# Improving Video-Text Retrieval by Multi-Stream Corpus Alignment and Dual Softmax Loss

arXiv: https://arxiv.org/abs/2109.04290 · HTML: https://mlsanity.com/paper/2109.04290/

## Key facts

- Cited by 116 papers in the map (data through 14 Oct 2026).
- Placed in Vision mixture-of-experts, one of 12 directions in Mixture-of-experts.
- Builds on 28 of its 46 references that are in the map.
- First posted on arXiv 9 Sep 2021.

## Placed in

- Mixture-of-experts / [Vision mixture-of-experts](https://mlsanity.com/moe/vision-mixture-of-experts/)

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [ViViT: A Video Vision Transformer](https://mlsanity.com/paper/2103.15691/) (2021)
- [Accurate, Large Minibatch SGD: Training ImageNet in 1 Hour](https://mlsanity.com/paper/1706.02677/) (2017)
- [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)
- [An Overview of Multi-Task Learning in Deep Neural Networks](https://mlsanity.com/paper/1706.05098/) (2017)
- [CogView: Mastering Text-to-Image Generation via Transformers](https://mlsanity.com/paper/2105.13290/) (2021)
- [Localizing Moments in Video with Natural Language](https://mlsanity.com/paper/1708.01641/) (2017)
- [CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval](https://mlsanity.com/paper/2104.08860/) (2021)
- [Less is More: ClipBERT for Video-and-Language Learning via Sparse Sampling](https://mlsanity.com/paper/2102.06183/) (2021)
- [Multi-modal Transformer for Video Retrieval](https://mlsanity.com/paper/2007.10639/) (2020)
- [ActBERT: Learning Global-Local Video-Text Representations](https://mlsanity.com/paper/2011.07231/) (2020)
- [CLIP2Video: Mastering Video-Text Retrieval via Image CLIP](https://mlsanity.com/paper/2106.11097/) (2021)
- [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)
- [Fine-grained Video-Text Retrieval with Hierarchical Graph Reasoning](https://mlsanity.com/paper/2003.00392/) (2020)
- [VinVL: Revisiting Visual Representations in Vision-Language Models](https://mlsanity.com/paper/2101.00529/) (2021)
- [T2VLAD: Global-Local Sequence Alignment for Text-Video Retrieval](https://mlsanity.com/paper/2104.10054/) (2021)
- [HiT: Hierarchical Transformer with Momentum Contrast for Video-Text Retrieval](https://mlsanity.com/paper/2103.15049/) (2021)
- [MDMMT: Multidomain Multimodal Transformer for Video Retrieval](https://mlsanity.com/paper/2103.10699/) (2021)
- [Look, Imagine and Match: Improving Textual-Visual Cross-Modal Retrieval with Generative Models](https://mlsanity.com/paper/1711.06420/) (2017)
- [The Long-Short Story of Movie Description](https://mlsanity.com/paper/1506.01698/) (2015)

## Built on by (most cited first, 30 of 116)

- [Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language](https://mlsanity.com/paper/2204.00598/) (2022)
- [InternVideo: General Video Foundation Models via Generative and Discriminative Learning](https://mlsanity.com/paper/2212.03191/) (2022)
- [Frozen CLIP Models are Efficient Video Learners](https://mlsanity.com/paper/2208.03550/) (2022)
- [VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset](https://mlsanity.com/paper/2305.18500/) (2023)
- [VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset](https://mlsanity.com/paper/2304.08345/) (2023)
- [TS2-Net: Token Shift and Selection Transformer for Text-Video Retrieval](https://mlsanity.com/paper/2207.07852/) (2022)
- [Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?](https://mlsanity.com/paper/2301.00184/) (2022)
- [Learning Audio-Video Modalities from Image Captions](https://mlsanity.com/paper/2204.00679/) (2022)
- [CLIP-ViP: Adapting Pre-trained Image-Text Model to Video-Language Representation Alignment](https://mlsanity.com/paper/2209.06430/) (2022)
- [LAVENDER: Unifying Video-Language Understanding as Masked Language Modeling](https://mlsanity.com/paper/2206.07160/) (2022)
- [HierVL: Learning Hierarchical Video-Language Embeddings](https://mlsanity.com/paper/2301.02311/) (2023)
- [Don't Stop Learning: Towards Continual Learning for the CLIP Model](https://mlsanity.com/paper/2207.09248/) (2022)
- [Revisiting Temporal Modeling for CLIP-based Image-to-Video Knowledge Transferring](https://mlsanity.com/paper/2301.11116/) (2023)
- [DePT: Decoupled Prompt Tuning](https://mlsanity.com/paper/2309.07439/) (2023)
- [LVAgent: Long Video Understanding by Multi-Round Dynamical Collaboration of MLLM Agents](https://mlsanity.com/paper/2503.10200/) (2025)
- [Zero-Shot Category-Level Object Pose Estimation](https://mlsanity.com/paper/2204.03635/) (2022)
- [A CLIP-Hitchhiker's Guide to Long Video Retrieval](https://mlsanity.com/paper/2205.08508/) (2022)
- [Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations](https://mlsanity.com/paper/2211.11427/) (2022)
- [UATVR: Uncertainty-Adaptive Text-Video Retrieval](https://mlsanity.com/paper/2301.06309/) (2023)
- [DirecT2V: Large Language Models are Frame-Level Directors for Zero-Shot Text-to-Video Generation](https://mlsanity.com/paper/2305.14330/) (2023)
- [Unified Coarse-to-Fine Alignment for Video-Text Retrieval](https://mlsanity.com/paper/2309.10091/) (2023)
- [Foundation Models for Video Understanding: A Survey](https://mlsanity.com/paper/2405.03770/) (2024)
- [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)
- [ECLIPSE: Efficient Long-range Video Retrieval using Sight and Sound](https://mlsanity.com/paper/2204.02874/) (2022)
- [Video-Mined Task Graphs for Keystep Recognition in Instructional Videos](https://mlsanity.com/paper/2307.08763/) (2023)
- [Text Is MASS: Modeling as Stochastic Embedding for Text-Video Retrieval](https://mlsanity.com/paper/2403.17998/) (2024)
- [Towards Generalisable Video Moment Retrieval: Visual-Dynamic Injection to Image-Text Pre-Training](https://mlsanity.com/paper/2303.00040/) (2023)
- [Disentangling Spatial and Temporal Learning for Efficient Image-to-Video Transfer Learning](https://mlsanity.com/paper/2309.07911/) (2023)
- [Enhancing Video-Language Representations with Structural Spatio-Temporal Alignment](https://mlsanity.com/paper/2406.19255/) (2024)

## Abstract (arXiv)

Employing large-scale pre-trained model CLIP to conduct video-text retrieval task (VTR) has become a new trend, which exceeds previous VTR methods. Though, due to the heterogeneity of structures and contents between video and text, previous CLIP-based models are prone to overfitting in the training phase, resulting in relatively poor retrieval performance. In this paper, we propose a multi-stream Corpus Alignment network with single gate Mixture-of-Experts (CAMoE) and a novel Dual Softmax Loss (DSL) to solve the two heterogeneity. The CAMoE employs Mixture-of-Experts (MoE) to extract multi-perspective video representations, including action, entity, scene, etc., then align them with the corresponding part of the text. In this stage, we conduct massive explorations towards the feature extraction module and feature alignment module. DSL is proposed to avoid the one-way optimum-match which occurs in previous contrastive methods. Introducing the intrinsic prior of each pair in a batch, DSL serves as a reviser to correct the similarity matrix and achieves the dual optimal match. DSL is easy to implement with only one-line code but improves significantly. The results show that the proposed CAMoE and DSL are of strong efficiency, and each of them is capable of achieving State-of-The-Art (SOTA) individually on various benchmarks such as MSR-VTT, MSVD, and LSMDC. Further, with both of them, the performance is advanced to a big extend, surpassing the previous SOTA methods for around 4.6% R@1 in MSR-VTT.