# D'ej`a Cue: Localizing States in Object Histories via Vocabulary-Relative Coordinates

arXiv: https://arxiv.org/abs/2608.02044 · HTML: https://mlsanity.com/paper/2608.02044/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 25 of its 38 references that are in the map.
- First posted on arXiv 3 Aug 2026.

## Builds on (most cited first, 25 of 25)

- [D-NeRF: Neural Radiance Fields for Dynamic Scenes](https://mlsanity.com/paper/2011.13961/) (2020)
- [Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction](https://mlsanity.com/paper/2309.13101/) (2023)
- [Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesis](https://mlsanity.com/paper/2308.09713/) (2023)
- [All-but-the-Top: Simple and Effective Postprocessing for Word Representations](https://mlsanity.com/paper/1702.01417/) (2017)
- [UniVTG: Towards Unified Video-Language Temporal Grounding](https://mlsanity.com/paper/2307.16715/) (2023)
- [Query-Dependent Video Representation for Moment Retrieval and Highlight Detection](https://mlsanity.com/paper/2303.13874/) (2023)
- [Knowing Where to Focus: Event-aware Transformer for Video Grounding](https://mlsanity.com/paper/2308.06947/) (2023)
- [UnLoc: A Unified Framework for Video Localization Tasks](https://mlsanity.com/paper/2308.11062/) (2023)
- [TR-DETR: Task-Reciprocal Transformer for Joint Moment Retrieval and Highlight Detection](https://mlsanity.com/paper/2401.02309/) (2024)
- [TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs](https://mlsanity.com/paper/2512.14698/) (2025)
- [The Double-Ellipsoid Geometry of CLIP](https://mlsanity.com/paper/2411.14517/) (2024)
- [Look for the Change: Learning Object States and State-Modifying Actions from Untrimmed Web Videos](https://mlsanity.com/paper/2203.11637/) (2022)
- [Learning Object State Changes in Videos: An Open-World Perspective](https://mlsanity.com/paper/2312.11782/) (2023)
- [SnAG: Scalable and Accurate Video Grounding](https://mlsanity.com/paper/2404.02257/) (2024)
- [Task-Driven Exploration: Decoupling and Inter-Task Feedback for Joint Moment Retrieval and Highlight Detection](https://mlsanity.com/paper/2404.09263/) (2024)
- [Enrich and Detect: Video Temporal Grounding with Multimodal LLMs](https://mlsanity.com/paper/2510.17023/) (2025)
- [Zero-shot Video Moment Retrieval With Off-the-Shelf Models](https://mlsanity.com/paper/2211.02178/) (2022)
- [GranAlign: Granularity-Aware Alignment Framework for Zero-Shot Video Moment Retrieval](https://mlsanity.com/paper/2601.00584/) (2026)
- [Moment Quantization for Video Temporal Grounding](https://mlsanity.com/paper/2504.02286/) (2025)
- [Sim-DETR: Unlock DETR for Temporal Sentence Grounding](https://mlsanity.com/paper/2509.23867/) (2025)
- [VeRVE: Versatile Retrieval for Videos via Unified Embeddings](https://mlsanity.com/paper/2601.12193/) (2026)
- [CVA: Context-aware Video-text Alignment for Video Temporal Grounding](https://mlsanity.com/paper/2603.24934/) (2026)
- [SPOC: Spatially-Progressing Object State Change Segmentation in Video](https://mlsanity.com/paper/2503.11953/) (2025)
- [Point to Span: Zero-Shot Moment Retrieval for Navigating Unseen Hour-Long Videos](https://mlsanity.com/paper/2512.10363/) (2025)
- [Object-Centric Framework for Video Moment Retrieval](https://mlsanity.com/paper/2512.18448/) (2025)

## Abstract (arXiv)

Tracking links observations of the same object through visual change, yet cannot by itself determine when the object is empty or filled, intact or cut. We formulate identity-conditioned state-moment retrieval: given a tracked-object history and alternative state descriptions, localize an interval in which each described state holds. Absolute image-text similarity scores descriptions independently; because every visible frame depicts the same target, shared object compatibility can obscure the state evidence needed to identify the target interval. The alternatives provide the missing reference: evidence for one state should be measured against the others. We introduce D'ej`a Cue, a training-free framework that turns these alternatives into a vocabulary-relative coordinate system. It subtracts their state-balanced centroid from each description, calibrates frame scores, and scans multiple durations within contiguous visible runs using a frozen encoder. On 78 VOST histories, holding the temporal scan fixed and changing only the query reference nearly doubles R@1 at tIoU 0.5 from 10.3% to 20.5% and raises Top-1 tIoU from 16.0% to 21.5%. Candidate-rank analyses show that vocabulary-relative queries rank useful intervals higher within the same candidate set. Related state descriptions can therefore serve as an object-specific, query-time coordinate system for reading frozen visual representations.