MADTempo: An Interactive System for Multi-Event Temporal Video Retrieval with Query Augmentation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909963296702464 |
|---|---|
| author | Vu, Huu-An Mai, Van-Khanh Nguyen, Trong-Tam Dam, Quang-Duc Nguyen, Tien-Huy Le, Thanh-Huong |
| author_facet | Vu, Huu-An Mai, Van-Khanh Nguyen, Trong-Tam Dam, Quang-Duc Nguyen, Tien-Huy Le, Thanh-Huong |
| contents | The rapid expansion of video content across online platforms has accelerated the need for retrieval systems capable of understanding not only isolated visual moments but also the temporal structure of complex events. Existing approaches often fall short in modeling temporal dependencies across multiple events and in handling queries that reference unseen or rare visual concepts. To address these challenges, we introduce MADTempo, a video retrieval framework developed by our team, AIO_Trinh, that unifies temporal search with web-scale visual grounding. Our temporal search mechanism captures event-level continuity by aggregating similarity scores across sequential video segments, enabling coherent retrieval of multi-event queries. Complementarily, a Google Image Search-based fallback module expands query representations with external web imagery, effectively bridging gaps in pretrained visual embeddings and improving robustness against out-of-distribution (OOD) queries. Together, these components advance the temporal reasoning and generalization capabilities of modern video retrieval systems, paving the way for more semantically aware and adaptive retrieval across large-scale video corpora. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_12929 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MADTempo: An Interactive System for Multi-Event Temporal Video Retrieval with Query Augmentation Vu, Huu-An Mai, Van-Khanh Nguyen, Trong-Tam Dam, Quang-Duc Nguyen, Tien-Huy Le, Thanh-Huong Computer Vision and Pattern Recognition Artificial Intelligence The rapid expansion of video content across online platforms has accelerated the need for retrieval systems capable of understanding not only isolated visual moments but also the temporal structure of complex events. Existing approaches often fall short in modeling temporal dependencies across multiple events and in handling queries that reference unseen or rare visual concepts. To address these challenges, we introduce MADTempo, a video retrieval framework developed by our team, AIO_Trinh, that unifies temporal search with web-scale visual grounding. Our temporal search mechanism captures event-level continuity by aggregating similarity scores across sequential video segments, enabling coherent retrieval of multi-event queries. Complementarily, a Google Image Search-based fallback module expands query representations with external web imagery, effectively bridging gaps in pretrained visual embeddings and improving robustness against out-of-distribution (OOD) queries. Together, these components advance the temporal reasoning and generalization capabilities of modern video retrieval systems, paving the way for more semantically aware and adaptive retrieval across large-scale video corpora. |
| title | MADTempo: An Interactive System for Multi-Event Temporal Video Retrieval with Query Augmentation |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2512.12929 |