Metraipolis › archive › dc_400a39827095

TAME: Temporal-Aware Mixture-of-Experts for Text-Video Retrieval — arXiv:2609.02204

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.02204
License (as archived): CC0-1.0
Archived: 2026-10-17T05:49:55.749Z
SHA-256 of the archived text: 58982963666658088bf44594f7ea67a56bcee56ec5e4c1076a9490e153f6ad01
Stable URL of this page: https://metraipolis.com/documento/dc_400a39827095

How to cite

TAME: Temporal-Aware Mixture-of-Experts for Text-Video Retrieval — arXiv:2609.02204 — arXiv (en), https://arxiv.org/abs/2609.02204 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_400a39827095 (Metraipolis archive dc_400a39827095, sha256 58982963666658088bf44594f7ea67a56bcee56ec5e4c1076a9490e153f6ad01)

BibTeX

@misc{dc400a39827095,
  title = {TAME: Temporal-Aware Mixture-of-Experts for Text-Video Retrieval — arXiv:2609.02204},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.02204},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_400a39827095; sha256 58982963666658088bf44594f7ea67a56bcee56ec5e4c1076a9490e153f6ad01},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.02204. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Text-Video Retrieval (TVR) retrieves videos that match a natural-language query, but extending image-text models such as CLIP to videos is fundamentally limited by the lack of temporal modeling. Videos exhibit frame-wise heterogeneity in appearance and motion, and compressing all frames into a single representation often obscures temporal structure and semantic transitions. To address this, we propose Temporal-Aware Mixture-of-Experts for Text-Video Retrieval (TAME), a CLIP-based framework that jointly models frame-level structure and temporal relations. First, we integrate sparse Mixture-of-Experts (MoE) layers into both CLIP encoders and apply frame-consistent routing on the vision branch so that experts specialize according to frame-level visual patterns while preserving the original vision-language alignment. Second, we introduce Frame-Temporal (FT) tokens that aggregate global cross-frame information and feed it back to each frame, enabling the visual encoder to capture long-range temporal dependencies without harming local details. Third, we design a Cross-Temporal Interaction and Aggregation (CTIA) module that refines frame-wise sentence-video similarities through staged temporal filtering and fusion. Experiments on standard TVR benchmarks show that TAME consistently improves over CLIP-based baselines. On MSR-VTT, it improves R@1 by 4.0 over CLIP4Clip, and also achieves consistent gains on DiDeMo, MSVD, LSMDC, and ActivityNet. The code is available at this https URL .

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-03 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.02204 — 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 2026-10-17T05:25:58.078Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-03?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).