Metraipolis › archive › dc_80844e64b486

Investigating Query-Insensitive Behavior in Spatio-Temporal Video Grounding — arXiv:2610.06018

Source
arXiv
Original
https://arxiv.org/abs/2610.06018
License (as archived)
CC0-1.0
Archived
2026-10-06T05:27:21.030Z
SHA-256 of the archived text
b13c998970d19319ec32746f708fc0e48a00f7ad4db1aae23e68e0c91c480999
Stable URL of this page
https://metraipolis.com/documento/dc_80844e64b486

How to cite

Investigating Query-Insensitive Behavior in Spatio-Temporal Video Grounding — arXiv:2610.06018 — arXiv, https://arxiv.org/abs/2610.06018 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_80844e64b486 (Metraipolis archive dc_80844e64b486, sha256 b13c998970d19319ec32746f708fc0e48a00f7ad4db1aae23e68e0c91c480999)
BibTeX
@misc{dc80844e64b486,
  title = {Investigating Query-Insensitive Behavior in Spatio-Temporal Video Grounding — arXiv:2610.06018},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.06018},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_80844e64b486; sha256 b13c998970d19319ec32746f708fc0e48a00f7ad4db1aae23e68e0c91c480999},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.06018. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Spatio-temporal video grounding (STVG) aims to localize objects or events described by natural language queries in both space and time. Existing STVG models are typically trained and evaluated under the assumption that each query is relevant to the input video. In this work, we challenge this assumption by studying the behavior of state-of-the-art STVG models under irrelevant queries and missing textual input. Our experiments show that current models can still produce plausible spatio-temporal predictions even when the query is unrelated to the video or removed entirely. We further analyze HCSTVG-v2 and VidSTG to identify dataset regularities that may encourage such query-insensitive behavior. Our study highlights an underexplored limitation of STVG models and motivates negative-aware evaluation protocols and architectures that explicitly assess query relevance.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2610.06018 — 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 2026-10-06T05:24:06.102Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).