Is Tracking Really More Challenging in First Person Egocentric Vision?
Matteo Dunnhofer, Zaira Manigrasso, Christian Micheloni
Abstract
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.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext ab4cc0be-7dc0-47e6-aa3f-0d7da376c01fBuilds on17
- Learning Spatio-Temporal Transformer for Visual TrackingBin Yan, Houwen Peng, Jianlong Fu, Dong Wang et al.ICCV 2021 · 1,062 citations
- Ego4D: Around the World in 3, 000 Hours of Egocentric VideoKristen Grauman, Andrew Westbury, Eugene Byrne, Zachary Chavis et al.CVPR 2022 · 525 citations
- Associating Objects with Transformers for Video Object SegmentationZongxin Yang, Yunchao Wei, Yi YangNeurIPS 2021 · 398 citations
- Learning Target Candidate Association to Keep Track of What Not to TrackChristoph Mayer, Martin Danelljan, Danda Pani Paudel, Luc Van GoolICCV 2021 · 356 citations
- MOSE: A New Dataset for Video Object Segmentation in Complex ScenesHenghui Ding, Chang Liu, Shuting He, Xudong Jiang et al.ICCV 2023 · 267 citations
Related papers
- EgoEnv: Human-centric environment representations from egocentric videoTushar Nagarajan, Santhosh Kumar Ramakrishnan, Ruta Desai, James Hillis et al.NeurIPS 2023 · 28 citations
- Ego-Only: Egocentric Action Detection without Exocentric TransferringHuiyu Wang, Mitesh Kumar Singh, Lorenzo TorresaniICCV 2023 · 41 citations
- 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 et al.CVPR 2026 · 4 citations
- POV: Prompt-Oriented View-Agnostic Learning for Egocentric Hand-Object Interaction in the Multi-view WorldBoshen Xu, Sipeng Zheng, Qin JinACM MM 2023 · 8 citations
