Metraipolis › archive › dc_187ea8c377cb

DiA: Directional Adapter — arXiv:2611.00029

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.00029
License (as archived)
CC0-1.0
Archived
2026-11-03T11:39:45.548Z
SHA-256 of the archived text
4a3c7a6d6f7843f90e4c29c09ed01590753f35aa59da29647aa34efd2b4fbd0c
Stable URL of this page
https://metraipolis.com/documento/dc_187ea8c377cb

How to cite

DiA: Directional Adapter — arXiv:2611.00029 — arXiv (en), https://arxiv.org/abs/2611.00029 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_187ea8c377cb (Metraipolis archive dc_187ea8c377cb, sha256 4a3c7a6d6f7843f90e4c29c09ed01590753f35aa59da29647aa34efd2b4fbd0c)
BibTeX
@misc{dc187ea8c377cb,
  title = {DiA: Directional Adapter — arXiv:2611.00029},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.00029},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_187ea8c377cb; sha256 4a3c7a6d6f7843f90e4c29c09ed01590753f35aa59da29647aa34efd2b4fbd0c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00029. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Fine-grained action recognition often depends on how an action unfolds over time rather than on appearance alone. Visually similar classes may differ in preparation, execution, or completion phases, making uniformly aggregated temporal context suboptimal. We study this problem under a practical objective: i) improving recognition performance with few tunable parameters, ii) being compute efficient, and iii) using only the readily available video modality. Motivated by this missing temporal observation and the accuracy--compute efficiency--unimodality objective, we propose Directional Adapter (DiA), a parameter-efficient adapter on top of CLIP. DiA formulates temporal specialization into causal and anti-causal directions, allowing past-to-present and future-to-present cues to be modeled differently. To keep this directional modeling parameter- and compute-efficient, both directions use depth-wise temporal convolutions in a compact bottleneck space and are combined through a learnable fusion. DiA achieves state-of-the-art performance among methods using a single video input modality across seven public benchmarks, with only $\sim$3.6M tunable parameters, while also delivering higher throughput and lower inference latency than prior methods. Code is available at this https URL .

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2611.00029 — 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 2026-11-03T11:06:37.355Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).