{"total":13,"rows":[{"id":"2604.03653","title":"Imagine Before Concentration: Diffusion-Guided Registers Enhance Partially Relevant Video Retrieval","created":"2026-04-04","cited_by_count":3,"area":null},{"id":"2606.00825","title":"SuperMemory-VQA: An Egocentric Visual Question-Answering Benchmark for Long-Horizon Memory","created":"2026-05-30","cited_by_count":3,"area":null},{"id":"2510.12327","title":"Simple Projection Variants Improve ColBERT Performance","created":"2025-10-14","cited_by_count":2,"area":null},{"id":"2605.06083","title":"Revisiting Uncertainty: On Evidential Learning for Partially Relevant Video Retrieval","created":"2026-05-07","cited_by_count":2,"area":null},{"id":"2511.00444","title":"LIR: The First Workshop on Late Interaction and Multi Vector Retrieval @ ECIR 2026","created":"2025-11-01","cited_by_count":1,"area":null},{"id":"2603.20336","title":"GEM: A Native Graph-based Index for Multi-Vector Retrieval","created":"2026-03-20","cited_by_count":1,"area":null},{"id":"2609.33800","title":"Binding Multiple Modalities via Multimodal Wasserstein Barycenter","created":"2026-09-27","cited_by_count":1,"area":null},{"id":"2507.20518","title":"T2VParser: Adaptive Decomposition Tokens for Partial Alignment in Text to Video Retrieval","created":"2025-07-28","cited_by_count":0,"area":null},{"id":"2603.08224","title":"SAVE: Speech-Aware Video Representation Learning for Video-Text Retrieval","created":"2026-03-09","cited_by_count":0,"area":null},{"id":"2603.13537","title":"AMES: Approximate Multi-modal Enterprise Search via Late Interaction Retrieval","created":"2026-03-13","cited_by_count":0,"area":null},{"id":"2607.20984","title":"Distribution-Alignment Bridge for Uncertainty-Aware Text-to-Video Retrieval","created":"2026-07-23","cited_by_count":0,"area":null},{"id":"2609.28437","title":"MultiVENT-Raw: A Benchmark for Retrieval and Reasoning over Raw Videos","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.29721","title":"SALI: Shot-Aware Late Interaction for Cross-Shot Relation Matching in Text-to-Video Retrieval using Film-Grammar Knowledge","created":"2026-09-24","cited_by_count":0,"area":null}],"next_cursor":null}