105 citations · 112 across the 12 of their papers we have counts for
12 papers
PromptPath: Prompt-Adaptive Computational Pathways for In-Context Learning
Hangrui Zhang, Feifei Shao, Yawei Luo +6
In-context learning (ICL) has attracted increasing attention for enabling models to perform new tasks using only a few ``input--output'' prompt examples. However, existing approach…
MICAS: Multi-grained In-Context Adaptive Sampling for 3D Point Cloud Processing
Feifei Shao, Ping Liu, Zhao Wang +3
Point cloud processing (PCP) encompasses tasks like reconstruction, denoising, registration, and segmentation, each often requiring specialized models to address unique task charac…
Triple Correlations-Guided Label Supplementation for Unbiased Video Scene Graph Generation
Wenqing Wang, Kaifeng Gao, Yawei Luo +5
Video-based scene graph generation (VidSGG) is an approach that aims to represent video content in a dynamic graph by identifying visual entities and their relationships. Due to th…
Generating Reliable Pixel-Level Labels for Source Free Domain Adaptation
Gabriel Tjio, Ping Liu, Yawei Luo +2
This work addresses the challenging domain adaptation setting in which knowledge from the labelled source domain dataset is available only from the pretrained black-box segmentatio…
Counterfactual Co-occurring Learning for Bias Mitigation in Weakly-supervised Object Localization
Feifei Shao, Yawei Luo, Lei Chen +4
Contemporary weakly-supervised object localization (WSOL) methods have primarily focused on addressing the challenge of localizing the most discriminative region while largely over…
Taking A Closer Look at Visual Relation: Unbiased Video Scene Graph Generation with Decoupled Label Learning
Wenqing Wang, Yawei Luo, Zhiqing Chen +4
Current video-based scene graph generation (VidSGG) methods have been found to perform poorly on predicting predicates that are less represented due to the inherent biased distribu…
Knowledge-guided Causal Intervention for Weakly-supervised Object Localization
Feifei Shao, Yawei Luo, Fei Gao +2
Previous weakly-supervised object localization (WSOL) methods aim to expand activation map discriminative areas to cover the whole objects, yet neglect two inherent challenges when…
Bidirectional Self-Training with Multiple Anisotropic Prototypes for Domain Adaptive Semantic Segmentation
Yulei Lu, Yawei Luo, Li Zhang +3
A thriving trend for domain adaptive segmentation endeavors to generate the high-quality pseudo labels for target domain and retrain the segmentor on them. Under this self-training…
Local-Global Context Aware Transformer for Language-Guided Video Segmentation
Chen Liang, Wenguan Wang, Tianfei Zhou +3
We explore the task of language-guided video segmentation (LVS). Previous algorithms mostly adopt 3D CNNs to learn video representation, struggling to capture long-term context and…
Active Learning for Point Cloud Semantic Segmentation via Spatial-Structural Diversity Reasoning
Feifei Shao, Yawei Luo, Ping Liu +4
The expensive annotation cost is notoriously known as the main constraint for the development of the point cloud semantic segmentation technique. Active learning methods endeavor t…
Unsupervised Domain Adaptive Person Re-Identification via Human Learning Imitation
Yang Peng, Ping Liu, Yawei Luo +3
Unsupervised domain adaptive person re-identification has received significant attention due to its high practical value. In past years, by following the clustering and finetuning…
Contrastive Video-Language Segmentation
Chen Liang, Yawei Luo, Yu Wu +1
We focus on the problem of segmenting a certain object referred by a natural language sentence in video content, at the core of formulating a pinpoint vision-language relation. Whi…