Exploiting Local Indexing And Deep Feature Confidence Scores For Fast Image-to-video Search
2018 · Savas Ozkan, Gozde Bozdagi Akar
Abstract
The cost-effective visual representation and fast query-by-example search are two challenging goals that should be maintained for web-scale visual retrieval tasks on moderate hardware. This paper introduces a fast and robust method that ensures both of these goals by obtaining state-of-the-art performance for an image-to-video search scenario. Hence, we present critical enhancements to well-known indexing and visual representation techniques by promoting faster, better and moderate retrieval performance. We also boost the superiority of our method for some visual challenges by exploiting individual decisions of local and global descriptors at query time. For instance, local content descriptors represent copied/duplicated scenes with large geometric deformations such as scale, orientation and affine transformation. In contrast, the use of global content descriptors is more practical for near-duplicate and semantic searches. Experiments are conducted on a large-scale Stanford I2V dataset
Authors
(none)
Tags
Stats
Related papers
- The VISIONE Video Search System: Exploiting Off-the-shelf Text Search Engines For Large-scale Video Retrieval (2020)10.74
- Simultaneous Feature Aggregating And Hashing For Large-scale Image Search (2017)10.61
- A Fast Content-based Image Retrieval Method Using Deep Visual Features (2019)6.77
- Vision-language Models Learn Super Images For Efficient Partially Relevant Video Retrieval (2023)3.58
- A Lightweight Moment Retrieval System With Global Re-ranking And Robust Adaptive Bidirectional Temporal Search (2025)3.58
- Encode The Unseen: Predictive Video Hashing For Scalable Mid-stream Retrieval (2020)3.58
- Global-to-local Or Local-to-global? Enhancing Image Retrieval With Efficient Local Search And Effective Global Re-ranking (2025)0.00
- Use What You Have: Video Retrieval Using Representations From Collaborative Experts (2019)0.00