Search Results for author:
Found 24 papers, 4 papers with code
TRRNet: Tiered Relation Reasoning for Compositional Visual Question Answering
Compositional visual question answering requires reasoning over both semantic and geometry object relations.
HLV-1K: A Large-scale Hour-Long Video Benchmark for Time-Specific Long Video Understanding
Multimodal large language models have become a popular topic in deep visual understanding due to many promising real-world applications.
Dataset Awareness is not Enough: Implementing Sample-level Tail Encouragement in Long-tailed Self-supervised Learning
However, most of these approaches focus on the joint optimization of all samples in the dataset or on constraining the category distribution, with little attention given to whether each individual sample is optimally guided during training.
Causally-Aware Unsupervised Feature Selection Learning
Additionally, previous graph-based methods fail to account for the differing impacts of non-causal and causal features in constructing the similarity graph, which leads to false links in the generated graph.
From Seconds to Hours: Reviewing MultiModal Large Language Models on Comprehensive Long Video Understanding
Given the diverse nature of visual data, MultiModal Large Language Models (MM-LLMs) exhibit variations in model designing and training for understanding images, short videos, and long videos.
Adaptive Collaborative Correlation Learning-based Semi-Supervised Multi-Label Feature Selection
Then, the instance correlation and label correlation are integrated into the proposed regression model to adaptively learn both the sample similarity graph and the label similarity graph, which mutually enhance feature selection performance.
Learning Contrastive Feature Representations for Facial Action Unit Detection
For the Facial Action Unit (AU) detection task, accurately capturing the subtle facial differences between distinct AUs is essential for reliable detection.
Colorectal Polyp Segmentation in the Deep Learning Era: A Comprehensive Survey
Colorectal polyp segmentation (CPS), an essential problem in medical image analysis, has garnered growing research attention.
Unified View Imputation and Feature Selection Learning for Incomplete Multi-view Data
UNIFIER explores the local structure of multi-view data by adaptively learning similarity-induced graphs from both the sample and feature spaces.
Multimodal Sentiment Analysis with Missing Modality: A Knowledge-Transfer Approach
Multimodal sentiment analysis aims to identify the emotions expressed by individuals through visual, language, and acoustic cues.
A Pre-trained Data Deduplication Model based on Active Learning
In the era of big data, the issue of data quality has become increasingly prominent.
C$^{2}$IMUFS: Complementary and Consensus Learning-based Incomplete Multi-view Unsupervised Feature Selection
Besides, learning the complete similarity graph, as an important promising technology in existing MUFS methods, cannot achieve due to the missing views.
Self-Training Vision Language BERTs with a Unified Conditional Model
We use the labeled image data to train a teacher model and use the trained model to generate pseudo captions on unlabeled image data.
Expanding Large Pre-Trained Unimodal Models With Multimodal Information Injection for Image-Text Multimodal Classification
Through the proposed MI2P unit, we can inject the language information into the vision backbone by attending the word-wise textual features to different visual channels, as well as inject the visual information into the language backbone by attending the channel-wise visual features to different textual words.
Progressive Modality Reinforcement for Human Multimodal Emotion Recognition From Unaligned Multimodal Sequences
In turn, it also collects the reinforced features from each modality and uses them to generate a reinforced common message.
Attention Is Not Enough: Mitigating the Distribution Discrepancy in Asynchronous Multimodal Sequence Fusion
To this end, both the marginal distribution and the elements with high-confidence correlations are aligned over the common space of the query and key vectors which are computed from different modalities.
Adaptive Graph-based Generalized Regression Model for Unsupervised Feature Selection
Other existing methods choose the discriminative features with low redundancy by constructing the graph matrix on the original feature space.
Learning unbiased zero-shot semantic segmentation networks via transductive transfer
Our method assumes that both the source images with full pixel-level labels and unlabeled target images are available during training.
Weakly-supervised Domain Adaption for Aspect Extraction via Multi-level Interaction Transfer
Specifically, the aspect category information is used to construct pivot knowledge for transfer with assumption that the interactions between sentence-level aspect category and token-level aspect terms are invariant across domains.
Cross-Domain Semantic Segmentation via Domain-Invariant Interactive Relation Transfer
Our method mainly focuses on constructing pivot information that is common knowledge shared across domains as a bridge to promote the adaptation of semantic segmentation model from synthetic domains to real-world domains.
Ranked #25 on
Domain Adaptation
on SYNTHIA-to-Cityscapes
Incorporating Multiple Cluster Centers for Multi-Label Learning
In this article, we propose to leverage the data augmentation technique to improve the performance of multi-label learning.
Learning Cross-domain Semantic-Visual Relationships for Transductive Zero-Shot Learning
Zero-Shot Learning (ZSL) learns models for recognizing new classes.
Constructing Self-motivated Pyramid Curriculums for Cross-Domain Semantic Segmentation: A Non-Adversarial Approach
We propose a new approach, called self-motivated pyramid curriculum domain adaptation (PyCDA), to facilitate the adaptation of semantic segmentation neural networks from synthetic source domains to real target domains.
Ranked #14 on
Image-to-Image Translation
on SYNTHIA-to-Cityscapes
MiniMax Entropy Network: Learning Category-Invariant Features for Domain Adaptation
Unlike most existing approaches which employ a generator to deal with domain difference, MMEN focuses on learning the categorical information from unlabeled target samples with the help of labeled source samples.
