Predict, Then Retrieve: Cross-Instance Future-State Retrieval from Video Prefixes

• URL: http://arxiv.org/abs/2608.04426v1
• Date: Wed, 05 Aug 2026 04:12:00 GMT
• Title: Predict, Then Retrieve: Cross-Instance Future-State Retrieval from Video Prefixes
• Abstract summary: We introduce Predictive State Retrieval (PSR), a task in which a model observes a short video prefix and a temporal question about an object's future state.<n>PSR combines anticipation with cross-instance retrieval across multiple temporal horizons.<n>We also propose LFTR, a lightweight retriever with frozen encoders that predicts a question- and horizon-conditioned future latent.
• Score: 39.17422574355306
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: We introduce Predictive State Retrieval (PSR), a task in which a model observes a short video prefix and a temporal question about an object's future state, then retrieves instances from other videos or images that depict that state. Unlike action anticipation, which predicts a label, moment retrieval, which localizes an observed event within a video, or video generation, which synthesizes pixels, PSR combines anticipation with cross-instance retrieval across multiple temporal horizons. We construct a benchmark from four datasets with graded, human-validated ground truth, difficulty tiers, and an oracle ceiling. We also propose LFTR, a lightweight retriever with frozen encoders that predicts a question- and horizon-conditioned future latent and matches it in complementary semantic and visual spaces. A ceiling decomposition reveals a clear bottleneck: the true future state is highly retrievable once specified, whereas every predictor we evaluate, including a large multimodal language model with access to the prefix frames, remains far below the oracle. Thus, forecasting rather than perception is the central learnable challenge. LFTR narrows this gap at substantially lower inference cost, and ablations attribute its gains to cross-space fusion and hard-negative training rather than latent rollout. We release the benchmark, code, and evaluation scripts.

Related papers

• Towards Generative Predictive Display for Vision-Based Teleoperation: A Zero-Shot Benchmark of Off-the-Shelf Video Models [0.0]
  This paper presents a benchmark of off-the-shelf generative video models for short-horizon predictive display.<n>Performance is assessed using prediction accuracy, per-rollout latency, peak GPU memory usage, and temporal error evolution.<n>Findings highlight a gap between general-purpose generative video synthesis and the requirements of predictive display in teleoperation.
  arXiv  Detail & Related papers  (2026-05-10T17:36:22Z)
• Rethinking Video Human-Object Interaction: Set Prediction over Time for Unified Detection and Anticipation [18.693454975393703]
  Video-based human-object interaction (HOI) understanding requires both detecting ongoing interactions and anticipating their future evolution.<n>We introduce DETAnt-HOI and HOI-DA, a pair-centric framework that jointly performs subject-object localization, present HOI detection, and future anticipation.<n>Experiments show consistent improvements in both detection and anticipation, with larger gains at longer horizons.
  arXiv  Detail & Related papers  (2026-04-12T01:07:43Z)
• EPRBench: A High-Quality Benchmark Dataset for Event Stream Based Visual Place Recognition [54.55914886780534]
  Event stream-based Visual Place Recognition (VPR) is an emerging research direction that offers a compelling solution to the instability of conventional visible-light cameras under challenging conditions such as low illumination, overexposure, and high-speed motion.<n>We introduce EPRBench, a high-quality benchmark specifically designed for event stream-based VPR.<n>EPRBench comprises 10K event sequences and 65K event frames, collected using both handheld and vehicle-mounted setups to comprehensively capture real-world challenges across diverse viewpoints, weather conditions, and lighting scenarios.
  arXiv  Detail & Related papers  (2026-02-13T13:25:05Z)
• Towards Fine-Grained Video Question Answering [17.582244704442747]
  This paper introduces the Multi-Object Multi-Actor Question Answering (MOMA-QA) dataset.<n>With ground truth scene graphs and temporal interval annotations, MOMA-QA is ideal for developing models for fine-grained video understanding.<n>We present a novel video-language model, SGVLM, which incorporates a scene graph predictor, an efficient frame retriever, and a pre-trained large language model for temporal localization and fine-grained relationship understanding.
  arXiv  Detail & Related papers  (2025-03-10T01:02:01Z)
• TimeRefine: Temporal Grounding with Time Refining Video LLM [75.99665302872901]
  Video temporal grounding aims to localize relevant temporal boundaries in a video given a textual prompt.<n>We reformulate the temporal grounding task as a temporal refining task.<n>We incorporate an auxiliary prediction head that penalizes the model more if a predicted segment deviates further from the ground truth.
  arXiv  Detail & Related papers  (2024-12-12T18:59:11Z)
• Object-Centric Temporal Consistency via Conditional Autoregressive Inductive Biases [69.46487306858789]
  Conditional Autoregressive Slot Attention (CA-SA) is a framework that enhances the temporal consistency of extracted object-centric representations in video-centric vision tasks. We present qualitative and quantitative results showing that our proposed method outperforms the considered baselines on downstream tasks.
  arXiv  Detail & Related papers  (2024-10-21T07:44:44Z)
• Predicting Long-horizon Futures by Conditioning on Geometry and Time [49.86180975196375]
  We explore the task of generating future sensor observations conditioned on the past. We leverage the large-scale pretraining of image diffusion models which can handle multi-modality. We create a benchmark for video prediction on a diverse set of videos spanning indoor and outdoor scenes.
  arXiv  Detail & Related papers  (2024-04-17T16:56:31Z)
• Video Prediction at Multiple Scales with Hierarchical Recurrent Networks [24.536256844130996]
  We propose a novel video prediction model able to forecast future possible outcomes of different levels of granularity simultaneously. By combining spatial and temporal downsampling, MSPred is able to efficiently predict abstract representations over long time horizons. In our experiments, we demonstrate that our proposed model accurately predicts future video frames as well as other representations on various scenarios.
  arXiv  Detail & Related papers  (2022-03-17T13:08:28Z)
• A Closer Look at Debiased Temporal Sentence Grounding in Videos: Dataset, Metric, and Approach [53.727460222955266]
  Temporal Sentence Grounding in Videos (TSGV) aims to ground a natural language sentence in an untrimmed video. Recent studies have found that current benchmark datasets may have obvious moment annotation biases. We introduce a new evaluation metric "dR@n,IoU@m" that discounts the basic recall scores to alleviate the inflating evaluation caused by biased datasets.
  arXiv  Detail & Related papers  (2022-03-10T08:58:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.