# GenSpan: Generation-Calibrated Motion Span Priors for Multi-Verb Video Corpus Moment Retrieval

arXiv: https://arxiv.org/abs/2603.22121 · HTML: https://mlsanity.com/paper/2603.22121/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 32 references that are in the map.
- First posted on arXiv 23 Mar 2026.

## Builds on (most cited first, 28 of 28)

- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://mlsanity.com/paper/2311.15127/) (2023)
- [Video Diffusion Models](https://mlsanity.com/paper/2204.03458/) (2022)
- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [Make-A-Video: Text-to-Video Generation without Text-Video Data](https://mlsanity.com/paper/2209.14792/) (2022)
- [Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality](https://mlsanity.com/paper/2405.21060/) (2024)
- [Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model](https://mlsanity.com/paper/2401.09417/) (2024)
- [Dense-Captioning Events in Videos](https://mlsanity.com/paper/1705.00754/) (2017)
- [Localizing Moments in Video with Natural Language](https://mlsanity.com/paper/1708.01641/) (2017)
- [VideoCrafter1: Open Diffusion Models for High-Quality Video Generation](https://mlsanity.com/paper/2310.19512/) (2023)
- [HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training](https://mlsanity.com/paper/2005.00200/) (2020)
- [VideoMamba: State Space Model for Efficient Video Understanding](https://mlsanity.com/paper/2403.06977/) (2024)
- [TVR: A Large-Scale Dataset for Video-Subtitle Moment Retrieval](https://mlsanity.com/paper/2001.09099/) (2020)
- [Localizing Moments in Video with Temporal Language](https://mlsanity.com/paper/1809.01337/) (2018)
- [Temporal Sentence Grounding in Videos: A Survey and Future Directions](https://mlsanity.com/paper/2201.08071/) (2022)
- [CONQUER: Contextual Query-aware Ranking for Video Corpus Moment Retrieval](https://mlsanity.com/paper/2109.10016/) (2021)
- [A Survey on Temporal Sentence Grounding in Videos](https://mlsanity.com/paper/2109.08039/) (2021)
- [SpikeMba: Multi-Modal Spiking Saliency Mamba for Temporal Video Grounding](https://mlsanity.com/paper/2404.01174/) (2024)
- [Selective Query-guided Debiasing for Video Corpus Moment Retrieval](https://mlsanity.com/paper/2210.08714/) (2022)
- [A Survey on Video Moment Localization](https://mlsanity.com/paper/2306.07515/) (2023)
- [MomentSeeker: A Task-Oriented Benchmark For Long-Video Moment Retrieval](https://mlsanity.com/paper/2502.12558/) (2025)
- [What, when, and where? -- Self-Supervised Spatio-Temporal Grounding in Untrimmed Multi-Action Videos from Narrated Instructions](https://mlsanity.com/paper/2303.16990/) (2023)
- [Localizing Events in Videos with Multimodal Queries](https://mlsanity.com/paper/2406.10079/) (2024)
- [Improving Video Corpus Moment Retrieval with Partial Relevance Enhancement](https://mlsanity.com/paper/2402.13576/) (2024)
- [Event-aware Video Corpus Moment Retrieval](https://mlsanity.com/paper/2402.13566/) (2024)
- [Boosting Temporal Sentence Grounding via Causal Inference](https://mlsanity.com/paper/2507.04958/) (2025)

## Abstract (arXiv)

Video Corpus Moment Retrieval (VCMR) aims to retrieve both the correct video and its temporal segment corresponding to a natural-language query, a task that is especially challenging for multi-verb queries where temporal action ordering is critical. Existing approaches often rely solely on text or static images and struggle to capture implicit motion dynamics, leading to retrieval errors and temporal misalignment. We propose GenSpan, a generation-calibrated VCMR framework that constructs short auxiliary videos from LLM-selected subtitle cues and decomposed sub-events, using these as temporal priors rather than direct retrieval targets. A token selector filters candidate-video features aligned with generated motion, and a bidirectional state-space model efficiently predicts video-moment tuples. Experiments on TVR and ActivityNet-Captions demonstrate that GenSpan improves corpus-level retrieval and moment localization, particularly for complex multi-action queries, while reducing computational cost compared to state-of-the-art multimodal baselines.