ABSTRACT
Video object detection is a challenging task due to the appearance deterioration problems in video frames. Thus, object features extracted from different frames of a video are usually deteriorated in varying degrees. Currently, some state-of-the-art methods enhance the deteriorated object features in a reference frame by aggregating the undeteriorated object features extracted from other frames, simply based on their learned appearance relation among object features. In this paper, we propose a novel intra-inter semantic aggregation method (ISA) to learn more effective intra and inter relations for semantically aggregating object features. Specifically, in the proposed ISA, we first introduce an intra semantic aggregation module (Intra-SAM) to enhance the deteriorated spatial features based on the learned intra relation among the features at different positions of an individual object. Then, we present an inter semantic aggregation module (Inter-SAM) to enhance the deteriorated object features in the temporal domain based on the learned inter relation among object features. As a result, by leveraging Intra-SAM and Inter-SAM, the proposed ISA can generate discriminative features from the novel perspective of intra-inter semantic aggregation for robust video object detection. We conduct extensive experiments on the ImageNet VID dataset to evaluate ISA. The proposed ISA obtains 84.5% mAP and 85.2% mAP with ResNet-101 and ResNeXt-101, and it achieves superior performance compared with several state-of-the-art video object detectors.
- Gedas Bertasius, Lorenzo Torresani, and Jianbo Shi. 2018. Object detection in video with spatiotemporal sampling networks. In Proceedings of the European Conference on Computer Vision. 331--346.Google ScholarCross Ref
- Zhaowei Cai and Nuno Vasconcelos. 2018. Cascade R-CNN: Delving into high quality object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 6154--6162.Google ScholarCross Ref
- Wenbin Che, Xiaopeng Fan, Ruiqin Xiong, and Debin Zhao. 2018. Paragraph generation network with visual relationship detection. In Proceedings of the ACM International Conference on Multimedia. 1435--1443.Google ScholarDigital Library
- Jifeng Dai, Yi Li, Kaiming He, and Jian Sun. 2016. R-fcn: Object detection via region-based fully convolutional networks. In Advances in Neural Information Processing Systems. 379--387.Google ScholarDigital Library
- Jifeng Dai, Haozhi Qi, Yuwen Xiong, Yi Li, Guodong Zhang, Han Hu, and Yichen Wei. 2017. Deformable convolutional networks. In Proceedings of the IEEE International Conference on Computer Vision. 764--773.Google ScholarCross Ref
- Hanming Deng, Yang Hua, Tao Song, Zongpu Zhang, Zhengui Xue, Ruhui Ma, Neil Martin Robertson, and Haibing Guan. 2019. Object guided external memory network for video object detection. In Proceedings of the IEEE International Conference on Computer Vision. 6678--6687.Google ScholarCross Ref
- Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, and Fei-Fei Li. 2009. ImageNet: A large-scale hierarchical image database. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 248--255.Google ScholarCross Ref
- Jiajun Deng, Yingwei Pan, Ting Yao, Wengang Zhou, and Houqiang Li. 2019. Relation distillation networks for video object detection. In Proceedings of the IEEE International Conference on Computer Vision. 7023--7032.Google ScholarCross Ref
- Xuanyi Dong, Deyu Meng, Fan Ma, and Yi Yang. 2017. A dual-network progressive approach to weakly supervised object detection. In Proceedings of the ACM International Conference on Multimedia. 279--287.Google ScholarDigital Library
- Christian Eggert, Dan Zecha, Stephan Brehm, and Rainer Lienhart. 2017. Improving small object proposals for company logo detection. In Proceedings of the ACM on International Conference on Multimedia Retrieval. 167--174.Google ScholarDigital Library
- Christoph Feichtenhofer, Axel Pinz, and Andrew Zisserman. 2017. Detect to track and track to detect. In Proceedings of the IEEE International Conference on Computer Vision. 3057--3065.Google ScholarCross Ref
- Zhihang Fu, Zhongming Jin, Guo-Jun Qi, Chen Shen, Rongxin Jiang, Yaowu Chen, and Xian-Sheng Hua. 2018. Previewer for multi-scale object detector. In Proceedings of the ACM International Conference on Multimedia. 265--273.Google ScholarDigital Library
- Chaojun Han, Fumin Shen, Li Liu, Yang Yang, and Heng Tao Shen. 2018. Visual spatial attention network for relationship detection. In Proceedings of the ACM International Conference on Multimedia. 510--518.Google ScholarDigital Library
- Guangxing Han, Xuan Zhang, and Chongrong Li. 2018. Semi-supervised DFF: decoupling detection and feature flow for video object detectors. In Proceedings of the ACM International Conference on Multimedia. 1811--1819.Google ScholarDigital Library
- Wei Han, Pooya Khorrami, Tom Le Paine, Prajit Ramachandran, Mohammad Babaeizadeh, Honghui Shi, Jianan Li, Shuicheng Yan, and Thomas S Huang. 2016. Seq-nms for video object detection. arXiv preprint arXiv:1602.08465 (2016).Google Scholar
- Kaiming He, Georgia Gkioxari, Piotr Dollár, and Ross B. Girshick. 2017. Mask R-CNN. In Proceedings of the IEEE International Conference on Computer Vision. 2980--2988.Google Scholar
- Kaiming He, X. Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 770--778.Google ScholarCross Ref
- Kai Kang, Hongsheng Li, Junjie Yan, Xingyu Zeng, Bin Yang, Tong Xiao, Cong Zhang, Zhe Wang, Ruohui Wang, Xiaogang Wang, and Wanli Ouyang. 2017. T-cnn: Tubelets with convolutional neural networks for object detection from videos. IEEE Transactions on Circuits and Systems for Video Technology (2017), 2896--2907.Google Scholar
- Kai Kang, Wanli Ouyang, Hongsheng Li, and Xiaogang Wang. 2016. Object detection from video tubelets with convolutional neural networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 817--825.Google ScholarCross Ref
- Byungjae Lee, Enkhbayar Erdenee, SongGuo Jin, Mi Young Nam, Young Giu Jung, and Phill Kyu Rhee. 2016. Multi-class multi-object tracking using changing point detection. In Proceedings of the European Conference on Computer Vision Workshops. 68--83.Google ScholarCross Ref
- Tianwei Lin, Xu Zhao, and Zheng Shou. 2017. Single shot temporal action detection. In Proceedings of the ACM International Conference on Multimedia. 988--996.Google ScholarDigital Library
- Mason Liu and Menglong Zhu. 2018. Mobile video object detection with temporally-aware feature maps. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 5686--5695.Google Scholar
- Wei Liu, Dragomir Anguelov, Dumitru Erhan, Christian Szegedy, Scott Reed, Cheng-Yang Fu, and Alexander C Berg. 2016. Ssd: Single shot multibox detector. In Proceedings of the European Conference on Computer Vision. 21--37.Google ScholarCross Ref
- Joseph Redmon, Santosh Divvala, Ross Girshick, and Ali Farhadi. 2016. You only look once: Unified, real-time object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 779--788.Google ScholarCross Ref
- Shaoqing Ren, Kaiming He, Ross B. Girshick, and Jian Sun. 2015. Faster R-CNN: Towards real-time object detection with region proposal Networks. In Advances in Neural Information Processing Systems. 91--99.Google Scholar
- Olga Russakovsky, Jia Deng, Hao Su, Jonathan Krause, Sanjeev Satheesh, Sean Ma, Zhiheng Huang, Andrej Karpathy, Aditya Khosla, Michael S. Bernstein, Alexander C. Berg, and Li Fei-Fei. 2015. ImageNet large scale visual recognition challenge. International Journal of Computer Vision (2015), 211--252.Google ScholarDigital Library
- Mykhailo Shvets, Wei Liu, and Alexander C Berg. 2019. Leveraging long-range temporal relationships between proposals for video object detection. In Proceedings of the IEEE International Conference on Computer Vision. 9756--9764.Google ScholarCross Ref
- Xu Sun, Tongwei Ren, Yuan Zi, and Gangshan Wu. 2019. Video visual relation detection via multi-modal feature fusion. In Proceedings of the ACM International Conference on Multimedia. 2657--2661.Google ScholarDigital Library
- Shiyao Wang, Yucong Zhou, Junjie Yan, and Zhidong Deng. 2018. Fully motion-aware network for video object detection. In Proceedings of the European Conference on Computer Vision. 542--557.Google ScholarCross Ref
- Xiaolong Wang, Ross Girshick, Abhinav Gupta, and Kaiming He. 2018. Non-local neural networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 7794--7803.Google ScholarCross Ref
- Haiping Wu, Yuntao Chen, Naiyan Wang, and Zhaoxiang Zhang. 2019. Sequence level semantics aggregation for video object detection. In Proceedings of the IEEE International Conference on Computer Vision. 9217--9225.Google ScholarCross Ref
- Fanyi Xiao and Yong Jae Lee. 2018. Video object detection with an aligned spatial-temporal memory. In Proceedings of the European Conference on Computer Vision. 494--510.Google ScholarCross Ref
- Saining Xie, Ross B. Girshick, Piotr Dollár, Zhuowen Tu, and Kaiming He. 2017. Aggregated residual transformations for deep neural networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 5987--5995.Google ScholarCross Ref
- Jiahui Yu, Yuning Jiang, Zhangyang Wang, Zhimin Cao, and Thomas Huang. 2016. Unitbox: An advanced object detection network. In Proceedings of the ACM International Conference on Multimedia. 516--520.Google ScholarDigital Library
- Hao Zhou, Chongyang Zhang, and Chuanping Hu. 2019. Visual relationship detection with relative location mining. In Proceedings of the ACM International Conference on Multimedia. 30--38.Google ScholarDigital Library
- Xizhou Zhu, Jifeng Dai, Lu Yuan, and Yichen Wei. 2018. Towards high performance video object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 7210--7218.Google ScholarCross Ref
- Xizhou Zhu, Han Hu, Stephen Lin, and Jifeng Dai. 2019. Deformable convnets v2: more deformable, better results. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 9308--9316.Google ScholarCross Ref
- Xizhou Zhu, Yujie Wang, Jifeng Dai, Lu Yuan, and Yichen Wei. 2017. Flow-guided feature aggregation for video object detection. In Proceedings of the IEEE International Conference on Computer Vision. 408--417.Google ScholarCross Ref
- Xizhou Zhu, Yuwen Xiong, Jifeng Dai, Lu Yuan, and Yichen Wei. 2017. Deep feature flow for video recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2349--2358.Google ScholarCross Ref
Index Terms
- Learning intra-inter semantic aggregation for video object detection
Recommendations
Exploiting Better Feature Aggregation for Video Object Detection
MM '20: Proceedings of the 28th ACM International Conference on MultimediaVideo object detection (VOD) has been a rising topic in recent years due to the challenges such as occlusion, motion blur, etc. To deal with these challenges, feature aggregation from local or global support frames is verified effective. To exploit ...
Temporal-adaptive sparse feature aggregation for video object detection
Highlights- We propose a novel temporal-adaptive sparse feature aggregation framework for challenging video object detection.
AbstractVideo object detection is a challenging task due to the appearance deterioration in video frames. To enhance feature representation of the deteriorated frames, previous methods usually aggregate features from fixed-density and fixed-...
Dual-Memory Feature Aggregation for Video Object Detection
Pattern Recognition and Computer VisionAbstractRecent studies on video object detection have shown the advantages of aggregating features across frames to capture temporal information, which can mitigate appearance degradation, such as occlusion, motion blur, and defocus. However, these ...
Comments