Enhanced Multimodal Video Retrieval System: Integrating Query Expansion And Cross-modal Temporal Event Retrieval
2025 Β· van-Thinh Vo, Minh-Khoi Nguyen, Minh-Huy Tran, et al.
Abstract
Multimedia information retrieval from videos remains a challenging problem. While recent systems have advanced multimodal search through semantic, object, and OCR queries - and can retrieve temporally consecutive scenes - they often rely on a single query modality for an entire sequence, limiting robustness in complex temporal contexts. To overcome this, we propose a cross-modal temporal event retrieval framework that enables different query modalities to describe distinct scenes within a sequence. To determine decision thresholds for scene transition and slide change adaptively, we build Kernel Density Gaussian Mixture Thresholding (KDE-GMM) algorithm, ensuring optimal keyframe selection. These extracted keyframes act as compact, high-quality visual exemplars that retain each segment's semantic essence, improving retrieval precision and efficiency. Additionally, the system incorporates a large language model (LLM) to refine and expand user queries, enhancing overall retrieval performa
Authors
(none)
Tags
Stats
Related papers
- Multimodal Contextualized Support For Enhancing Video Retrieval System (2026)0.00
- Unified Interactive Multimodal Moment Retrieval Via Cascaded Embedding-reranking And Temporal-aware Score Fusion (2025)0.00
- Madtempo: An Interactive System For Multi-event Temporal Video Retrieval With Query Augmentation (2025)0.00
- Towards Efficient And Robust Moment Retrieval System: A Unified Framework For Multi-granularity Models And Temporal Reranking (2025)2.26
- Clamr: Contextualized Late-interaction For Multimodal Content Retrieval (2025)0.00
- Tree-augmented Cross-modal Encoding For Complex-query Video Retrieval (2020)15.57
- A Lightweight Moment Retrieval System With Global Re-ranking And Robust Adaptive Bidirectional Temporal Search (2025)3.58
- Verve: Versatile Retrieval For Videos Via Unified Embeddings (2026)0.00