Is Tracking Really More Challenging in First Person Egocentric Vision?
Matteo Dunnhofer, Zaira Manigrasso, Christian Micheloni
摘要
Visual object tracking and segmentation are becoming fundamental tasks for understanding human activities in egocentric vision. Recent research has benchmarked state-of-the-art methods and concluded that first person egocentric vision presents challenges compared to previously studied domains. However, these claims are based on evaluations conducted across significantly different scenarios. Many of the challenging characteristics attributed to egocentric vision are also present in third person videos of human-object activities. This raises a critical question: how much of the observed performance drop stems from the unique first person viewpoint inherent to egocentric vision versus the domain of human-object activities? To address this question, we introduce a new benchmark study designed to disentangle such factors. Our evaluation strategy enables a more precise separation of challenges related to the first person perspective from those linked to the broader domain of human-object activity understanding. By doing so, we provide deeper insights into the true sources of difficulty in egocentric tracking and segmentation, facilitating more targeted advancements on this task.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了最后一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
它引用的顶会 Paper17
- Learning Spatio-Temporal Transformer for Visual TrackingBin Yan, Houwen Peng, Jianlong Fu, Dong Wang 等ICCV 2021 · 被引用 1,062 次
- Ego4D: Around the World in 3, 000 Hours of Egocentric VideoKristen Grauman, Andrew Westbury, Eugene Byrne, Zachary Chavis 等CVPR 2022 · 被引用 525 次
- Associating Objects with Transformers for Video Object SegmentationZongxin Yang, Yunchao Wei, Yi YangNeurIPS 2021 · 被引用 398 次
- Learning Target Candidate Association to Keep Track of What Not to TrackChristoph Mayer, Martin Danelljan, Danda Pani Paudel, Luc Van GoolICCV 2021 · 被引用 356 次
- MOSE: A New Dataset for Video Object Segmentation in Complex ScenesHenghui Ding, Chang Liu, Shuting He, Xudong Jiang 等ICCV 2023 · 被引用 267 次
相关 Paper
- EgoEnv: Human-centric environment representations from egocentric videoTushar Nagarajan, Santhosh Kumar Ramakrishnan, Ruta Desai, James Hillis 等NeurIPS 2023 · 被引用 28 次
- Ego-Only: Egocentric Action Detection without Exocentric TransferringHuiyu Wang, Mitesh Kumar Singh, Lorenzo TorresaniICCV 2023 · 被引用 41 次
- Ego-Exo: Transferring Visual Representations From Third-Person to First-Person VideosYanghao Li, Tushar Nagarajan, Bo Xiong, Kristen GraumanCVPR 2021
- Ego2Web: A Web Agent Benchmark Grounded in Egocentric VideosShoubin Yu, Lei Shu, Antoine Yang, Yao Fu 等CVPR 2026 · 被引用 4 次
- POV: Prompt-Oriented View-Agnostic Learning for Egocentric Hand-Object Interaction in the Multi-view WorldBoshen Xu, Sipeng Zheng, Qin JinACM MM 2023 · 被引用 8 次
