MADTempo: An Interactive System for Multi-Event Temporal Video Retrieval with Query Augmentation
This addresses the need for more semantically aware video retrieval systems for online platforms, though it appears incremental by combining existing techniques like temporal aggregation and query augmentation.
The paper tackles the problem of retrieving videos with complex temporal events and handling queries referencing unseen concepts by introducing MADTempo, a framework that unifies temporal search with web-scale visual grounding, improving robustness against out-of-distribution queries.
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.