Adaptive CLIP for open-domain 3D model retrieval
Authors:
- Dan SongDSDan Song
- Zekai QiangZQZekai Qiang
- Chumeng ZhangCZChumeng Zhang
- Lanjun WangLWLanjun Wang
- Qiong LiuQLQiong Liu
- You YangYYYou Yang
- An-An LiuALAn-An Liu
- 29 November 2024
- journal article
- Published by Elsevier in Information Processing & Management
- Vol. 62 (2)
Abstract
No abstract availableFunding Information
- Tianjin Municipal Natural Science Foundation (23JCQNJC01520, 23JCQNJC01980)
- Natural Science Foundation of Tianjin Municipal Science and Technology Commission
- National Natural Science Foundation of China (U23A20320, 62202329, 62425307, U21B2024)
This publication has 35 references indexed in Scilit:
- MeshCLIP: Efficient cross-modal information processing for 3D mesh data in zero/few-shot learningInformation Processing & Management, 2023
- KRL_MLCCL: Multi-label classification based on contrastive learning for knowledge representation learning under open worldInformation Processing & Management, 2023
- Instance-prototype similarity consistency for unsupervised 2D image-based 3D model retrievalInformation Processing & Management, 2023
- Joint contrastive triple-learning for deep multi-view clusteringInformation Processing & Management, 2023
- CLIP4Clip: An empirical study of CLIP for end to end video clip retrieval and captioningNeurocomputing, 2022
- 3D Reconstruction of Laparoscope Images With Contrastive Learning MethodsIEEE Access, 2022
- Instance Level Affinity-Based Transfer for Unsupervised Domain Adaptation2021
- Momentum Contrast for Unsupervised Visual Representation Learning2020
- Self-Supervised Domain Adaptation for Computer Vision TasksIEEE Access, 2019
- Joint Geometrical and Statistical Alignment for Visual Domain Adaptation2017