Referred by Multi-Modality: A Unified Temporal Transformer for Video Object Segmentation

被引:0
|
作者
Yan, Shilin [1 ,2 ]
Zhang, Renrui [2 ,3 ]
Guo, Ziyu [3 ]
Chen, Wenchao [1 ]
Zhang, Wei [1 ]
Li, Hongyang [2 ]
Qiao, Yu [2 ]
Dong, Hao [4 ,5 ]
He, Zhongjiang [6 ]
Gao, Peng [2 ]
机构
[1] Fudan Univ, Sch Comp Sci, Shanghai, Peoples R China
[2] Shanghai Artificial Intelligence Lab, Shanghai, Peoples R China
[3] Chinese Univ Hong Kong, Hong Kong, Peoples R China
[4] Peking Univ, Sch CS, Beijing, Peoples R China
[5] PKU agibot Lab, Beijing, Peoples R China
[6] China Telecom Corp Ltd, Data&AI Technol Co, Beijing, Peoples R China
基金
中国国家自然科学基金;
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Recently, video object segmentation (VOS) referred by multi-modal signals, e.g., language and audio, has evoked increasing attention in both industry and academia. It is challenging for exploring the semantic alignment within modalities and the visual correspondence across frames. However, existing methods adopt separate network architectures for different modalities, and neglect the inter-frame temporal interaction with references. In this paper, we propose MUTR, a Multi-modal Unified Temporal transformer for Referring video object segmentation. With a unified framework for the first time, MUTR adopts a DETR-style transformer and is capable of segmenting video objects designated by either text or audio reference. Specifically, we introduce two strategies to fully explore the temporal relations between videos and multi-modal signals. Firstly, for low-level temporal aggregation before the transformer, we enable the multi-modal references to capture multi-scale visual cues from consecutive video frames. This effectively endows the text or audio signals with temporal knowledge and boosts the semantic alignment between modalities. Secondly, for high-level temporal interaction after the transformer, we conduct inter-frame feature communication for different object embeddings, contributing to better object-wise correspondence for tracking along the video. On Ref-YouTube-VOS and AVSBench datasets with respective text and audio references, MUTR achieves +4.2% and +8.7% J&F improvements to state-of-the-art methods, demonstrating our significance for unified multi-modal VOS. Code is released at https://github.com/OpenGVLab/MUTR.
引用
收藏
页码:6449 / 6457
页数:9
相关论文
共 50 条
  • [41] Video Semantic Segmentation via Sparse Temporal Transformer
    Li, Jiangtong
    Wang, Wentao
    Chen, Junjie
    Niu, Li
    Si, Jianlou
    Qian, Chen
    Zhang, Liqing
    PROCEEDINGS OF THE 29TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA, MM 2021, 2021, : 59 - 68
  • [42] Multi-Modality Image Fusion and Object Detection Based on Semantic Information
    Liu, Yong
    Zhou, Xin
    Zhong, Wei
    ENTROPY, 2023, 25 (05)
  • [43] Contrastive Trustworthy Prototype Learning for multi-modality myocardial pathology segmentation
    Liu, Jingjing
    Wei, Ao
    Cao, Lijuan
    He, Xiao
    Tang, Chang
    APPLIED SOFT COMPUTING, 2025, 173
  • [44] Multi-modality MRI Arbitrary Transformation using Unified Generative Adversarial Networks
    Lei, Yang
    Fu, Yabo
    Mao, Hui
    Curran, Walter J.
    Liu, Tian
    Yang, Xiaofeng
    MEDICAL IMAGING 2020: IMAGE PROCESSING, 2021, 11313
  • [45] XlanV Model with Adaptively Multi-Modality Feature Fusing for Video Captioning
    Huang, Yiqing
    Cai, Qiuyu
    Xu, Siyu
    Chen, Jiansheng
    MM '20: PROCEEDINGS OF THE 28TH ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA, 2020, : 4600 - 4604
  • [46] Towards Unified Modality Understanding for Alzheimer's Disease Diagnosis Using Incomplete Multi-modality Data
    Han, Kangfu
    Zhao, Fenqiang
    Zhu, Dajiang
    Liu, Tianming
    Yang, Feng
    Li, Gang
    MACHINE LEARNING IN MEDICAL IMAGING, MLMI 2023, PT II, 2024, 14349 : 184 - 193
  • [47] Multi-scale patch and multi-modality atlases for whole heart segmentation of MRI
    Zhuang, Xiahai
    Shen, Juan
    MEDICAL IMAGE ANALYSIS, 2016, 31 : 77 - 87
  • [48] ADVIT: VISION TRANSFORMER ON MULTI-MODALITY PET IMAGES FOR ALZHEIMER DISEASE DIAGNOSIS
    Xing, Xin
    Liang, Gongbo
    Zhang, Yu
    Khanal, Subash
    Lin, Ai-Ling
    Jacobs, Nathan
    2022 IEEE INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING (IEEE ISBI 2022), 2022,
  • [49] Learning spatiotemporal relationships with a unified framework for video object segmentation
    Mei, Jianbiao
    Wang, Mengmeng
    Yang, Yu
    Li, Zizhang
    Liu, Yong
    APPLIED INTELLIGENCE, 2024, 54 (08) : 6138 - 6153
  • [50] Structural Transformer with Region Strip Attention for Video Object Segmentation
    Guan, Qingfeng
    Fang, Hao
    Han, Chenchen
    Wang, Zhicheng
    Zhang, Ruiheng
    Zhang, Yitian
    Lu, Xiankai
    NEUROCOMPUTING, 2024, 596