Deep Feature Flow for Video Recognition
Xizhou Zhu,Yuwen Xiong,Jifeng Dai,Lu Yuan,Yichen Wei +4 more
- pp 4141-4150
TLDR
Deep Feature Flow as mentioned in this paper runs the expensive convolutional sub-network only on sparse key frames and propagates their deep feature maps to other frames via a flow field, which achieves significant speedup as flow computation is relatively fast.Abstract:
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. Code would be released.read more
Citations
More filters
Book ChapterDOI
Simple Baselines for Human Pose Estimation and Tracking
Bin Xiao,Haiping Wu,Yichen Wei +2 more
TL;DR: In this article, the authors provide simple and effective baseline methods for pose estimation, which are helpful for inspiring and evaluating new ideas for the field and achieve state-of-the-art results on challenging benchmarks.
Book ChapterDOI
ICNet for Real-Time Semantic Segmentation on High-Resolution Images
TL;DR: ICNet as discussed by the authors proposes an image cascade network (ICNet) that incorporates multi-resolution branches under proper label guidance to reduce a large portion of computation for pixel-wise label inference, which yields real-time inference on a single GPU card.
Journal ArticleDOI
A Survey of Deep Learning-Based Object Detection
TL;DR: This survey provides a comprehensive overview of a variety of object detection methods in a systematic manner, covering the one-stage and two-stage detectors, and lists the traditional and new applications.
Proceedings ArticleDOI
Flow-Guided Feature Aggregation for Video Object Detection
TL;DR: This work presents flow-guided feature aggregation, an accurate and end-to-end learning framework for video object detection that improves the per-frame features by aggregation of nearby features along the motion paths, and thus improves the video recognition accuracy.
Journal ArticleDOI
The ApolloScape Open Dataset for Autonomous Driving and Its Application
TL;DR: This paper provides a sensor fusion scheme integrating camera videos, consumer-grade motion sensors (GPS/IMU), and a 3D semantic map in order to achieve robust self-localization and semantic segmentation for autonomous driving.
References
More filters
Proceedings ArticleDOI
Deep Residual Learning for Image Recognition
TL;DR: In this article, the authors proposed a residual learning framework to ease the training of networks that are substantially deeper than those used previously, which won the 1st place on the ILSVRC 2015 classification task.
Proceedings Article
ImageNet Classification with Deep Convolutional Neural Networks
TL;DR: The state-of-the-art performance of CNNs was achieved by Deep Convolutional Neural Networks (DCNNs) as discussed by the authors, which consists of five convolutional layers, some of which are followed by max-pooling layers, and three fully-connected layers with a final 1000-way softmax.
Proceedings Article
Very Deep Convolutional Networks for Large-Scale Image Recognition
Karen Simonyan,Andrew Zisserman +1 more
TL;DR: In this paper, the authors investigated the effect of the convolutional network depth on its accuracy in the large-scale image recognition setting and showed that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 layers.
Proceedings ArticleDOI
Going deeper with convolutions
Christian Szegedy,Wei Liu,Yangqing Jia,Pierre Sermanet,Scott Reed,Dragomir Anguelov,Dumitru Erhan,Vincent Vanhoucke,Andrew Rabinovich +8 more
TL;DR: Inception as mentioned in this paper is a deep convolutional neural network architecture that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVRC14).
Proceedings Article
Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Sergey Ioffe,Christian Szegedy +1 more
TL;DR: Applied to a state-of-the-art image classification model, Batch Normalization achieves the same accuracy with 14 times fewer training steps, and beats the original model by a significant margin.