paper-with-me

홈 › Papers

LOCORE: Image Re-ranking with Long-Context Sequence Modeling

2025-03-27 · CVPR 2025 1 · Zilin Xiao, Pavel Suma, Ayush Sachdeva, Hao-Jen Wang, Giorgos Kordopatis-Zilos, Giorgos Tolias, Vicente Ordonez

We introduce LOCORE, Long-Context Re-ranker, a model that takes as input local descriptors corresponding to an image query and a list of gallery images and outputs similarity scores between the query and each gallery image. This model is used for image retrieval, where typically a first ranking is performed with an efficient similarity measure, and then a shortlist of top-ranked images is re-ranked based on a more fine-grained similarity measure. Compared to existing methods that perform pair-wise similarity estimation with local descriptors or list-wise re-ranking with global descriptors, LOCORE is the first method to perform list-wise re-ranking with local descriptors. To achieve this, we leverage efficient long-context sequence models to effectively capture the dependencies between query and gallery images at the local-descriptor level. During testing, we process long shortlists with a sliding window strategy that is tailored to overcome the context size limitations of sequence models. Our approach achieves superior performance compared with other re-rankers on established image retrieval benchmarks of landmarks (ROxf and RPar), products (SOP), fashion items (In-Shop), and bird species (CUB-200) while having comparable latency to the pair-wise local descriptor re-rankers.

📄 PDF Abstract BibTeX arXiv:2503.21772

Code (1)

MrZilinXiao/LongContextReranker 공식 구현 pytorch

Tasks

Image RetrievalRe-RankingRetrieval

Similar Papers 제목 키워드 기반

AI Models Close to your Chest: Robust Federated Learning Strategies for Multi-site CT

2023-03-23 · Edward H. Lee, Brendan Kelly, Emre Altinmakas, Hakan Dogan 외

While it is well known that population differences from genetics, sex, race, and environmental factors contribute to disease, AI studies in medicine have largely focused on locoregional patient cohorts with less diverse …

Federated Learning

One Ranking, Any Budget: Matryoshka Evidence-to-Context Frame Selection for Long-Video Understanding

2026-08-06 · Wang Chen, Yu Chen, Xiang Wang, Shuai Li 외 arxiv

Frame selection is essential for applying Large Multimodal Models (LMMs) to long videos due to severe frame redundancy and limited context windows. Since the appropriate frame budget varies with the downstream LMM, reaso…

Contrastive Learning of User Behavior Sequence for Context-Aware Document Ranking

2021-08-24 · Yutao Zhu, Jian-Yun Nie, Zhicheng Dou, Zhengyi Ma 외

Context information in search sessions has proven to be useful for capturing user search intent. Existing studies explored user behavior sequences in sessions in different ways to enhance query suggestion or document ran…

Contrastive LearningData AugmentationDocument Ranking

Leveraging Structural Context Models and Ranking Score Fusion for Human Interaction Prediction

2016-08-18 · Qiuhong Ke, Mohammed Bennamoun, Senjian An, Farid Bossaid 외

Predicting an interaction before it is fully executed is very important in applications such as human-robot interaction and video surveillance. In a two-human interaction scenario, there often contextual dependency struc…

Optical Flow Estimation

Hallucination Begins Where Saliency Drops

2026-01-28 · Xiaofeng Zhang, Yuanchao Zhu, Chaochen Gu, Xiaosong Yuan 외 arxiv

Recent studies have examined attention dynamics in large vision-language models (LVLMs) to detect hallucinations. However, existing approaches remain limited in reliably distinguishing hallucinated from factually grounde…

Visual Grounding