Abstract
Previous video object detection methods focus on aggregating the features of other frames into the current frame to alleviate the image degradation, but they rarely focus on multi-class scenes. Aggregating features of different classes will generate confusing information and affect network performance. This problem can be solved by using a classifier to divide the features. However, classifier method has three problems: (a) Heterogeneous high-similarity objects and homogeneous low-similarity objects affect the accuracy of the classifier. (b) Two objects whose positions overlap also affect the classifier. (c) Previous classifier method did not exploit sufficient global information. Therefore, we propose a new method that divides the features of different instances to deal with the problems of (a) and (b). Then we designed two new memories (one is Init Memory and the other is MDR) to solve problem (c). These three parts constitute the MIDFA network. Experiments show that our method achieves 83.76% mAP on the ImageNet VID dataset based on ResNet-101, and 84.6% mAP on ResNeXt-101. In addition, we also conduct experiments on a custom-designed multi-class VID dataset, and adding Instance Division and MDR can increase the mAP of the network by 0.6% compared to using only Init Memory.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bertasius, G., Torresani, L., Shi, J.: Object detection in video with spatiotemporal sampling networks. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11216, pp. 342–357. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01258-8_21
Chen, K., et al.: Optimizing video object detection via a scale-time lattice. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7814–7823 (2018)
Chen, Y., Cao, Y., Hu, H., Wang, L.: Memory enhanced global-local aggregation for video object detection. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 10337–10346 (2020)
Deng, H., et al.: Object guided external memory network for video object detection. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 6678–6687 (2019)
Deng, J., Pan, Y., Yao, T., Zhou, W., Li, H., Mei, T.: Relation distillation networks for video object detection. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 7023–7032 (2019)
Dosovitskiy, A., et al.: FlowNet: learning optical flow with convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2758–2766 (2015)
Gong, T., et al.: Temporal ROI align for video object recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 1442–1450 (2021)
Han, L., Wang, P., Yin, Z., Wang, F., Li, H.: Class-aware feature aggregation network for video object detection. IEEE Trans. Circuits Syst. Video Technol. 32, 8165–8178 (2021)
Han, L., Wang, P., Yin, Z., Wang, F., Li, H.: Context and structure mining network for video object detection. Int. J. Comput. Vision 129(10), 2927–2946 (2021)
Han, W., et al.: Seq-NMS for video object detection. arXiv preprint arXiv:1602.08465 (2016)
He, F., Gao, N., Li, Q., Du, S., Zhao, X., Huang, K.: Temporal context enhanced feature aggregation for video object detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 10941–10948 (2020)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Jiang, Z., et al.: Learning where to focus for efficient video object detection. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12361, pp. 18–34. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58517-4_2
Lin, L.: Dual semantic fusion network for video object detection. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 1855–1863 (2020)
Luo, H., Xie, W., Wang, X., Zeng, W.: Detect or track: towards cost-effective video object detection/tracking. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 8803–8810 (2019)
Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in Neural Information Processing Systems, vol. 28 (2015)
Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vision 115(3), 211–252 (2015)
Shvets, M., Liu, W., Berg, A.C.: Leveraging long-range temporal relationships between proposals for video object detection. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 9756–9764 (2019)
Sun, G., Hua, Y., Hu, G., Robertson, N.: MAMBA: multi-level aggregation via memory bank for video object detection. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 2620–2627 (2021)
Wu, H., Chen, Y., Wang, N., Zhang, Z.: Sequence level semantics aggregation for video object detection. In: Proceedings of the IEEE/CVF International Conference on Computer Vision, pp. 9217–9225 (2019)
Xie, S., Girshick, R., Dollár, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1492–1500 (2017)
Zhu, X., Dai, J., Yuan, L., Wei, Y.: Towards high performance video object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7210–7218 (2018)
Zhu, X., Wang, Y., Dai, J., Yuan, L., Wei, Y.: Flow-guided feature aggregation for video object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 408–417 (2017)
Han, M., Wang, Y., Chang, X., Qiao, Yu.: Mining inter-video proposal relations for video object detection. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12366, pp. 431–446. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58589-1_26
Acknowledgement
This work is supported by Shanghai “Science and Technology Innovation Action Plan” Venus Project (Sailing Special Project) under Grant 23YF1412900.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Chen, Q., Zhou, M., Yu, H. (2023). MIDFA: Memory-Based Instance Division and Feature Aggregation Network for Video Object Detection. In: Kashima, H., Ide, T., Peng, WC. (eds) Advances in Knowledge Discovery and Data Mining. PAKDD 2023. Lecture Notes in Computer Science(), vol 13937. Springer, Cham. https://doi.org/10.1007/978-3-031-33380-4_12
Download citation
DOI: https://doi.org/10.1007/978-3-031-33380-4_12
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-33379-8
Online ISBN: 978-3-031-33380-4
eBook Packages: Computer ScienceComputer Science (R0)