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
  • [21] Thoracic and Abdominal Atlas Segmentation with Diffeomorphic Multi-Modality Registration
    Schreibmann, E.
    Fox, T.
    Crocker, I.
    MEDICAL PHYSICS, 2011, 38 (06)
  • [22] Multi-Modality Microscopy Image Style Augmentation for Nuclei Segmentation
    Liu, Ye
    Wagner, Sophia J.
    Peng, Tingying
    JOURNAL OF IMAGING, 2022, 8 (03)
  • [23] Video Event Detection via Multi-modality Deep Learning
    Jhuo, I-Hong
    Lee, D. T.
    2014 22ND INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2014, : 666 - 671
  • [24] A software vulnerability detection method based on multi-modality with unified processing
    Cai, Wenjing
    Chen, Junlin
    Yu, Jiaping
    Hu, Wei
    Gao, Lipeng
    INFORMATION AND SOFTWARE TECHNOLOGY, 2025, 182
  • [25] Multi-modality Based Affective Video Summarization for Game Players
    Farooq, Sehar Shahzad
    Aziz, Abdullah
    Mukhtar, Hammad
    Fiaz, Mustansar
    Baek, Ki Yeol
    Choi, Naram
    Yun, Sang Bin
    Kim, Kyung Joong
    Jung, Soon Ki
    FRONTIERS OF COMPUTER VISION, IW-FCV 2021, 2021, 1405 : 59 - 69
  • [26] Concept-Driven Multi-Modality Fusion for Video Search
    Wei, Xiao-Yong
    Jiang, Yu-Gang
    Ngo, Chong-Wah
    IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2011, 21 (01) : 62 - 73
  • [27] A Multi-modality Driven Promptable Transformer for Automated Parapneumonic Effusion Staging
    Chen, Yan
    Liu, Qing
    Xiang, Yao
    PATTERN RECOGNITION AND COMPUTER VISION, PRCV 2023, PT XIII, 2024, 14437 : 248 - 259
  • [28] Siamese Network with Interactive Transformer for Video Object Segmentation
    Lan, Meng
    Zhang, Jing
    He, Fengxiang
    Zhang, Lefei
    THIRTY-SIXTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE / THIRTY-FOURTH CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE / THE TWELVETH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2022, : 1228 - 1236
  • [29] Spatial-Temporal Multi-level Association for Video Object Segmentation
    Miao, Deshui
    Li, Xin
    He, Zhenyu
    Lu, Huchuan
    Yang, Ming-Hsuan
    COMPUTER VISION - ECCV 2024, PT LXVII, 2025, 15125 : 91 - 107
  • [30] UMINet: a unified multi-modality interaction network for RGB-D and RGB-T salient object detection
    Lina Gao
    Ping Fu
    Mingzhu Xu
    Tiantian Wang
    Bing Liu
    The Visual Computer, 2024, 40 : 1565 - 1582