Multi-objective Reasoning ( MoRe) is proposed, a zero-shot framework based on MLLMs for multi-objective candidate selection and fine-grained transformation reasoning and introduces a recall-oriented multi-objective candidate selection module that identifies high-quality retrieval targets by jointly balancing visual, textual, and multimodal similarities before transformation reasoning.
Results show that adaptively orchestrating foundation-model capabilities can combine scalable retrieval with fine-grained reasoning without task-specific training, and are shown to be state-of-the-art among training-free approaches.
Dmitry Demidov, Muhammad Zaigham Zaheer, Omkar Thawakar et al.· 0 citations
This work proposes a large-scale multimodal large language model-based supervision generation framework that improves supervision diversity, fidelity, and semantic coverage, and introduces a granularity-aware text representation with separate CLS tokens for summary and detailed views.
F. M. Thoker, Renaud Vandeghen, Karen Sanchez et al.· 0 citations
Text-video retrieval, which aims to bridge visual and textual modalities by learning a joint embedding space, has become a crucial task in multimodal intelligence. Despite extensive efforts to mitigate visual redundancy, previous methods typically rely on a single-aspect criterion to assess visual importance, overlooki...
Shu-Quan Wei, Xi Chen, Xu Chen et al.· 0 citations
The rapid growth of digital media has increased the availability of posts that combine spoken narration, visual demonstrations, embedded images, captions, and video sequences within a single communicative unit. Although existing information extraction systems perform well on textual data, their effectiveness remains li...
Timothy Dillan, S. Isa, A. S. Girsang et al.· Engineering, Technology &...· 0 citations
Partially Relevant Video Retrieval (PRVR) aims to retrieve untrimmed videos containing moments relevant to a given text query. Despite recent progress, existing PRVR methods suffer from two key limitations: a fixed video decomposition scheme that causes semantic dilution, and source-domain overfitting induced by task-s...
STITCH is presented, a training-free method that divides a video into semantically meaningful temporal chunks that are computed once per video and reused across tasks, suggesting that reusable temporal abstraction is a promising direction for general video understanding.
Etienne Casanova, S. Brodjian, Pietro Perona· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
