S-DOD-CNN: Doubly Injecting Spatially-Preserved Object Information for Event Recognition

  title={S-DOD-CNN: Doubly Injecting Spatially-Preserved Object Information for Event Recognition},
  author={Hyungtae Lee and Sungmin Eum and Heesung Kwon},
  journal={ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  • Hyungtae Lee, Sungmin Eum, H. Kwon
  • Published 11 February 2019
  • Computer Science
  • ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
We present a novel event recognition approach called Spatially-preserved Doubly-injected Object Detection CNN (S-DOD-CNN), which incorporates the spatially preserved object detection information in both a direct and an indirect way. Indirect injection is carried out by simply sharing the weights between the object detection modules and the event recognition module. Meanwhile, our novelty lies in the fact that we have preserved the spatial information for the direct injection. Once multiple… 
ME R-CNN: Multi-Expert R-CNN for Object Detection
A practical training strategy is introduced which is tailored to optimize ME, EAN, and the shared network in an end-to-end fashion and shows that both of the architectures provide considerable performance increase over the baselines on PASCAL VOC 07, 12, and MS COCO datasets.
How to practically deploy deep neural networks to distributed network environments for scene perception
The proposed work aims to decompose DNNs and then distribute over edge nodes in such a way that a trade-off between resources available in the constrained network and recognition performance can be optimized.
DBF: Dynamic Belief Fusion for Combining Multiple Object Detectors
  • Hyungtae Lee, H. Kwon
  • Computer Science, Medicine
    IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2021
Experiments show that the detection accuracy of the DBF is significantly higher than any of the baseline fusion approaches as well as individual detectors used for the fusion.


DOD-CNN: Doubly-injecting Object Information for Event Recognition
  • Hyungtae Lee, Sungmin Eum, H. Kwon
  • Computer Science
    ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • 2019
A novel approach, referred to as Doubly-injected Object Detection CNN (DOD-CNN), exploiting the object information in both ways for the task of event recognition, and introduces a batch pooling layer which constructs one representative feature map from multiple object hypotheses.
IOD-CNN: Integrating object detection networks for event recognition
This work presents a novel unified deep CNN architecture which integrates architecturally different, yet semantically-related object detection networks to enhance the performance of the event recognition task.
Better Exploiting OS-CNNs for Better Event Recognition in Images
This paper addresses the problem of cultural event recognition in still images and focuses on applying deep learning methods on this problem by utilizing the successful architecture of Object-Scene Convolutional Neural Networks (OS-CNNs) to perform event recognition.
Object-Scene Convolutional Neural Networks for event recognition in images
This paper designs a new architecture, called Object-Scene Convolutional Neural Network (OS-CNN), which is decomposed into object net and scene net, which extract useful information for event understanding from the perspective of objects and scene context, respectively, and investigates different network architectures for OS-CNN design.
Learning Deep Features for Scene Recognition using Places Database
A new scene-centric database called Places with over 7 million labeled pictures of scenes is introduced with new methods to compare the density and diversity of image datasets and it is shown that Places is as dense as other scene datasets and has more diversity.
Detection bank: an object detection based video representation for multimedia event recognition
This paper proposes an image representation, called Detection Bank, based on the detection images from a large number of windowed object detectors where an image is represented by different statistics derived from these detections, and empirically shows that it captures complementary information to state-of-the-art representations such as Spatial Pyramid Matching and Object Bank.
Going deeper with CNN in malicious crowd event classification
It is found that deeper networks typically show better accuracy, and that GoogLeNet is the most favorable among the seven architectures for the task of malicious event classification.
Exploitation of Semantic Keywords for Malicious Event Classification
This paper shows that incorporating the keyword-driven information into early-and late-fusion approaches can significantly enhance malicious event classification and demonstrates the beneficial aspects of using semantically-driven keyword information.
Enhanced object detection via fusion with prior beliefs from image classification
Experimental results show that the detection performance of all the detection algorithms used in the proposed work is improved on benchmark datasets via the proposed fusion framework.
Rapid object detection using a boosted cascade of simple features
  • Paul A. Viola, Michael J. Jones
  • Computer Science
    Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001
  • 2001
A machine learning approach for visual object detection which is capable of processing images extremely rapidly and achieving high detection rates and the introduction of a new image representation called the "integral image" which allows the features used by the detector to be computed very quickly.