# TACo: Token-aware Cascade Contrastive Learning for Video-Text Alignment

arXiv: https://arxiv.org/abs/2108.09980 · HTML: https://mlsanity.com/paper/2108.09980/

## Key facts

- Cited by 102 papers in the map (data through 14 Oct 2026).
- Placed in MLLM training and visual instruction tuning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 43 of its 61 references that are in the map.
- First posted on arXiv 23 Aug 2021.

## Placed in

- Multimodal LLMs / vision-language models / [MLLM training and visual instruction tuning](https://mlsanity.com/mllm/mllm-training-and-visual-instruction-tuning/)

## Builds on (most cited first, 30 of 43)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [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)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks](https://mlsanity.com/paper/1908.02265/) (2019)
- [LXMERT: Learning Cross-Modality Encoder Representations from Transformers](https://mlsanity.com/paper/1908.07490/) (2019)
- [Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks](https://mlsanity.com/paper/2004.06165/) (2020)
- [A Closer Look at Spatiotemporal Convolutions for Action Recognition](https://mlsanity.com/paper/1711.11248/) (2017)
- [HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips](https://mlsanity.com/paper/1906.03327/) (2019)
- [Dense-Captioning Events in Videos](https://mlsanity.com/paper/1705.00754/) (2017)
- [VideoBERT: A Joint Model for Video and Language Representation Learning](https://mlsanity.com/paper/1904.01766/) (2019)
- [Towards Automatic Learning of Procedures from Web Instructional Videos](https://mlsanity.com/paper/1703.09788/) (2017)
- [Can Spatiotemporal 3D CNNs Retrace the History of 2D CNNs and ImageNet?](https://mlsanity.com/paper/1711.09577/) (2017)
- [Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification](https://mlsanity.com/paper/1712.04851/) (2017)
- [End-to-End Learning of Visual Representations from Uncurated Instructional Videos](https://mlsanity.com/paper/1912.06430/) (2019)
- [Unified Vision-Language Pre-Training for Image Captioning and VQA](https://mlsanity.com/paper/1909.11059/) (2019)
- [TVQA: Localized, Compositional Video Question Answering](https://mlsanity.com/paper/1809.01696/) (2018)
- [Stacked Cross Attention for Image-Text Matching](https://mlsanity.com/paper/1803.08024/) (2018)
- [Multi-modal Transformer for Video Retrieval](https://mlsanity.com/paper/2007.10639/) (2020)
- [TGIF-QA: Toward Spatio-Temporal Reasoning in Visual Question Answering](https://mlsanity.com/paper/1704.04497/) (2017)
- [HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training](https://mlsanity.com/paper/2005.00200/) (2020)
- [COIN: A Large-scale Dataset for Comprehensive Instructional Video Analysis](https://mlsanity.com/paper/1903.02874/) (2019)
- [MovieQA: Understanding Stories in Movies through Question-Answering](https://mlsanity.com/paper/1512.02902/) (2015)
- [ActBERT: Learning Global-Local Video-Text Representations](https://mlsanity.com/paper/2011.07231/) (2020)
- [UniVL: A Unified Video and Language Pre-Training Model for Multimodal Understanding and Generation](https://mlsanity.com/paper/2002.06353/) (2020)
- [Experience Grounds Language](https://mlsanity.com/paper/2004.10151/) (2020)

## Built on by (most cited first, 30 of 102)

- [Multimodal Learning with Transformers: A Survey](https://mlsanity.com/paper/2206.06488/) (2022)
- [X-CLIP: End-to-End Multi-grained Contrastive Learning for Video-Text Retrieval](https://mlsanity.com/paper/2207.07285/) (2022)
- [Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning](https://mlsanity.com/paper/2302.14115/) (2023)
- [VIOLET : End-to-End Video-Language Transformers with Masked Visual-token Modeling](https://mlsanity.com/paper/2111.12681/) (2021)
- [All in One: Exploring Unified Video-Language Pre-training](https://mlsanity.com/paper/2203.07303/) (2022)
- [VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset](https://mlsanity.com/paper/2304.08345/) (2023)
- [EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbone](https://mlsanity.com/paper/2307.05463/) (2023)
- [Vision-Language Pre-training: Basics, Recent Advances, and Future Trends](https://mlsanity.com/paper/2210.09263/) (2022)
- [TS2-Net: Token Shift and Selection Transformer for Text-Video Retrieval](https://mlsanity.com/paper/2207.07852/) (2022)
- [Language Models Can See: Plugging Visual Controls in Text Generation](https://mlsanity.com/paper/2205.02655/) (2022)
- [Temporal Alignment Networks for Long-term Video](https://mlsanity.com/paper/2204.02968/) (2022)
- [Bridging Video-text Retrieval with Multiple Choice Questions](https://mlsanity.com/paper/2201.04850/) (2022)
- [Verbs in Action: Improving verb understanding in video-language models](https://mlsanity.com/paper/2304.06708/) (2023)
- [LAVENDER: Unifying Video-Language Understanding as Masked Language Modeling](https://mlsanity.com/paper/2206.07160/) (2022)
- [HiTeA: Hierarchical Temporal-Aware Video-Language Pre-training](https://mlsanity.com/paper/2212.14546/) (2022)
- [VideoCoCa: Video-Text Modeling with Zero-Shot Transfer from Contrastive Captioners](https://mlsanity.com/paper/2212.04979/) (2022)
- [HierVL: Learning Hierarchical Video-Language Embeddings](https://mlsanity.com/paper/2301.02311/) (2023)
- [UnLoc: A Unified Framework for Video Localization Tasks](https://mlsanity.com/paper/2308.11062/) (2023)
- [Long-Form Video-Language Pre-Training with Multimodal Temporal Contrastive Learning](https://mlsanity.com/paper/2210.06031/) (2022)
- [Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations](https://mlsanity.com/paper/2211.11427/) (2022)
- [CoVR-2: Automatic Data Construction for Composed Video Retrieval](https://mlsanity.com/paper/2308.14746/) (2023)
- [Unified Coarse-to-Fine Alignment for Video-Text Retrieval](https://mlsanity.com/paper/2309.10091/) (2023)
- [Learning Procedure-aware Video Representation from Instructional Videos and Their Narrations](https://mlsanity.com/paper/2303.17839/) (2023)
- [Video-Text as Game Players: Hierarchical Banzhaf Interaction for Cross-Modal Representation Learning](https://mlsanity.com/paper/2303.14369/) (2023)
- [LocVTP: Video-Text Pre-training for Temporal Localization](https://mlsanity.com/paper/2207.10362/) (2022)
- [Clover: Towards A Unified Video-Language Alignment and Fusion Model](https://mlsanity.com/paper/2207.07885/) (2022)
- [Video-Mined Task Graphs for Keystep Recognition in Instructional Videos](https://mlsanity.com/paper/2307.08763/) (2023)
- [Multi-granularity Correspondence Learning from Long-term Noisy Videos](https://mlsanity.com/paper/2401.16702/) (2024)
- [COTS: Collaborative Two-Stream Vision-Language Pre-Training Model for Cross-Modal Retrieval](https://mlsanity.com/paper/2204.07441/) (2022)
- [TaCL: Improving BERT Pre-training with Token-aware Contrastive Learning](https://mlsanity.com/paper/2111.04198/) (2021)

## Abstract (arXiv)

Contrastive learning has been widely used to train transformer-based vision-language models for video-text alignment and multi-modal representation learning. This paper presents a new algorithm called Token-Aware Cascade contrastive learning (TACo) that improves contrastive learning using two novel techniques. The first is the token-aware contrastive loss which is computed by taking into account the syntactic classes of words. This is motivated by the observation that for a video-text pair, the content words in the text, such as nouns and verbs, are more likely to be aligned with the visual contents in the video than the function words. Second, a cascade sampling method is applied to generate a small set of hard negative examples for efficient loss estimation for multi-modal fusion layers. To validate the effectiveness of TACo, in our experiments we finetune pretrained models for a set of downstream tasks including text-video retrieval (YouCook2, MSR-VTT and ActivityNet), video action step localization (CrossTask), video action segmentation (COIN). The results show that our models attain consistent improvements across different experimental settings over previous methods, setting new state-of-the-art on three public text-video retrieval benchmarks of YouCook2, MSR-VTT and ActivityNet.