Metraipolis › archive › dc_7ef6e3d50df9
Language-Augmented Video Action Anticipation: Design Fundamentals, Benchmarks, and Open Challenges — arXiv:2609.31665
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.31665
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T23:50:25.370Z
- SHA-256 of the archived text
361b8b4fdb1260834574f55c78a618e38806c608d67cbc5b21a0b94231c7f698- Stable URL of this page
https://metraipolis.com/documento/dc_7ef6e3d50df9
How to cite
Language-Augmented Video Action Anticipation: Design Fundamentals, Benchmarks, and Open Challenges — arXiv:2609.31665 — arXiv (en), https://arxiv.org/abs/2609.31665 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7ef6e3d50df9 (Metraipolis archive dc_7ef6e3d50df9, sha256 361b8b4fdb1260834574f55c78a618e38806c608d67cbc5b21a0b94231c7f698)
BibTeX
@misc{dc7ef6e3d50df9,
title = {Language-Augmented Video Action Anticipation: Design Fundamentals, Benchmarks, and Open Challenges — arXiv:2609.31665},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.31665},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7ef6e3d50df9; sha256 361b8b4fdb1260834574f55c78a618e38806c608d67cbc5b21a0b94231c7f698},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.31665. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Action anticipation predicts future human actions from partial video under incomplete context and temporal uncertainty. Recent systems introduce large language models (LLMs), vision-language models (VLMs), or language-derived semantics at different stages, but reported gains are difficult to interpret when task formulation, visual pretraining, supervision, decoder design, and evaluation code change simultaneously. The central contribution of this review is an evidence-aware design map that crosses task regime with the point at which language-derived information intervenes. We characterise task regimes along six axes. These axes organise the literature into five broad task families: single-action, sequence, object-interaction, cross-view, and planning-oriented settings. C1-C3 locate interventions in context construction, goal/intention modelling, and future decoding, while C4 is treated as an adjacent, emerging grounding/executability extension. Unlike a generic processing pipeline, the map links each intervention to an appropriate counterfactual, failure diagnosis, and permissible evidence claim. Supporting contributions include a protocol-level audit of Ego4D-LTA and EPIC-KITCHENS-100, a multidimensional evidence profile, and the Backbone-Aware Comparison and Ablation Protocol (BCAP). The unresolved EK-100 record is treated as a reporting-comparability case study and is not used as a leaderboard. Evidence for LLM benefits, goal ambiguity, and horizon effects is therefore formulated as testable hypotheses requiring matched validation, not as causal conclusions. The accompanying package contains the coded evidence, source locators, protocol metadata, and versioned catalogue used in the review. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-29 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.31665 — 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 2026-10-07T23:29:26.856Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).