Salvato in:
Dettagli Bibliografici
Autori principali: Chiu, Bo-Cheng, Chen, Jen-Jee, Tseng, Yu-Chee, Chen, Feng-Chi, Yen, An-Zi
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2506.11558
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914286954086400
author Chiu, Bo-Cheng
Chen, Jen-Jee
Tseng, Yu-Chee
Chen, Feng-Chi
Yen, An-Zi
author_facet Chiu, Bo-Cheng
Chen, Jen-Jee
Tseng, Yu-Chee
Chen, Feng-Chi
Yen, An-Zi
contents Large Language Models (LLMs) have recently been extended to the video domain, enabling sophisticated video-language understanding. However, existing Video LLMs often exhibit limitations in fine-grained temporal reasoning, restricting their ability to precisely attribute responses to specific video moments, especially under constrained supervision. We introduce DaMO, a data-efficient Video LLM explicitly designed for accurate temporal reasoning and multimodal understanding. At its core, the proposed Temporal-aware Fuseformer employs a hierarchical dual-stream architecture that progressively captures temporal dynamics within each modality and effectively fuses complementary visual and audio information. To further enhance computational efficiency, DaMO integrates a global residual that reduces spatial redundancy while preserving essential semantic details. We train DaMO via a structured four-stage progressive training paradigm, incrementally equipping the model with multimodal alignment, semantic grounding, and temporal reasoning capabilities. This work also contributes multiple datasets augmented from existing ones with LLM-generated temporally grounded QA pairs for tasks requiring temporal supervision. Comprehensive experiments on temporal grounding and video QA benchmarks demonstrate that DaMO consistently surpasses prior methods, particularly in tasks demanding precise temporal alignment and reasoning. Our work establishes a promising direction for data-efficient video-language modeling.
format Preprint
id arxiv_https___arxiv_org_abs_2506_11558
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DaMO: A Data-Efficient Multimodal Orchestrator for Temporal Reasoning with Video LLMs
Chiu, Bo-Cheng
Chen, Jen-Jee
Tseng, Yu-Chee
Chen, Feng-Chi
Yen, An-Zi
Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
Large Language Models (LLMs) have recently been extended to the video domain, enabling sophisticated video-language understanding. However, existing Video LLMs often exhibit limitations in fine-grained temporal reasoning, restricting their ability to precisely attribute responses to specific video moments, especially under constrained supervision. We introduce DaMO, a data-efficient Video LLM explicitly designed for accurate temporal reasoning and multimodal understanding. At its core, the proposed Temporal-aware Fuseformer employs a hierarchical dual-stream architecture that progressively captures temporal dynamics within each modality and effectively fuses complementary visual and audio information. To further enhance computational efficiency, DaMO integrates a global residual that reduces spatial redundancy while preserving essential semantic details. We train DaMO via a structured four-stage progressive training paradigm, incrementally equipping the model with multimodal alignment, semantic grounding, and temporal reasoning capabilities. This work also contributes multiple datasets augmented from existing ones with LLM-generated temporally grounded QA pairs for tasks requiring temporal supervision. Comprehensive experiments on temporal grounding and video QA benchmarks demonstrate that DaMO consistently surpasses prior methods, particularly in tasks demanding precise temporal alignment and reasoning. Our work establishes a promising direction for data-efficient video-language modeling.
title DaMO: A Data-Efficient Multimodal Orchestrator for Temporal Reasoning with Video LLMs
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2506.11558