D human face analysis is considered to be more and more important as a fundamental step for those virtual reality tasks.
Beyond Face Rotation: Global and Local Perception GAN for Photorealistic and Identity Preserving Frontal View Synthesis
This paper proposes a Two-Pathway Generative Adversarial Network (TP-GAN) for photorealistic frontal view synthesis by simultaneously perceiving global structures and local details.
A Distribution-based Model to Learn Bilingual Word Embeddings
We introduce a distribution based model to learn bilingual word embeddings from monolingual data.
DeMeshNet: Blind Face Inpainting for Deep MeshFace Verification
The occlusions incurred by random meshes severely degenerate the performance of face verification systems, which raises the MeshFace verification problem between MeshFace and daily photos.
Adaptive Algorithm and Platform Selection for Visual Detection and Tracking
In this paper, we focus on this problem and propose a framework to adaptively select the "best" algorithm-parameter combination and the computation platform under performance and cost constraints at design time, and adapt the algorithms at runtime based on real-time inputs.
