DART: Difficulty-Adaptive Routing for Zero-Shot Video Temporal Grounding

• URL: http://arxiv.org/abs/2607.00672v1
• Date: Wed, 01 Jul 2026 09:18:59 GMT
• Title: DART: Difficulty-Adaptive Routing for Zero-Shot Video Temporal Grounding
• Abstract summary: Zero-shot video temporal grounding (VTG) localizes events in untrimmed videos from natural language queries without task-specific training.<n>We propose DART, which bridges the gap by coupling difficulty-aware routing with structured reasoning in large vision models.<n>On Charades-STA and ActivityNet Captions, DART achieves state-of-the-art zero-shot performance across both identically distributed and multiple out-of-distribution settings.
• Score: 41.985888701957826
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Zero-shot video temporal grounding (VTG) localizes events in untrimmed videos from natural language queries without task-specific training. Existing methods rely on frame-query feature matching, which suffices for simple events but struggles with complex multi-stage queries that require understanding temporal ordering and causal structure -- a disparity we call the reasoning gap. We propose DART (Difficulty-Adaptive Routing for Temporal Grounding), which bridges this gap by coupling difficulty-aware routing with structured reasoning in large vision-language models. A query-conditioned Determinantal Point Process (DPP) serves a dual role: selecting diverse, query-relevant keyframes as temporal evidence, and providing spectral entropy as a difficulty indicator. Simple queries are routed to a Fast path for direct prediction, while complex queries follow a Slow path with Temporal Markup Prompting, which decomposes localization into global event analysis, per-frame temporal role annotation, and boundary extraction. On Charades-STA and ActivityNet Captions, DART achieves state-of-the-art zero-shot performance across both identically distributed and multiple out-of-distribution settings, improving mIoU by up to 3.5 points over the strongest baseline while using over 7 times fewer frames. The project homepage is available at https://dart-vtg.github.io/.

Related papers

• Routing Before Looking: Query-Adaptive Evidence Acquisition for Long-form Video Understanding [34.47367969610384]
  Route2Look is a lightweight and model-agnostic framework for query-adaptive evidence acquisition in long-form video understanding.<n> Route2Look operates in a Route-Look-Memorize loop with three tools: Global Browse for holistic context, Temporal Ground for explicit temporal cues, and Semantic Retrieve for semantic search.<n> Experiments on challenging long-video benchmarks show that Route2Look achieves state-of-the-art performance while maintaining strong frame efficiency across datasets and query types.
  arXiv  Detail & Related papers  (2026-08-21T07:23:35Z)
• VisualRouter: Query-Grounded Visual Sampling for Long Video Understanding [60.161767365040554]
  We propose a training-free and plug-and-play framework for query-grounded visual sampling.<n>Visual first classifies each query as either global or local and then applies the corresponding sampling strategy.<n>Experiments show that Visual consistently improves multiple LVLMs over uniform sampling, achieving gains of 5.2%, 7.7%, and 11.6% on Video-MME, LongVideoBench, and MLVU with Qwen2.5-VL-7B, and outperforming existing training-free visual sampling methods under the same setting.
  arXiv  Detail & Related papers  (2026-07-30T16:23:10Z)
• SPATIOROUTE: Dynamic Prompt Routing for Zero-Shot Spatial Reasoning [20.773619604028283]
  We introduce SpatioRoute, a dynamic prompt generation approach that routes each incoming question to a semantically tailored prompt template.<n>SpatioRoute achieves consistent overall accuracy gains up to 5% over fixed prompt baselines, establishing a new state-of-the-art for zero-shot video-only spatial VQA.
  arXiv  Detail & Related papers  (2026-05-18T10:54:55Z)
• AdaSpot: Spend Resolution Where It Matters for Precise Event Spotting [59.31340724915079]
  Event Spotting is a key task for applications in sports analytics, robotics, and autonomous systems.<n>bfAdaSpot achieves state-of-the-art performance under strict evaluation metrics.
  arXiv  Detail & Related papers  (2026-02-25T16:24:48Z)
• TAG: A Simple Yet Effective Temporal-Aware Approach for Zero-Shot Video Temporal Grounding [12.57589714067771]
  Video Temporal Grounding aims to extract relevant video segments based on a given natural language query.<n>Previous approaches suffer from semantic fragmentation, where temporally continuous frames sharing the same semantics are split across multiple segments.<n>We propose a simple yet effective Temporal-Aware approach for zero-shot video temporal Grounding, which incorporates temporal pooling, temporal coherence clustering, and similarity adjustment.
  arXiv  Detail & Related papers  (2025-08-11T12:38:46Z)
• Logic-in-Frames: Dynamic Keyframe Search via Visual Semantic-Logical Verification for Long Video Understanding [23.022070084937603]
  We introduce a semantics-driven search framework that reformulates selection under the paradigm of Visual Semantic-Logical Search.<n>Our method establishes new SOTA performance on the manually annotated benchmark in key-frame selection metrics.
  arXiv  Detail & Related papers  (2025-03-17T13:07:34Z)
• Temporally Grounding Instructional Diagrams in Unconstrained Videos [51.85805768507356]
  We study the challenging problem of simultaneously localizing a sequence of queries in instructional diagrams in a video.<n>Most existing methods focus on grounding one query at a time, ignoring the inherent structures among queries.<n>We propose composite queries constructed by exhaustively pairing up the visual content features of the step diagrams.<n>We demonstrate the effectiveness of our approach on the IAW dataset for grounding step diagrams and the YouCook2 benchmark for grounding natural language queries.
  arXiv  Detail & Related papers  (2024-07-16T05:44:30Z)
• Single-Stage Visual Query Localization in Egocentric Videos [79.71065005161566]
  We propose a single-stage VQL framework that is end-to-end trainable. We establish the query-video relationship by considering query-to-frame correspondences between the query and each video frame. Our experiments demonstrate that our approach outperforms prior VQL methods by 20% accuracy while obtaining a 10x improvement in inference speed.
  arXiv  Detail & Related papers  (2023-06-15T17:57:28Z)
• Learning Commonsense-aware Moment-Text Alignment for Fast Video Temporal Grounding [78.71529237748018]
  Grounding temporal video segments described in natural language queries effectively and efficiently is a crucial capability needed in vision-and-language fields. Most existing approaches adopt elaborately designed cross-modal interaction modules to improve the grounding performance. We propose a commonsense-aware cross-modal alignment framework, which incorporates commonsense-guided visual and text representations into a complementary common space.
  arXiv  Detail & Related papers  (2022-04-04T13:07:05Z)

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.