Search Results for author:
Found 26 papers, 7 papers with code
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 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.
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.
HandGCAT: Occlusion-Robust 3D Hand Mesh Reconstruction from Monocular Images
KGC extracts hand prior information from 2D hand pose by graph convolution.
Delving into Decision-based Black-box Attacks on Semantic Segmentation
We conduct adversarial robustness evaluation on 5 models from Cityscapes and ADE20K under 8 attacks.
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.
Improving Generalization in Visual Reinforcement Learning via Conflict-aware Gradient Agreement Augmentation
In particular, CG2A develops a Gradient Agreement Solver to adaptively balance the varying gradient magnitudes, and introduces a Soft Gradient Surgery strategy to alleviate the gradient conflicts.
Sampling to Distill: Knowledge Transfer from Open-World Data
Then, we introduce a low-noise representation to alleviate the domain shifts and build a structured relationship of multiple data examples to exploit data knowledge.
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.
Spatio-Temporal Domain Awareness for Multi-Agent Collaborative Perception
In this paper, we propose SCOPE, a novel collaborative perception framework that aggregates the spatio-temporal awareness characteristics across on-road agents in an end-to-end manner.
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.
Out of Thin Air: Exploring Data-Free Adversarial Robustness Distillation
Adversarial Robustness Distillation (ARD) is a promising task to solve the issue of limited adversarial robustness of small capacity models while optimizing the expensive computational costs of Adversarial Training (AT).
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.
Efficient Decision-based Black-box Patch Attacks on Video Recognition
First, STDE introduces target videos as patch textures and only adds patches on keyframes that are adaptively selected by temporal difference.
A novel efficient Multi-view traffic-related object detection framework
With the rapid development of intelligent transportation system applications, a tremendous amount of multi-view video data has emerged to enhance vehicle perception.
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.
Adversarial Contrastive Distillation with Adaptive Denoising
To this end, we propose a novel structured ARD method called Contrastive Relationship DeNoise Distillation (CRDND).
Generalized Video Anomaly Event Detection: Systematic Taxonomy and Comparison of Deep Models
Video Anomaly Detection (VAD) serves as a pivotal technology in the intelligent surveillance systems, enabling the temporal or spatial identification of anomalous events within videos.
Boosting the Transferability of Adversarial Attacks with Global Momentum Initialization
To tackle these issues, we propose Global Momentum Initialization (GI) to suppress gradient elimination and help search for the global optimum.
Learning Appearance-motion Normality for Video Anomaly Detection
Video anomaly detection is a challenging task in the computer vision community.
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.
