# Contrastive Learning of Semantic and Visual Representations for Text Tracking

arXiv: https://arxiv.org/abs/2112.14976 · HTML: https://mlsanity.com/paper/2112.14976/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 54 references that are in the map.
- First posted on arXiv 30 Dec 2021.

## Builds on (most cited first, 25 of 25)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [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)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics](https://mlsanity.com/paper/1705.07115/) (2017)
- [VL-BERT: Pre-training of Generic Visual-Linguistic Representations](https://mlsanity.com/paper/1908.08530/) (2019)
- [An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition](https://mlsanity.com/paper/1507.05717/) (2015)
- [Tracking Objects as Points](https://mlsanity.com/paper/2004.01177/) (2020)
- [EAST: An Efficient and Accurate Scene Text Detector](https://mlsanity.com/paper/1704.03155/) (2017)
- [COCO-Text: Dataset and Benchmark for Text Detection and Recognition in Natural Images](https://mlsanity.com/paper/1601.07140/) (2016)
- [Shape Robust Text Detection with Progressive Scale Expansion Network](https://mlsanity.com/paper/1903.12473/) (2019)
- [Towards Accurate Scene Text Recognition with Semantic Reasoning Networks](https://mlsanity.com/paper/2003.12294/) (2020)
- [SEED: Semantics Enhanced Encoder-Decoder Framework for Scene Text Recognition](https://mlsanity.com/paper/2005.10977/) (2020)
- [Semantic-aware Knowledge Distillation for Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2103.04059/) (2021)
- [Detecting Text in Natural Image with Connectionist Text Proposal Network](https://mlsanity.com/paper/1609.03605/) (2016)
- [PAN++: Towards Efficient and Accurate End-to-End Spotting of Arbitrarily-Shaped Text](https://mlsanity.com/paper/2105.00405/) (2021)
- [Towards End-to-end Text Spotting with Convolutional Recurrent Neural Networks](https://mlsanity.com/paper/1707.03985/) (2017)
- [A Bilingual, OpenWorld Video Text Dataset and End-to-end Video Text Spotter with Transformer](https://mlsanity.com/paper/2112.04888/) (2021)
- [You Only Recognize Once: Towards Fast Video Text Spotting](https://mlsanity.com/paper/1903.03299/) (2019)
- [Towards End-to-End Text Spotting in Natural Scenes](https://mlsanity.com/paper/1906.06013/) (2019)
- [Video Text Tracking With a Spatio-Temporal Complementary Model](https://mlsanity.com/paper/2111.04987/) (2021)

## Built on by (most cited first, 4 of 4)

- [End-to-End Video Text Spotting with Transformer](https://mlsanity.com/paper/2203.10539/) (2022)
- [Real-time End-to-End Video Text Spotter with Contrastive Representation Learning](https://mlsanity.com/paper/2207.08417/) (2022)
- [GloTSFormer: Global Video Text Spotting Transformer](https://mlsanity.com/paper/2401.03694/) (2024)
- [LOGO: Video Text Spotting with Language Collaboration and Glyph Perception Model](https://mlsanity.com/paper/2405.19194/) (2024)

## Abstract (arXiv)

Semantic representation is of great benefit to the video text tracking(VTT) task that requires simultaneously classifying, detecting, and tracking texts in the video. Most existing approaches tackle this task by appearance similarity in continuous frames, while ignoring the abundant semantic features. In this paper, we explore to robustly track video text with contrastive learning of semantic and visual representations. Correspondingly, we present an end-to-end video text tracker with Semantic and Visual Representations(SVRep), which detects and tracks texts by exploiting the visual and semantic relationships between different texts in a video sequence. Besides, with a light-weight architecture, SVRep achieves state-of-the-art performance while maintaining competitive inference speed. Specifically, with a backbone of ResNet-18, SVRep achieves an rm IDF1 of 65.9%, running at 16.7 FPS, on the ICDAR2015(video) dataset with 8.6% improvement than the previous state-of-the-art methods.