Search Results for author:
Found 21 papers, 6 papers with code
Efficiency in Focus: LayerNorm as a Catalyst for Fine-tuning Medical Visual Language Pre-trained Models
In the realm of Medical Visual Language Models (Med-VLMs), the quest for universal efficient fine-tuning mechanisms remains paramount, especially given researchers in interdisciplinary fields are often extremely short of training resources, yet largely unexplored.
Correlation-Decoupled Knowledge Distillation for Multimodal Sentiment Analysis with Incomplete Modalities
Specifically, we present a sample-level contrastive distillation mechanism that transfers comprehensive knowledge containing cross-sample correlations to reconstruct missing semantics.
De-confounded Data-free Knowledge Distillation for Handling Distribution Shifts
Data-Free Knowledge Distillation (DFKD) is a promising task to train high-performance small models to enhance actual deployment without relying on the original training data.
Can LLMs' Tuning Methods Work in Medical Multimodal Domain?
We show the different impacts of fine-tuning methods for large models on medical VLMs and develop the most efficient ways to fine-tune medical VLP models.
Robust Emotion Recognition in Context Debiasing
Following the causal graph, CLEF introduces a non-invasive context branch to capture the adverse direct effect caused by the context bias.
Towards Multimodal Human Intention Understanding Debiasing via Subject-Deconfounding
Multimodal intention understanding (MIU) is an indispensable component of human expression analysis (e. g., sentiment or humor) from heterogeneous modalities, including visual postures, linguistic contents, and acoustic behaviors.
Towards Multimodal Sentiment Analysis Debiasing via Bias Purification
In the inference phase, given a factual multimodal input, MCIS imagines two counterfactual scenarios to purify and mitigate these biases.
HandGCAT: Occlusion-Robust 3D Hand Mesh Reconstruction from Monocular Images
KGC extracts hand prior information from 2D hand pose by graph convolution.
An objective comparison of methods for augmented reality in laparoscopic liver resection by preoperative-to-intraoperative image fusion
A total of 6 teams from 4 countries participated, whose proposed methods were evaluated on 16 images and two preoperative 3D models from two patients.
MISS: A Generative Pretraining and Finetuning Approach for Med-VQA
However, most methods in the medical field treat VQA as an answer classification task which is difficult to transfer to practical application scenarios.
CPR-Coach: Recognizing Composite Error Actions based on Single-class Training
For the first time, this paper constructs a vision-based system to complete error action recognition and skill assessment in CPR.
AIDE: A Vision-Driven Multi-View, Multi-Modal, Multi-Tasking Dataset for Assistive Driving Perception
Driver distraction has become a significant cause of severe traffic accidents over the past decade.
Human 3D Avatar Modeling with Implicit Neural Representation: A Brief Survey
This paper comprehensively reviews the application of implicit neural representation in human body modeling.
Context De-confounded Emotion Recognition
However, a long-overlooked issue is that a context bias in existing datasets leads to a significantly unbalanced distribution of emotional states among different context scenarios.
Towards Simultaneous Segmentation of Liver Tumors and Intrahepatic Vessels via Cross-attention Mechanism
Accurate visualization of liver tumors and their surrounding blood vessels is essential for noninvasive diagnosis and prognosis prediction of tumors.
Achieving a Given Financial Goal with Optimal Deferred Term Insurance Purchasing Policy
It is worth noting that when m=0, n \rightarrow \infty, our problem is equivalent to achieving the just mentioned bequest goal by purchasing whole life insurance, at which point the maximum probability and the life insurance purchasing strategies we provide are consistent with those in \cite{Bayraktar2014, Bayraktar2016}.
CA-SpaceNet: Counterfactual Analysis for 6D Pose Estimation in Space
Considering that the pose estimator is sensitive to background interference, this paper proposes a counterfactual analysis framework named CASpaceNet to complete robust 6D pose estimation of the spaceborne targets under complicated background.
A Survey of Video-based Action Quality Assessment
Most of the existing work focuses on sports and medical care.
TSA-Net: Tube Self-Attention Network for Action Quality Assessment
Specifically, we introduce a single object tracker into AQA and propose the Tube Self-Attention Module (TSA), which can efficiently generate rich spatio-temporal contextual information by adopting sparse feature interactions.
Sample Efficient Imitation Learning via Reward Function Trained in Advance
Our method, which we call \textit{Model Reward Function Based Imitation Learning} (MRFIL), uses an ensemble dynamic model as a reward function, what is trained with expert demonstrations.
A Unified Joint Matrix Factorization Framework for Data Integration
In this paper, we introduce a sparse multiple relationship data regularized joint matrix factorization (JMF) framework and two adapted prediction models for pattern recognition and data integration.
