Solve the Puzzle of Instance Segmentation in Videos: A Weakly Supervised Framework With Spatio-Temporal Collaboration

Yan, Liqi; Wang, Qifan; Ma, Siqi; Wang, Jingang; Yu, Changbin

doi:10.1109/tcsvt.2022.3202574

Cited by 59 publications

(2 citation statements)

References 94 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Extensive evaluations demonstrate the superior performance of PointTrackV2 on various datasets, also discussing the applicability of this method in areas beyond tracking, such as detailed image classification, 2D pose estimation and object segmentation in videos. Liqi Yan et al [52] (STC-Seg) present a novel framework for instance segmentation in videos under a weakly supervised approach. Using unsupervised depth estimation and optical flow, STC-Seg generates efficient pseudo-labels to train deep networks, focusing on the accurate generation of instance masks.…”

Section: Multiple Object Tracking and Segmentationmentioning

confidence: 99%

“…The expansion to multiple objects tracking and segmentation, as demonstrated by Zhenbo Xu et al [51] and Liqi Yan et al [52], opens up new possibilities for real-time monitoring and analysis of complex scenes. These techniques, which transform images into more malleable representations such as point clouds, highlight the potential of deep learning to extract and analyze information in an efficient and innovative way.…”

Section: A Object Trackingmentioning

confidence: 99%

See 1 more Smart Citation

Enhancing Image Annotation With Object Tracking and Image Retrieval: A Systematic Review

Fernandes,

Pessoa,

Salgado

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Effective image and video annotation is a fundamental pillar in computer vision and artificial intelligence, crucial for the development of accurate machine learning models. Object tracking and image retrieval techniques are essential in this process, significantly improving the efficiency and accuracy of automatic annotation. This paper systematically investigates object tracking and image acquisition techniques. It explores how these technologies can collectively enhance the efficiency and accuracy of the annotation processes for image and video datasets. Object tracking is examined for its role in automating annotations by tracking objects across video sequences, while image retrieval is evaluated for its ability to suggest annotations for new images based on existing data. The review encompasses diverse methodologies, including advanced neural networks and machine learning techniques, highlighting their effectiveness in various contexts like medical analyses and urban monitoring. Despite notable advancements, challenges such as algorithm robustness and effective human-AI collaboration are identified. This review provides valuable insights into these technologies' current state and future potential in improving image annotation processes, even showing existing applications of these techniques and their full potential when combined.

show abstract

Section: Multiple Object Tracking and Segmentationmentioning

confidence: 99%

Section: A Object Trackingmentioning

confidence: 99%