# X-Pool: Cross-Modal Language-Video Attention for Text-Video Retrieval

arXiv: https://arxiv.org/abs/2203.15086 · HTML: https://mlsanity.com/paper/2203.15086/

## Key facts

- Cited by 128 papers in the map (data through 14 Oct 2026).
- Builds on 40 of its 52 references that are in the map.
- First posted on arXiv 28 Mar 2022.

## Builds on (most cited first, 30 of 40)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [VQA: Visual Question Answering](https://mlsanity.com/paper/1505.00468/) (2015)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks](https://mlsanity.com/paper/1908.02265/) (2019)
- [Align before Fuse: Vision and Language Representation Learning with Momentum Distillation](https://mlsanity.com/paper/2107.07651/) (2021)
- [LXMERT: Learning Cross-Modality Encoder Representations from Transformers](https://mlsanity.com/paper/1908.07490/) (2019)
- [Show, Attend and Tell: Neural Image Caption Generation with Visual Attention](https://mlsanity.com/paper/1502.03044/) (2015)
- [VisualBERT: A Simple and Performant Baseline for Vision and Language](https://mlsanity.com/paper/1908.03557/) (2019)
- [Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks](https://mlsanity.com/paper/2004.06165/) (2020)
- [Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval](https://mlsanity.com/paper/2104.00650/) (2021)
- [Multimodal Machine Learning: A Survey and Taxonomy](https://mlsanity.com/paper/1705.09406/) (2017)
- [Deep Visual-Semantic Alignments for Generating Image Descriptions](https://mlsanity.com/paper/1412.2306/) (2014)
- [HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips](https://mlsanity.com/paper/1906.03327/) (2019)
- [CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval](https://mlsanity.com/paper/2104.08860/) (2021)
- [End-to-End Learning of Visual Representations from Uncurated Instructional Videos](https://mlsanity.com/paper/1912.06430/) (2019)
- [Less is More: ClipBERT for Video-and-Language Learning via Sparse Sampling](https://mlsanity.com/paper/2102.06183/) (2021)
- [Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm](https://mlsanity.com/paper/2110.05208/) (2021)
- [Multi-modal Transformer for Video Retrieval](https://mlsanity.com/paper/2007.10639/) (2020)
- [Self-Supervised MultiModal Versatile Networks](https://mlsanity.com/paper/2006.16228/) (2020)
- [ActBERT: Learning Global-Local Video-Text Representations](https://mlsanity.com/paper/2011.07231/) (2020)
- [Use What You Have: Video Retrieval Using Representations From Collaborative Experts](https://mlsanity.com/paper/1907.13487/) (2019)
- [A Joint Sequence Fusion Model for Video Question Answering and Retrieval](https://mlsanity.com/paper/1808.02559/) (2018)
- [Movie Description](https://mlsanity.com/paper/1605.03705/) (2016)
- [Support-set bottlenecks for video-text representation learning](https://mlsanity.com/paper/2010.02824/) (2020)
- [Quality Assessment of In-the-Wild Videos](https://mlsanity.com/paper/1908.00375/) (2019)

## Built on by (most cited first, 30 of 128)

- [Self-Chained Image-Language Model for Video Localization and Question Answering](https://mlsanity.com/paper/2305.06988/) (2023)
- [Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?](https://mlsanity.com/paper/2301.00184/) (2022)
- [CLIP-ViP: Adapting Pre-trained Image-Text Model to Video-Language Representation Alignment](https://mlsanity.com/paper/2209.06430/) (2022)
- [Revisiting Temporal Modeling for CLIP-based Image-to-Video Knowledge Transferring](https://mlsanity.com/paper/2301.11116/) (2023)
- [Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations](https://mlsanity.com/paper/2211.11427/) (2022)
- [Koala: Key frame-conditioned long video-LLM](https://mlsanity.com/paper/2404.04346/) (2024)
- [UATVR: Uncertainty-Adaptive Text-Video Retrieval](https://mlsanity.com/paper/2301.06309/) (2023)
- [VITATECS: A Diagnostic Dataset for Temporal Concept Understanding of Video-Language Models](https://mlsanity.com/paper/2311.17404/) (2023)
- [KeyVideoLLM: Towards Large-scale Video Keyframe Selection](https://mlsanity.com/paper/2407.03104/) (2024)
- [DiffusionRet: Generative Text-Video Retrieval with Diffusion Model](https://mlsanity.com/paper/2303.09867/) (2023)
- [Unified Coarse-to-Fine Alignment for Video-Text Retrieval](https://mlsanity.com/paper/2309.10091/) (2023)
- [TESTA: Temporal-Spatial Token Aggregation for Long-form Video-Language Understanding](https://mlsanity.com/paper/2310.19060/) (2023)
- [Video-Text as Game Players: Hierarchical Banzhaf Interaction for Cross-Modal Representation Learning](https://mlsanity.com/paper/2303.14369/) (2023)
- [Clover: Towards A Unified Video-Language Alignment and Fusion Model](https://mlsanity.com/paper/2207.07885/) (2022)
- [TempMe: Video Temporal Token Merging for Efficient Text-Video Retrieval](https://mlsanity.com/paper/2409.01156/) (2024)
- [ECLIPSE: Efficient Long-range Video Retrieval using Sight and Sound](https://mlsanity.com/paper/2204.02874/) (2022)
- [VoP: Text-Video Co-operative Prompt Tuning for Cross-Modal Retrieval](https://mlsanity.com/paper/2211.12764/) (2022)
- [Cross-Modal Adapter for Vision-Language Retrieval](https://mlsanity.com/paper/2211.09623/) (2022)
- [Prompt Switch: Efficient CLIP Adaptation for Text-Video Retrieval](https://mlsanity.com/paper/2308.07648/) (2023)
- [Text Is MASS: Modeling as Stochastic Embedding for Text-Video Retrieval](https://mlsanity.com/paper/2403.17998/) (2024)
- [Text-Video Retrieval with Disentangled Conceptualization and Set-to-Set Alignment](https://mlsanity.com/paper/2305.12218/) (2023)
- [DGL: Dynamic Global-Local Prompt Tuning for Text-Video Retrieval](https://mlsanity.com/paper/2401.10588/) (2024)
- [Prototype-based Aleatoric Uncertainty Quantification for Cross-modal Retrieval](https://mlsanity.com/paper/2309.17093/) (2023)
- [Audio-Enhanced Text-to-Video Retrieval using Text-Conditioned Feature Alignment](https://mlsanity.com/paper/2307.12964/) (2023)
- [Balance Act: Mitigating Hubness in Cross-Modal Retrieval with Query and Gallery Banks](https://mlsanity.com/paper/2310.11612/) (2023)
- [Video-ColBERT: Contextualized Late Interaction for Text-to-Video Retrieval](https://mlsanity.com/paper/2503.19009/) (2025)
- [ReVisionLLM: Recursive Vision-Language Model for Temporal Grounding in Hour-Long Videos](https://mlsanity.com/paper/2411.14901/) (2024)
- [LiteVL: Efficient Video-Language Learning with Enhanced Spatial-Temporal Modeling](https://mlsanity.com/paper/2210.11929/) (2022)
- [Meta-Personalizing Vision-Language Models to Find Named Instances in Video](https://mlsanity.com/paper/2306.10169/) (2023)
- [RAP: Efficient Text-Video Retrieval with Sparse-and-Correlated Adapter](https://mlsanity.com/paper/2405.19465/) (2024)

## Abstract (arXiv)

In text-video retrieval, the objective is to learn a cross-modal similarity function between a text and a video that ranks relevant text-video pairs higher than irrelevant pairs. However, videos inherently express a much wider gamut of information than texts. Instead, texts often capture sub-regions of entire videos and are most semantically similar to certain frames within videos. Therefore, for a given text, a retrieval model should focus on the text's most semantically similar video sub-regions to make a more relevant comparison. Yet, most existing works aggregate entire videos without directly considering text. Common text-agnostic aggregations schemes include mean-pooling or self-attention over the frames, but these are likely to encode misleading visual information not described in the given text. To address this, we propose a cross-modal attention model called X-Pool that reasons between a text and the frames of a video. Our core mechanism is a scaled dot product attention for a text to attend to its most semantically similar frames. We then generate an aggregated video representation conditioned on the text's attention weights over the frames. We evaluate our method on three benchmark datasets of MSR-VTT, MSVD and LSMDC, achieving new state-of-the-art results by up to 12% in relative improvement in Recall@1. Our findings thereby highlight the importance of joint text-video reasoning to extract important visual cues according to text. Full code and demo can be found at: https://layer6ai-labs.github.io/xpool/