Metraipolis › archive › dc_f901fcb62670
G3Ego: Gaze-Guided Graphs for Egocentric Action Understanding — arXiv:2608.20157
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.20157
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T12:04:49.507Z
- SHA-256 of the archived text
81d4aba7b96fdd9a756181474687f689f2069574093be17acdc1edeb7fc2d368- Stable URL of this page
https://metraipolis.com/documento/dc_f901fcb62670
How to cite
G3Ego: Gaze-Guided Graphs for Egocentric Action Understanding — arXiv:2608.20157 — arXiv (en), https://arxiv.org/abs/2608.20157 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f901fcb62670 (Metraipolis archive dc_f901fcb62670, sha256 81d4aba7b96fdd9a756181474687f689f2069574093be17acdc1edeb7fc2d368)
BibTeX
@misc{dcf901fcb62670,
title = {G3Ego: Gaze-Guided Graphs for Egocentric Action Understanding — arXiv:2608.20157},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.20157},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f901fcb62670; sha256 81d4aba7b96fdd9a756181474687f689f2069574093be17acdc1edeb7fc2d368},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.20157. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Egocentric action understanding is often addressed using large video models pretrained on extensive exocentric datasets. However, many first-person actions depend on a small number of hand-object interactions involving only a few relevant entities. We propose G3Ego, a graph-based framework for egocentric action understanding that uses gaze as a structural cue to identify action-relevant entities in the scene. From sparsely sampled frames, G3Ego constructs action scene graphs from vision-language descriptions, grounded objects, and hand cues, and then prunes irrelevant entities using the camera wearer's gaze. The resulting graph embeddings are temporally aggregated for action recognition and anticipation. Unlike prior work that uses gaze primarily as an auxiliary modality or attention signal, G3Ego incorporates gaze directly into graph construction, producing efficient and interpretable representations focused on action-relevant interactions. Experiments on EGTEA Gaze+ and MECCANO show that G3Ego achieves competitive performance compared with video-based approaches and consistently improves Macro-F1 under class-imbalanced evaluation, while avoiding reliance on computationally expensive video pretraining. These results demonstrate the effectiveness of gaze-guided graph representations for egocentric action understanding. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-21 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.20157 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-18T12:01:57.744Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).