A summarization pipeline around Global Entity Unification and Robust Importance Scoring is built, but unlike earlier efforts, each object is traced across frames and attached consistent identifiers to it, and Fragmented, isolated descriptions become a single, object-aware text corpus that unifies the storyline.
A new prototype-based hierarchical alignment network (PHA-Net) to align individual/local/global level representations across modalities and introduces multiple modality-shared prototypes as the bridge to efficiently optimize text and video representations for cross-modal alignment.
Xiaolun Jing, Kezhao Yin, Xin-Xing Yang et al.· Neurocomputing· 0 citations
This paper introduces two core modules designed to strengthen the feature representation and the semantic association between text and video, respectively and introduces semantic reconstruction feedback to serve as an auxiliary supervision alongside the primary global-local text-video alignment task.
Jiayao Qian, Shijie Luo, Lili Yan et al.· Multimedia Systems· 0 citations
This work proposes Self-SiMS, a self-similarity-based Moment Proposal and Scoring that exploits intrinsic relationships within videos, enabling robust span generation and scoring and introduces a query-aware MLLM-based reasoning stage to further sharpen alignment between text and video.
Jihyun Lee, Cheol-Ho Cho, Woojin Jun et al.· arXiv.org· 0 citations
Experimental results establish persistent object narratives as a compact, structured, and temporally organized visual interface for Video-LLMs as a favorable trade-off between accuracy and visual-token count compared with prior compact Video-LLM interfaces.
Experiments on four text-video retrieval benchmarks show that MARS achieves state-of-the-art results in both direct similarity-based retrieval and reranking settings, and a hard-negative-aware slot specialization objective that encourages the slots to capture discriminative matching cues is introduced.
Uicheol Jung, Juyoung Hong, Geuntaek Lim et al.· 0 citations
GCR is proposed, a training-free framework that casts fixed-budget frame selection as a joint evidence curation problem and maintains a fixed number of chronologically ordered frames and requires no VLM training or architectural modification.
Fan Wei, Si-Ru Zhong, Run-Min Dong et al.· 2 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
