Metraipolis › archive › dc_ca30415ab371
AdaFrame: Hierarchical Multimodal Deduplication with Adaptive Information Budgeting for Cost-Efficient Video Advertisement Analysis — arXiv:2610.19127
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.19127
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-15T21:58:18.018Z
- SHA-256 of the archived text
de68d14ed420a4f25d5153e09af014a4e58a377f3256c3453ed7351b34f60794- Stable URL of this page
https://metraipolis.com/documento/dc_ca30415ab371
How to cite
AdaFrame: Hierarchical Multimodal Deduplication with Adaptive Information Budgeting for Cost-Efficient Video Advertisement Analysis — arXiv:2610.19127 — arXiv (en), https://arxiv.org/abs/2610.19127 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ca30415ab371 (Metraipolis archive dc_ca30415ab371, sha256 de68d14ed420a4f25d5153e09af014a4e58a377f3256c3453ed7351b34f60794)
BibTeX
@misc{dcca30415ab371,
title = {AdaFrame: Hierarchical Multimodal Deduplication with Adaptive Information Budgeting for Cost-Efficient Video Advertisement Analysis — arXiv:2610.19127},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.19127},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ca30415ab371; sha256 de68d14ed420a4f25d5153e09af014a4e58a377f3256c3453ed7351b34f60794},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.19127. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Uniform frame sampling for vision-language model (VLM)-based video analysis often floods multimodal backbones with redundant content, while existing keyframe selection methods are typically optimized for human viewing rather than downstream extraction accuracy. We propose AdaFrame, a content-adaptive preprocessing cascade that reduces visual redundancy without sacrificing extraction fidelity. Three progressively finer filters, perceptual hashing, learned perceptual image patch similarity (LPIPS), and CLIP-based semantic clustering, efficiently eliminate redundant frames before costly cross-modal inference. Per-video frame budgets are determined using Intrinsic Semantic Dimensionality (ISD), which estimates each video's semantic complexity through singular value decomposition of its frame embeddings. Experiments on 500 video advertisements from the Pitt Ads Dataset show that AdaFrame reduces the frame count by 48 percent and VLM inference cost by 75 percent compared with uniform sampling, while achieving 86.0 percent topic accuracy, an improvement of 1.6 percentage points, and 79.4 percent sentiment accuracy, an improvement of 7.5 percentage points. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MM, nuovi lavori del giorno). Categorie arXiv: Multimedia (cs.MM). Pagina del lavoro: https://arxiv.org/abs/2610.19127 — 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 2026-10-15T21:39:29.398Z dalla pagina https://arxiv.org/list/cs.MM/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).