# Deep Feature Flow for Video Recognition

arXiv: https://arxiv.org/abs/1611.07715 · HTML: https://mlsanity.com/paper/1611.07715/

## Key facts

- Cited by 186 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Nov 2016.

## Built on by (most cited first, 30 of 186)

- [BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers](https://mlsanity.com/paper/2203.17270/) (2022)
- [KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D](https://mlsanity.com/paper/2109.13410/) (2021)
- [Occluded Video Instance Segmentation: A Benchmark](https://mlsanity.com/paper/2102.01558/) (2021)
- [A Survey on Deep Learning Technique for Video Segmentation](https://mlsanity.com/paper/2107.01153/) (2021)
- [Transformer-Based Visual Segmentation: A Survey](https://mlsanity.com/paper/2304.09854/) (2023)
- [Video K-Net: A Simple, Strong, and Unified Baseline for Video Segmentation](https://mlsanity.com/paper/2204.04656/) (2022)
- [TransVOD: End-to-End Video Object Detection with Spatial-Temporal Transformers](https://mlsanity.com/paper/2201.05047/) (2022)
- [Adaptive Focus for Efficient Video Recognition](https://mlsanity.com/paper/2105.03245/) (2021)
- [STEP: Segmenting and Tracking Every Pixel](https://mlsanity.com/paper/2102.11859/) (2021)
- [Semantic Segmentation using Vision Transformers: A survey](https://mlsanity.com/paper/2305.03273/) (2023)
- [Self-Supervised Monocular Depth and Ego-Motion Estimation in Endoscopy: Appearance Flow to the Rescue](https://mlsanity.com/paper/2112.08122/) (2021)
- [MPPNet: Multi-Frame Feature Intertwining with Proxy Points for 3D Temporal Object Detection](https://mlsanity.com/paper/2205.05979/) (2022)
- [Temporal Memory Attention for Video Semantic Segmentation](https://mlsanity.com/paper/2102.08643/) (2021)
- [Temporal RoI Align for Video Object Recognition](https://mlsanity.com/paper/2109.03495/) (2021)
- [End-to-End Video Object Detection with Spatial-Temporal Transformers](https://mlsanity.com/paper/2105.10920/) (2021)
- [TF-Blender: Temporal Feature Blender for Video Object Detection](https://mlsanity.com/paper/2108.05821/) (2021)
- [PolyphonicFormer: Unified Query Learning for Depth-aware Video Panoptic Segmentation](https://mlsanity.com/paper/2112.02582/) (2021)
- [TubeFormer-DeepLab: Video Mask Transformer](https://mlsanity.com/paper/2205.15361/) (2022)
- [Time Does Tell: Self-Supervised Time-Tuning of Dense Image Representations](https://mlsanity.com/paper/2308.11796/) (2023)
- [Deep Learning for UAV-based Object Detection and Tracking: A Survey](https://mlsanity.com/paper/2110.12638/) (2021)
- [Less is More: Reducing Task and Model Complexity for 3D Point Cloud Semantic Segmentation](https://mlsanity.com/paper/2303.11203/) (2023)
- [Skip-Convolutions for Efficient Video Processing](https://mlsanity.com/paper/2104.11487/) (2021)
- [Stubborn: A Strong Baseline for Indoor Object Navigation](https://mlsanity.com/paper/2203.07359/) (2022)
- [A New Dataset and A Baseline Model for Breast Lesion Detection in Ultrasound Videos](https://mlsanity.com/paper/2207.00141/) (2022)
- [AuxAdapt: Stable and Efficient Test-Time Adaptation for Temporally Consistent Video Semantic Segmentation](https://mlsanity.com/paper/2110.12369/) (2021)
- [Flow-Based Feature Fusion for Vehicle-Infrastructure Cooperative 3D Object Detection](https://mlsanity.com/paper/2311.01682/) (2023)
- [Discovering Sounding Objects by Audio Queries for Audio Visual Segmentation](https://mlsanity.com/paper/2309.09501/) (2023)
- [Video Super-Resolution Transformer with Masked Inter&Intra-Frame Attention](https://mlsanity.com/paper/2401.06312/) (2024)
- [Self-Supervised Representation Learning from Flow Equivariance](https://mlsanity.com/paper/2101.06553/) (2021)
- [LiDAR-based Recurrent 3D Semantic Segmentation with Temporal Memory Alignment](https://mlsanity.com/paper/2103.02263/) (2021)

## Abstract (arXiv)

Deep convolutional neutral networks have achieved great success on image recognition tasks. Yet, it is non-trivial to transfer the state-of-the-art image recognition networks to videos as per-frame evaluation is too slow and unaffordable. We present deep feature flow, a fast and accurate framework for video recognition. It runs the expensive convolutional sub-network only on sparse key frames and propagates their deep feature maps to other frames via a flow field. It achieves significant speedup as flow computation is relatively fast. The end-to-end training of the whole architecture significantly boosts the recognition accuracy. Deep feature flow is flexible and general. It is validated on two recent large scale video datasets. It makes a large step towards practical video recognition.