AI Paper Atlas

Research map / Video / Video-language understanding

TimeTraveler: Temporal Strategy Planning with Time Dictionary for Streaming Video Understanding

Minkuk Kim, Junho Kim, Seong Tae Kim

NeurIPS 2026 · Video › Video-language understanding · approach: Event and anomaly reasoning in video · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes TimeTraveler, a temporal strategy planning framework with a time dictionary for answering queries over streaming video by deciding how to access past, current, and future evidence.

Problem

Streaming video understanding requires answering user queries whose evidence may lie in the past, the present, or only emerge in future observations; existing systems use compact visual memories or fixed evidence-access schemes that lose fine-grained details and fail to adapt.

Approach

Plans a query-dependent temporal access strategy over a time dictionary that indexes the stream, rather than relying on compact memory or a fixed retrieval scheme. Details beyond the abstract are not stated in the provided text.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add TimeTraveler (Time Dictionary + temporal strategy planning)Qwen3-VL-8B · OVO-Benchoverall accuracy (%): 51.70 -> 58.02Improved
add TimeTravelerQwen3-VL-8B · StreamingBenchoverall accuracy (%): 59.33 -> 64.51Improved
add TimeTravelerInternVL3.5-8B · OVO-Benchoverall accuracy (%): 47.84 -> 49.03Improved
add TimeTravelerInternVL3.5-8B · OVO-Bench Forward Active Respondingaccuracy (%): 42.59 -> 37.06Hurt
use structured eight-field dictionary instead of flat text memory (ablation)TimeTraveler · OVO-Benchoverall accuracy (%): 55.79 -> 58.02Improved
use structured dictionary instead of visual prototype memory at equal budget (ablation)TimeTraveler · OVO-Benchoverall accuracy (%): 53.90 -> 58.02Improved
use planner routing instead of random routing (ablation)TimeTraveler · OVO-Bench Backward Tracingaccuracy (%): 45.05 -> 51.37Improved
use planner routing instead of always looking back to past (ablation)TimeTraveler · OVO-Bench Backward Tracingaccuracy (%): 50.43 -> 51.37Improved
use adaptive probabilistic selection instead of fixed top-4 (ablation)TimeTraveler past lookback · OVO-Bench Backward Tracingaccuracy (%): 49.64 -> 51.37Improved
add Explicit Text field group to schema (ablation)Time Dictionary · StreamingBench TRaccuracy (%): 85.98 -> 90.97Improved
add Entity-Centric field group to schema (ablation)Time Dictionary · OVO-Bench OJRaccuracy (%): 72.83 -> 74.46Improved
add future gating to Time Dictionary (ablation)TimeTraveler · StreamingBench Proactive Output (Qwen3-VL-8B)accuracy (%): 45.20 -> 62.90Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy