Related references
Note: Only part of the references are listed.
Proceedings Paper
Computer Science, Artificial Intelligence
Haojie Zhao et al.
Summary: This paper proposes a simple yet effective representation learning method for visual object tracking. By utilizing an encoder-decoder architecture, the method achieves visual appearance reconstruction and target appearance transfer, resulting in more discriminative learned representations.
2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2023)
Proceedings Paper
Computer Science, Artificial Intelligence
Shenyuan Gao et al.
Summary: Compared with previous two-stream trackers, the recent one-stream tracking pipeline allows earlier interaction between the template and search region, resulting in remarkable performance improvement. To address the issue of insufficient discriminative feature representations, we propose a generalized relation modeling method based on adaptive token division.
2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2023)
Proceedings Paper
Computer Science, Artificial Intelligence
Hao Ren et al.
Summary: Discriminative representation is crucial for maintaining unique identifiers for each target in multiple object tracking. Some recent methods have extracted features from the bounding box region or center point as identity embeddings, but these global representations become unreliable when targets are occluded. This study proposes exploring diverse fine-grained representation that comprehensively describes appearance from global and local perspectives.
2023 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2023)
Proceedings Paper
Computer Science, Artificial Intelligence
Zhuang Liu et al.
Summary: The development of visual recognition has gone through stages from ConvNets to ViTs and then to hybrid approaches. In this work, the design of a pure ConvNet is reexamined and several key components are discovered, resulting in the construction of the ConvNeXt model series. These models compete with Transformers in terms of accuracy and performance while maintaining the simplicity and efficiency of ConvNets.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2022)
Article
Computer Science, Artificial Intelligence
Lianghua Huang et al.
Summary: GOT-10k is a large tracking database that covers over 560 classes of moving objects and 87 motion patterns, providing a unified training and evaluation platform for tracker development. Additionally, the introduction of a one-shot protocol for tracker evaluation avoids biased results towards familiar objects and promotes generalization in tracker development.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2021)
Article
Computer Science, Artificial Intelligence
Yuankai Qi et al.
Article
Computer Science, Artificial Intelligence
Martin Danelljan et al.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2017)
Proceedings Paper
Computer Science, Artificial Intelligence
Esteban Real et al.
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017)
(2017)
Proceedings Paper
Computer Science, Artificial Intelligence
Francois Chollet
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017)
(2017)
Article
Computer Science, Artificial Intelligence
Joao F. Henriques et al.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2015)