Dynamic Spatial Verification For Large-scale Object-level Image Retrieval

Abstract

Images from social media can reflect diverse viewpoints, heated arguments, and expressions of creativity, adding new complexity to retrieval tasks. Researchers working onContent-Based Image Retrieval (CBIR) have traditionally tuned their algorithms to match filtered results with user search intent. However, we are now bombarded with composite images of unknown origin, authenticity, and even meaning. With such uncertainty, users may not have an initial idea of what the results of a search query should look like. For instance, hidden people, spliced objects, and subtly altered scenes can be difficult for a user to detect initially in a meme image, but may contribute significantly to its composition. We propose a new approach for spatial verification that aims at modeling object-level regions dynamically clustering keypoints in a 2D Hough space, which are then used to accurately weight small contributing objects within the results, without the need for costly object detection steps. We ca

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keybrogan2019dynamic

Related papers

• Object Retrieval And Localization In Large Art Collections Using Deep Multi-style Feature Fusion And Iterative Voting (2021)7.50
• Detect-to-retrieve: Efficient Regional Aggregation For Image Search (2018)24.71
• Visual Model Checking: Graph-based Inference Of Visual Routines For Image Retrieval (2026)0.00
• Object-centric Open-vocabulary Image-retrieval With Aggregated Features (2023)0.00
• Efficient Object Embedding For Spliced Image Retrieval (2019)8.09
• Exploiting Local Indexing And Deep Feature Confidence Scores For Fast Image-to-video Search (2018)2.26
• Deepimagesearch: Benchmarking Multimodal Agents For Context-aware Image Retrieval In Visual Histories (2026)0.00
• CSMCIR: Cot-enhanced Symmetric Alignment With Memory Bank For Composed Image Retrieval (2026)0.00