# ConvTransformer: A Convolutional Transformer Network for Video Frame Synthesis

arXiv: https://arxiv.org/abs/2011.10185 · HTML: https://mlsanity.com/paper/2011.10185/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Nov 2020.

## Built on by (most cited first, 30 of 34)

- [UniFormer: Unifying Convolution and Self-attention for Visual Recognition](https://mlsanity.com/paper/2201.09450/) (2022)
- [UniFormer: Unified Transformer for Efficient Spatiotemporal Representation Learning](https://mlsanity.com/paper/2201.04676/) (2022)
- [OadTR: Online Action Detection with Transformers](https://mlsanity.com/paper/2106.11149/) (2021)
- [A Transformer-Based Feature Segmentation and Region Alignment Method For UAV-View Geo-Localization](https://mlsanity.com/paper/2201.09206/) (2022)
- [Facial Expression Recognition with Visual Transformers and Attentional Selective Fusion](https://mlsanity.com/paper/2103.16854/) (2021)
- [ConTNet: Why not use convolution and transformer at the same time?](https://mlsanity.com/paper/2104.13497/) (2021)
- [Less is More: Consistent Video Depth Estimation with Masked Frames Modeling](https://mlsanity.com/paper/2208.00380/) (2022)
- [3D Medical Point Transformer: Introducing Convolution to Attention Networks for Medical Point Cloud Analysis](https://mlsanity.com/paper/2112.04863/) (2021)
- [VPTR: Efficient Transformers for Video Prediction](https://mlsanity.com/paper/2203.15836/) (2022)
- [MIMO Is All You Need : A Strong Multi-In-Multi-Out Baseline for Video Prediction](https://mlsanity.com/paper/2212.04655/) (2022)
- [Video Prediction by Efficient Transformers](https://mlsanity.com/paper/2212.06026/) (2022)
- [Continuous Intermediate Token Learning with Implicit Motion Manifold for Keyframe Based Motion Interpolation](https://mlsanity.com/paper/2303.14926/) (2023)
- [NAST: Non-Autoregressive Spatial-Temporal Transformer for Time Series Forecasting](https://mlsanity.com/paper/2102.05624/) (2021)
- [Transformers predicting the future. Applying attention in next-frame and time series forecasting](https://mlsanity.com/paper/2108.08224/) (2021)
- [SiamTrans: Zero-Shot Multi-Frame Image Restoration with Pre-Trained Siamese Transformers](https://mlsanity.com/paper/2112.09426/) (2021)
- [JNMR: Joint Non-linear Motion Regression for Video Frame Interpolation](https://mlsanity.com/paper/2206.04231/) (2022)
- [A unified model for continuous conditional video prediction](https://mlsanity.com/paper/2210.05810/) (2022)
- [Characterization of anomalous diffusion through convolutional transformers](https://mlsanity.com/paper/2210.04959/) (2022)
- [NVDS+: Towards Efficient and Versatile Neural Stabilizer for Video Depth Estimation](https://mlsanity.com/paper/2307.08695/) (2023)
- [Soft-Sensing ConFormer: A Curriculum Learning-based Convolutional Transformer](https://mlsanity.com/paper/2111.06981/) (2021)
- [SVFormer: A Direct Training Spiking Transformer for Efficient Video Action Recognition](https://mlsanity.com/paper/2406.15034/) (2024)
- [Deformation Driven Seq2Seq Longitudinal Tumor and Organs-at-Risk Prediction for Radiotherapy](https://mlsanity.com/paper/2106.09076/) (2021)
- [EEG-ConvTransformer for Single-Trial EEG based Visual Stimuli Classification](https://mlsanity.com/paper/2107.03983/) (2021)
- [PTCT: Patches with 3D-Temporal Convolutional Transformer Network for Precipitation Nowcasting](https://mlsanity.com/paper/2112.01085/) (2021)
- ["If you could see me through my eyes": Predicting Pedestrian Perception](https://mlsanity.com/paper/2202.13981/) (2022)
- [ConvFormer: Parameter Reduction in Transformer Models for 3D Human Pose Estimation by Leveraging Dynamic Multi-Headed Convolutional Attention](https://mlsanity.com/paper/2304.02147/) (2023)
- [Heterogeneous Encoders Scaling In The Transformer For Neural Machine Translation](https://mlsanity.com/paper/2312.15872/) (2023)
- [Micro-Expression Recognition via Fine-Grained Dynamic Perception](https://mlsanity.com/paper/2509.06015/) (2025)
- [Dispatcher: A Message-Passing Approach To Language Modelling](https://mlsanity.com/paper/2105.03994/) (2021)
- [WavFT: Acoustic model finetuning with labelled and unlabelled data](https://mlsanity.com/paper/2204.00348/) (2022)

## Abstract (arXiv)

Deep Convolutional Neural Networks (CNNs) are powerful models that have achieved excellent performance on difficult computer vision tasks. Although CNNs perform well whenever large labeled training samples are available, they work badly on video frame synthesis due to objects deforming and moving, scene lighting changes, and cameras moving in video sequence. In this paper, we present a novel and general end-to-end architecture, called convolutional Transformer or ConvTransformer, for video frame sequence learning and video frame synthesis. The core ingredient of ConvTransformer is the proposed attention layer, i.e., multi-head convolutional self-attention layer, that learns the sequential dependence of video sequence. ConvTransformer uses an encoder, built upon multi-head convolutional self-attention layer, to encode the sequential dependence between the input frames, and then a decoder decodes the long-term dependence between the target synthesized frames and the input frames. Experiments on video future frame extrapolation task show ConvTransformer to be superior in quality while being more parallelizable to recent approaches built upon convolutional LSTM (ConvLSTM). To the best of our knowledge, this is the first time that ConvTransformer architecture is proposed and applied to video frame synthesis.