# SALI: Shot-Aware Late Interaction for Cross-Shot Relation Matching in Text-to-Video Retrieval using Film-Grammar Knowledge

arXiv: https://arxiv.org/abs/2609.29721 · HTML: https://mlsanity.com/paper/2609.29721/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 24 references that are in the map.
- First posted on arXiv 24 Sep 2026.

## Builds on (most cited first, 18 of 18)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances](https://mlsanity.com/paper/1306.0895/) (2013)
- [ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT](https://mlsanity.com/paper/2004.12832/) (2020)
- [Dense-Captioning Events in Videos](https://mlsanity.com/paper/1705.00754/) (2017)
- [CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval](https://mlsanity.com/paper/2104.08860/) (2021)
- [FILIP: Fine-grained Interactive Language-Image Pre-Training](https://mlsanity.com/paper/2111.07783/) (2021)
- [When and why vision-language models behave like bags-of-words, and what to do about it?](https://mlsanity.com/paper/2210.01936/) (2022)
- [X-CLIP: End-to-End Multi-grained Contrastive Learning for Video-Text Retrieval](https://mlsanity.com/paper/2207.07285/) (2022)
- [A Joint Sequence Fusion Model for Video Question Answering and Retrieval](https://mlsanity.com/paper/1808.02559/) (2018)
- [MovieNet: A Holistic Dataset for Movie Understanding](https://mlsanity.com/paper/2007.10937/) (2020)
- [Movie Description](https://mlsanity.com/paper/1605.03705/) (2016)
- [X-Pool: Cross-Modal Language-Video Attention for Text-Video Retrieval](https://mlsanity.com/paper/2203.15086/) (2022)
- [MAD: A Scalable Dataset for Language Grounding in Videos from Movie Audio Descriptions](https://mlsanity.com/paper/2112.00431/) (2021)
- [TS2-Net: Token Shift and Selection Transformer for Text-Video Retrieval](https://mlsanity.com/paper/2207.07852/) (2022)
- [Condensed Movies: Story Based Retrieval with Contextual Embeddings](https://mlsanity.com/paper/2005.04208/) (2020)
- [Disentangled Representation Learning for Text-Video Retrieval](https://mlsanity.com/paper/2203.07111/) (2022)
- [VoLTA: Vision-Language Transformer with Weakly-Supervised Local-Feature Alignment](https://mlsanity.com/paper/2210.04135/) (2022)
- [Video-ColBERT: Contextualized Late Interaction for Text-to-Video Retrieval](https://mlsanity.com/paper/2503.19009/) (2025)

## Abstract (arXiv)

Text-to-video retrieval usually represents a video clip by a single embedding. This embedding often loses important relations between people. E.g., an interaction "Anna confronts Mark" is regularly filmed as alternating shot and reverse shot of both (Fig. 1a). No single shot or averaged embedding over clip shots captures this relation. Thus, we propose SALI (Shot-Aware Late Interaction). It extracts the subject and object from a single-sentence query, and matches the query, its subject and object text embeddings against each visual shot embedding of a video clip. The matching operator is greedy max or optimal transport. A film-grammar penalty in fine-tuning adds a small, consistent shift. Built on CLIP4Clip-meanP, SALI keeps overall recall on par on Condensed Movies and ActivityNet while raising R@1 on multi-shot relation queries by 3 and 12 points, the most among all compared methods, and improves such queries on MSR-VTT at a cost of 1.4 R@1 overall.