Clip-cluster: Clip-guided attribute hallucination for face clustering

S Shen, W Li, X Wang, D Zhang… - Proceedings of the …, 2023 - openaccess.thecvf.com
One of the most important yet rarely studied challenges for supervised face clustering is the
large intra-class variance caused by different face attributes such as age, pose, and …

Hireview: Hierarchical taxonomy-driven automatic literature review generation

Y Hu, Z Li, Z Zhang, C Ling, R Kanjiani, B Zhao… - arxiv preprint arxiv …, 2024 - arxiv.org
In this work, we present HiReview, a novel framework for hierarchical taxonomy-driven
automatic literature review generation. With the exponential growth of academic documents …

Hierarchical graph pattern understanding for zero-shot video object segmentation

G Pei, F Shen, Y Yao, T Chen, XS Hua… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
The optical flow guidance strategy is ideal for obtaining motion information of objects in the
video. It is widely utilized in video segmentation tasks. However, existing optical flow-based …

DCOM-GNN: A deep clustering optimization method for graph neural networks

H Yang, J Wang, R Duan, C Yan - Knowledge-Based Systems, 2023 - Elsevier
Deep clustering plays an important role in data analysis, and with the prevalence of graph
data nowadays, various deep clustering models on graph are constantly proposed …

Deep Incomplete Multi-view Clustering via Multi-level Imputation and Contrastive Alignment

Z Wang, Y Du, Y Wang, R Ning, L Li - Neural Networks, 2025 - Elsevier
Deep incomplete multi-view clustering (DIMVC) aims to enhance clustering performance by
capturing consistent information from incomplete multiple views using deep models. Most …

VertexSerum: Poisoning Graph Neural Networks for Link Inference

R Ding, S Duan, X Xu, Y Fei - Proceedings of the IEEE/CVF …, 2023 - openaccess.thecvf.com
Graph neural networks (GNNs) have brought superb performance to various applications
utilizing graph structural data, such as social analysis and fraud detection. The graph links …

HG-CAD: hierarchical graph learning for material prediction and recommendation in computer-aided design

S Bian, D Grandi, T Liu… - Journal of …, 2024 - asmedigitalcollection.asme.org
To support intelligent computer-aided design (CAD), we introduce a machine learning
architecture, namely HG-CAD, that recommends assembly body material through joint …

Equivariant graph hierarchy-based neural networks

J Han, W Huang, T Xu, Y Rong - Advances in Neural …, 2022 - proceedings.neurips.cc
Abstract Equivariant Graph neural Networks (EGNs) are powerful in characterizing the
dynamics of multi-body physical systems. Existing EGNs conduct flat message passing …

Neural trees for learning on graphs

R Talak, S Hu, L Peng… - Advances in Neural …, 2021 - proceedings.neurips.cc
Abstract Graph Neural Networks (GNNs) have emerged as a flexible and powerful approach
for learning over graphs. Despite this success, existing GNNs are constrained by their local …

Comprehensive relationship reasoning for composed query based image retrieval

F Zhang, M Yan, J Zhang, C Xu - Proceedings of the 30th ACM …, 2022 - dl.acm.org
Composed Query Based Image Retrieval (CQBIR) aims at searching images relevant to a
composed query, ie, a reference image together with a modifier text. Compared with …