{"type":"ScholarlyArticle","title":"DAMO-StreamNet: Optimizing Streaming Perception in Autonomous Driving","authors":[{"name":"Jun-Yan He","slug":"jun-yan-he","given":"Jun-Yan","family":"He","affiliation":"DAMO Academy , Alibaba Group"},{"name":"Zhi-Qi Cheng","slug":"zhi-qi-cheng","given":"Zhi-Qi","family":"Cheng","affiliation":"Carnegie Mellon University"},{"name":"Chenyang Li","slug":"chenyang-li","given":"Chenyang","family":"Li","affiliation":"DAMO Academy , Alibaba Group"},{"name":"Wangmeng Xiang","slug":"wangmeng-xiang","given":"Wangmeng","family":"Xiang","affiliation":"DAMO Academy , Alibaba Group"},{"name":"Binghui Chen","slug":"binghui-chen","given":"Binghui","family":"Chen","affiliation":"DAMO Academy , Alibaba Group"},{"name":"Bin Luo","slug":"bin-luo","given":"Bin","family":"Luo","affiliation":"DAMO Academy , Alibaba Group"},{"name":"Yifeng Geng","slug":"yifeng-geng","given":"Yifeng","family":"Geng","affiliation":"DAMO Academy , Alibaba Group"},{"name":"Xuansong Xie","slug":"xuansong-xie","given":"Xuansong","family":"Xie","affiliation":"DAMO Academy , Alibaba Group"}],"abstract":"In the realm of autonomous driving, real-time perception or streaming perception remains under-explored. This research introduces DAMO-StreamNet, a novel framework that merges the cutting-edge elements of the YOLO series with a detailed examination of spatial and temporal perception techniques. DAMO-StreamNet's main inventions include: (1) a robust neck structure employing deformable convolution, bolstering receptive field and feature alignment capabilities; (2) a dual-branch structure synthesizing short-path semantic features and long-path temporal features, enhancing the accuracy of motion state prediction; (3) logits-level distillation facilitating efficient optimization, which aligns the logits of teacher and student networks in semantic space; and (4) a real-time prediction mechanism that updates the features of support frames with the current frame, providing smooth streaming perception during inference. Our testing shows that DAMO-StreamNet surpasses current state-of-the-art methodologies, achieving 37.8% (normal size (600, 960)) and 43.3% (large size (1200, 1920)) sAP without requiring additional data. This study not only establishes a new standard for real-time perception but also offers valuable insights for future research. The source code is at https://github.com/zhiqic/DAMO-StreamNet.","doi":"10.24963/ijcai.2023/90","url":"https://ijcai.org/proceedings/2023/90","pdf":"https://ijcai.org/proceedings/2023/0090.pdf","markdown":"https://ijcai.org/proceedings/2023/90.md","bibtex":"https://ijcai.org/proceedings/2023/bibtex/90","volume":{"slug":"2023","title":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2023","url":"https://ijcai.org/proceedings/2023/","year":2023,"location":"Macao, SAR","dates":"19-25 August 2023","editors":"Edith Elkind","isbn":"978-1-956792-03-4","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2023"},"section":"Computer Vision","track":"Main Track","number":90,"pages":{"first":810,"last":818},"keywords":["Computer Vision: CV: Recognition (object detection, categorization)","Computer Vision: CV: 3D computer vision"],"videos":[],"references":[{"position":1,"raw":"Methods sAP sAP50 sAP75 sAPs sAPm sAP l Non-real-time detector-based methods Streamer (S=900) [Li et al., 2020] 18.2 35.3 16.8 4.7 14.4 34.6 Streamer (S=600) [Li et al., 2020] 20.4 35.6 20.8 3.6 18.0 47.2 Streamer + AdaScale [Chin et al., 2019; Ghosh et al., 2021] 13.8 23.4 14.2 0.2 9.0 39.9 Adaptive Streamer [Ghosh et al., 2021] 21.3 37.3 21.1 4.4 18.7","title":"Methods sAP sAP50 sAP75 sAPs sAPm sAP l Non-real-time detector-based methods Streamer (S=900)","authors":"Chin","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":2,"raw":"1 Real-time detector-based methods StreamYOLO-S [Yang et al., 2022a] 28.8 50.3 27.6 9.7 30.7 53.1 StreamYOLO-M [Yang et al., 2022a] 32.9 54.0 32.5 12.4 34.8 58.1 StreamYOLO-L [Yang et al., 2022a] 36.1 57.6 35.6 13.8 37.1 63.3 LongShortNet-S [Li et al., 2022] 29.8 50.4 29.5 11.0 30.6 52.8 LongShortNet-M [Li et al., 2022] 34.1 54.8 34.6 13.3 35.3 58.1 LongShortNet-L [Li et al., 2022] 37.1 57.8 37.7 15.2 37.3 63.8 DAMO-StreamNetNet-S (Ours) 31.8 52.3 31.0 11.4 32.9 58.7 DAMO-StreamNetNet-M (Ours) 35.7 56.7 35.9 14.5 36.3 63.3 DAMO-StreamNetNet-L (Ours) 37.8 59.1 38.6 16.1 39.0 64.6 Large resolution StreamYOLO-L ‡ 41.6 65.2 43.8 23.1 44.7 60.5 LongShortNet-L † 42.7 (+1.1) 65.4 (+0.2) 45.0 (+1.2) 23.9 (+0.8) 44.8 (+0.1) 61.7 (+1.2","title":"1 Real-time detector-based methods StreamYOLO-S","authors":"Yang","year":"2022","venue":"DAMO-StreamNetNet-L","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"DAMO-StreamNet-L † (Ours) 43.3 (+1.7) 66.1 (+0.9) 44.6 (+0.8) 24.2 (+1.1) 47.3 (+2.6) 64.1 (+3.","title":"Ours)","authors":"Damo-Streamnet-L †","year":null,"venue":"Ours)","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Belhassen et al., 2019] Hatem Belhassen, Heng Zhang, Virginie Fresse, and El-Bay Bourennane. Improving video object detec- tion by seq-bbox matching. In Proceedings of the International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISAPP), pages 226-233, 2019.","title":"Improving video object detection by seq-bbox matching","authors":"Hatem Belhassen, Heng Zhang, Virginie Fresse, El-Bay Bourennane","year":"2019","venue":"Proceedings of the International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISAPP)","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Carion et al., 2020] Nicolas Carion, Francisco Massa, Gabriel Synnaeve, Nicolas Usunier, Alexander Kirillov, and Sergey Zagoruyko. End-to-end object detection with transformers. In Andrea Vedaldi, Horst Bischof, Thomas Brox, and Jan- Michael Frahm, editors, European Conference on Computer Vi- sion (ECCV), pages 213-229, 2020.","title":"End-to-end object detection with transformers","authors":"Nicolas Carion, Francisco Massa, Gabriel Synnaeve, Nicolas Usunier, Alexander Kirillov, Sergey Zagoruyko","year":"2020","venue":"European Conference on Computer Vision (ECCV)","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Chen et al., 2017] Guobin Chen, Wongun Choi, Xiang Yu, Tony Han, and Manmohan Chandraker. Learning efficient object de- tection models with knowledge distillation. Advances in neural information processing systems (NeurIPS), 30, 2017.","title":"Learning efficient object detection models with knowledge distillation","authors":"Guobin Chen, Wongun Choi, Xiang Yu, Tony Han, Manmohan Chandraker","year":"2017","venue":"Advances in neural information processing systems","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Chen et al., 2018] Kai Chen, Jiaqi Wang, Shuo Yang, Xingcheng Zhang, Yuanjun Xiong, Chen Change Loy, and Dahua Lin. Op- timizing video object detection via a scale-time lattice. In Pro- ceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 7814-7823, 2018.","title":"Optimizing video object detection via a scale-time lattice","authors":"Kai Chen, Jiaqi Wang, Shuo Yang, Xingcheng Zhang, Yuanjun Xiong, Chen Change Loy, Dahua Lin","year":"2018","venue":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Chen et al., 2021] Defang Chen, Jian-Ping Mei, Yuan Zhang, Can Wang, Zhe Wang, Yan Feng, and Chun Chen. Cross-layer dis- tillation with semantic calibration. In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), pages 7028-7036, 2021.","title":"Cross-layer distillation with semantic calibration","authors":"Defang Chen, Jian-Ping Mei, Yuan Zhang, Can Wang, Zhe Wang, Yan Feng, Chun Chen","year":"2021","venue":"Proceedings of the AAAI Conference on Artificial Intelligence (AAAI)","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Chen et al., 2023] Hanyuan Chen, Jun-Yan He, Wangmeng Xiang, Wei Liu, Zhi-Qi Cheng, Hanbing Liu, Bin Luo, Yifeng Geng, and Xuansong Xie. Hdformer: High-order directed transformer for 3d human pose estimation. arXiv preprint arXiv:2302.01825, 2023.","title":"Hdformer: High-order directed transformer for 3d human pose estimation","authors":"Hanyuan Chen, Jun-Yan He, Wangmeng Xiang, Wei Liu, Zhi-Qi Cheng, Hanbing Liu, Bin Luo, Yifeng Geng, Xuansong Xie","year":"2023","venue":null,"doi":null,"url":null,"internal_url":"/proceedings/2023/65"},{"position":10,"raw":"[Cheng et al., 2017a] Zhi-Qi Cheng, Xiao Wu, Yang Liu, and Xian- Sheng Hua. Video2shop: Exact matching clothes in videos to online shopping images. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 4048-4056, 2017.","title":"Video2shop: Exact matching clothes in videos to online shopping images","authors":"Cheng","year":"2017","venue":"Proceedings of the IEEE conference on computer vision and pattern recognition","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Cheng et al., 2017b] Zhi-Qi Cheng, Hao Zhang, Xiao Wu, and Chong-Wah Ngo. On the selection of anchors and targets for video hyperlinking. In Proceedings of the 2017 acm on inter- national conference on multimedia retrieval (ICMR), pages 287- 293, 2017.","title":"On the selection of anchors and targets for video hyperlinking","authors":"Cheng","year":"2017","venue":"Proceedings of the 2017 acm on international conference on multimedia retrieval (ICMR)","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Cheng et al., 2018] Zhi-Qi Cheng, Xiao Wu, Siyu Huang, Jun-Xiu Li, Alexander G Hauptmann, and Qiang Peng. Learning to trans- fer: Generalizable attribute learning with multitask neural model search. In Proceedings of the ACM international conference on Multimedia (ACM MM), pages 90-98, 2018.","title":"Learning to transfer: Generalizable attribute learning with multitask neural model search","authors":"Zhi-Qi Cheng, Xiao Wu, Siyu Huang, Jun-Xiu Li, Alexander G Hauptmann, Qiang Peng","year":"2018","venue":"Proceedings of the ACM international conference on Multimedia (ACM MM)","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Cheng et al., 2019a] Zhi-Qi Cheng, Jun-Xiu Li, Qi Dai, Xiao Wu, and Alexander G Hauptmann. Learning spatial awareness to im- prove crowd counting. In Proceedings of the IEEE/CVF interna- tional conference on computer vision (ICCV), pages 6152-6161, 2019.","title":"Learning spatial awareness to improve crowd counting","authors":"Cheng","year":"2019","venue":"Proceedings of the IEEE/CVF international conference on computer vision (ICCV)","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Cheng et al., 2019b] Zhi-Qi Cheng, Jun-Xiu Li, Qi Dai, Xiao Wu, Jun-Yan He, and Alexander G Hauptmann. Improving the learn- ing of multi-column convolutional neural network for crowd counting. In Proceedings of the ACM international conference on multimedia (ACM MM), pages 1897-1906, 2019.","title":"Improving the learning of multi-column convolutional neural network for crowd counting","authors":"Cheng","year":"2019","venue":"Proceedings of the ACM international conference on multimedia (ACM MM)","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Cheng et al., 2022] Zhi-Qi Cheng, Qi Dai, Siyao Li, Teruko Mi- tamura, and Alexander Hauptmann. Gsrformer: Grounded sit- uation recognition transformer with alternate semantic attention refinement. In Proceedings of the 30th ACM International Con- ference on Multimedia (ACM MM), pages 3272-3281, 2022.","title":"Gsrformer: Grounded situation recognition transformer with alternate semantic attention refinement","authors":"Zhi-Qi Cheng, Qi Dai, Siyao Li, Teruko Mitamura, Alexander Hauptmann","year":"2022","venue":"Proceedings of the 30th ACM International Conference on Multimedia (ACM MM)","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Chin et al., 2019] Ting-Wu Chin, Ruizhou Ding, and Diana Mar- culescu. Adascale: Towards real-time video object detection us- ing adaptive scaling. In Proceedings of Machine Learning and Systems (MLSys), 2019.","title":"Adascale: Towards real-time video object detection using adaptive scaling","authors":"Ting-Wu Chin, Ruizhou Ding, Diana Marculescu","year":"2019","venue":"Proceedings of Machine Learning and Systems (MLSys)","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Ding et al., 2019] Xiaohan Ding, Yuchen Guo, Guiguang Ding, and Jungong Han. Acnet: Strengthening the kernel skeletons for powerful CNN via asymmetric convolution blocks. In Inter- national Conference on Computer Vision (ICCV), pages 1911- 1920, 2019.","title":"Acnet: Strengthening the kernel skeletons for powerful CNN via asymmetric convolution blocks","authors":"Xiaohan Ding, Yuchen Guo, Guiguang Ding, Jungong Han","year":"2019","venue":"International Conference on Computer Vision (ICCV)","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Ding et al., 2021a] Xiaohan Ding, Xiangyu Zhang, Jungong Han, and Guiguang Ding. Diverse branch block: Building a convolu- tion as an inception-like unit. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 10886-10895, 2021.","title":"Diverse branch block: Building a convolution as an inception-like unit","authors":"Ding","year":"2021","venue":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Ding et al., 2021b] Xiaohan Ding, Xiangyu Zhang, Ningning Ma, Jungong Han, Guiguang Ding, and Jian Sun. Repvgg: Making vgg-style convnets great again. In Proceedings of IEEE Confer- ence on Computer Vision and Pattern Recognition (CVPR), pages 13733-13742, 2021.","title":"Repvgg: Making vgg-style convnets great again","authors":"Ding","year":"2021","venue":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Gao et al., 2021] Kaifeng Gao, Long Chen, Yifeng Huang, and Jun Xiao. Video relation detection via tracklet based visual trans- former. In Proceedings of ACM Conference on Multimedia (ACM MM), pages 4833-4837. ACM, 2021.","title":"Video relation detection via tracklet based visual transformer","authors":"Gao","year":"2021","venue":"Proceedings of ACM Conference on Multimedia (ACM MM)","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Ge et al., 2021a] Zheng Ge, Songtao Liu, Zeming Li, Osamu Yoshie, and Jian Sun. OTA: optimal transport assignment for object detection. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 303-312, 2021.","title":"OTA: optimal transport assignment for object detection","authors":"Ge","year":"2021","venue":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Ge et al., 2021b] Zheng Ge, Songtao Liu, Feng Wang, Zeming Li, and Jian Sun. YOLOX: exceeding YOLO series in 2021. CoRR, abs/2107.08430, 2021.","title":"YOLOX: exceeding YOLO series in 2021","authors":"Ge","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Ghiasi et al., 2019] Golnaz Ghiasi, Tsung-Yi Lin, and Quoc V. Le. NAS-FPN: learning scalable feature pyramid architecture for ob- ject detection. In IEEE Conference on Computer Vision and Pat- tern Recognition (CVPR), pages 7036-7045, 2019.","title":"NAS-FPN: learning scalable feature pyramid architecture for object detection","authors":"Golnaz Ghiasi, Tsung-Yi Lin, V Quoc, Le","year":"2019","venue":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Ghosh et al., 2021] A. Ghosh, A. Nambi, A. Singh, and et al. Adaptive streaming perception using deep reinforcement learn- ing. CoRR, abs/2106.05665, 2021.","title":"Adaptive streaming perception using deep reinforcement learning","authors":"A Ghosh, A Nambi, A Singh","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Han et al., 2016] Wei Han, Pooya Khorrami, Tom Le Paine, Prajit Ramachandran, Mohammad Babaeizadeh, Honghui Shi, Jianan Li, Shuicheng Yan, and Thomas S. Huang. Seq-nms for video object detection. CoRR, abs/1602.08465, 2016.","title":"Seq-nms for video object detection","authors":"Wei Han, Pooya Khorrami, Tom Le Paine, Prajit Ramachandran, Mohammad Babaeizadeh, Honghui Shi, Jianan Li, Shuicheng Yan, Thomas S Huang","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[He et al., 2021] Jun-Yan He, Xiao Wu, Zhi-Qi Cheng, Zhaoquan Yuan, and Yu-Gang Jiang. Db-lstm: Densely-connected bi- directional lstm for human action recognition. Neurocomputing, 444:319-331, 2021.","title":"Db-lstm: Densely-connected bidirectional lstm for human action recognition","authors":"Jun-Yan He, Xiao Wu, Zhi-Qi Cheng, Zhaoquan Yuan, Yu-Gang Jiang","year":"2021","venue":"Neurocomputing","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Heo et al., 2019] Byeongho Heo, Minsik Lee, Sangdoo Yun, and Jin Young Choi. Knowledge transfer via distillation of activa- tion boundaries formed by hidden neurons. In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), pages 3779- 3787, 2019.","title":"Knowledge transfer via distillation of activation boundaries formed by hidden neurons","authors":"Heo","year":"2019","venue":"Proceedings of the AAAI Conference on Artificial Intelligence (AAAI)","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Hinton et al., 2015] Geoffrey Hinton, Oriol Vinyals, Jeff Dean, et al. Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531, 2(7), 2015.","title":"Distilling the knowledge in a neural network","authors":"Geoffrey Hinton, Oriol Vinyals, Jeff Dean","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Huang et al., 2018] Siyu Huang, Xi Li, Zhi-Qi Cheng, Zhongfei Zhang, and Alexander Hauptmann. Gnas: A greedy neural archi- tecture search method for multi-attribute learning. In Proceed- ings of the 26th ACM international conference on Multimedia (ACM MM), pages 2049-2057, 2018.","title":"Gnas: A greedy neural architecture search method for multi-attribute learning","authors":"Siyu Huang, Xi Li, Zhi-Qi Cheng, Zhongfei Zhang, Alexander Hauptmann","year":"2018","venue":"Proceedings of the 26th ACM international conference on Multimedia (ACM MM)","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Huang et al., 2022] Ziyuan Huang, Shiwei Zhang, Liang Pan, Zhiwu Qing, Mingqian Tang, Ziwei Liu, and Marcelo H. Ang Jr. Tada! temporally-adaptive convolutions for video understanding. In Proceedings of International Conference on Learning Repre- sentations, (ICLR), 2022.","title":"Tada! temporally-adaptive convolutions for video understanding","authors":"Ziyuan Huang, Shiwei Zhang, Liang Pan, Zhiwu Qing, Mingqian Tang, Ziwei Liu, Marcelo H Ang","year":"2022","venue":"Proceedings of International Conference on Learning Representations","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Jiang et al., 2022] Yiqi Jiang, Zhiyu Tan, Junyan Wang, Xiuyu Sun, Ming Lin, and Hao Li. Giraffedet: A heavy-neck paradigm for object detection. In International Conference on Learning Representations (ICLR), 2022.","title":"Giraffedet: A heavy-neck paradigm for object detection","authors":"Yiqi Jiang, Zhiyu Tan, Junyan Wang, Xiuyu Sun, Ming Lin, Hao Li","year":"2022","venue":"International Conference on Learning Representations (ICLR)","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Kang et al., 2016] Kai Kang, Wanli Ouyang, Hongsheng Li, and Xiaogang Wang. Object detection from video tubelets with con- volutional neural networks. In Proceedings of IEEE Confer- ence on Computer Vision and Pattern Recognition (CVPR), pages 817-825, 2016.","title":"Object detection from video tubelets with convolutional neural networks","authors":"Kai Kang, Wanli Ouyang, Hongsheng Li, Xiaogang Wang","year":"2016","venue":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Kim and Lee, 2020] Kang Kim and Hee Seok Lee. Probabilis- tic anchor assignment with iou prediction for object detection. In Andrea Vedaldi, Horst Bischof, Thomas Brox, and Jan- Michael Frahm, editors, European Conference on Computer Vi- sion(ECCV), volume 12370, pages 355-371, 2020.","title":"Probabilistic anchor assignment with iou prediction for object detection","authors":"Kang Kim, Hee Seok, Lee","year":"2020","venue":"European Conference on Computer Vision(ECCV)","doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Lan et al., 2022] Jin-Peng Lan, Zhi-Qi Cheng, Jun-Yan He, Chenyang Li, Bin Luo, Xu Bao, Wangmeng Xiang, Yifeng Geng, and Xuansong Xie. Procontext: Exploring progressive context transformer for tracking. arXiv preprint arXiv:2210.15511, 2022.","title":"Procontext: Exploring progressive context transformer for tracking","authors":"Jin-Peng Lan, Zhi-Qi Cheng, Jun-Yan He, Chenyang Li, Bin Luo, Xu Bao, Wangmeng Xiang, Yifeng Geng, Xuansong Xie","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":35,"raw":"[Li et al., 2020] Mengtian Li, Yu-Xiong Wang, and Deva Ramanan. Towards streaming perception. In Proceedings of the European Conference on Computer Vision (ECCV), volume 12347, pages 473-488, 2020.","title":"Towards streaming perception","authors":"Mengtian Li, Yu-Xiong Wang, Deva Ramanan","year":"2020","venue":"Proceedings of the European Conference on Computer Vision (ECCV)","doi":null,"url":null,"internal_url":null},{"position":36,"raw":"[Li et al., 2022] Chenyang Li, Zhi-Qi Cheng, Jun-Yan He, Pengyu Li, Bin Luo, Han-Yuan Chen, Yifeng Geng, Jin-Peng Lan, and Xuansong Xie. Longshortnet: Exploring temporal and se- mantic features fusion in streaming perception. arXiv preprint arXiv:2210.15518, 2022.","title":"Longshortnet: Exploring temporal and semantic features fusion in streaming perception","authors":"Chenyang Li, Zhi-Qi Cheng, Jun-Yan He, Pengyu Li, Bin Luo, Han-Yuan Chen, Yifeng Geng, Jin-Peng Lan, Xuansong Xie","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":37,"raw":"[Lin et al., 2014] T. Lin, M. Maire, S. Belongie, and et al. Microsoft COCO: common objects in context. In European Conference on Computer Vision (ECCV), volume 8693, pages 740-755, 2014.","title":"Microsoft COCO: common objects in context","authors":"T Lin, M Maire, S Belongie","year":"2014","venue":"European Conference on Computer Vision (ECCV)","doi":null,"url":null,"internal_url":null},{"position":38,"raw":"[Lin et al., 2017] Tsung-Yi Lin, Piotr Dollár, Ross B. Girshick, Kaiming He, Bharath Hariharan, and Serge J. Belongie. Feature pyramid networks for object detection. In 2017 IEEE Confer- ence on Computer Vision and Pattern Recognition (CVPR), pages 936-944. IEEE Computer Society, 2017.","title":"Feature pyramid networks for object detection","authors":"Tsung-Yi Lin, Piotr Dollár, Ross B Girshick, Kaiming He, Bharath Hariharan, Serge J Belongie","year":"2017","venue":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","doi":null,"url":null,"internal_url":null},{"position":39,"raw":"[Lin et al., 2020] Lijian Lin, Haosheng Chen, Honglun Zhang, Jun Liang, Yu Li, Ying Shan, and Hanzi Wang. Dual semantic fu- sion network for video object detection. In ACM International Conference on Multimedia (ACM MM), pages 1855-1863, 2020.","title":"Dual semantic fusion network for video object detection","authors":"Lijian Lin, Haosheng Chen, Honglun Zhang, Jun Liang, Yu Li, Ying Shan, Hanzi Wang","year":"2020","venue":"ACM International Conference on Multimedia (ACM MM)","doi":null,"url":null,"internal_url":null},{"position":40,"raw":"[Liu et al., 2018] Shu Liu, Lu Qi, Haifang Qin, Jianping Shi, and Jiaya Jia. Path aggregation network for instance segmentation. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 8759-8768. Computer Vision Foundation / IEEE Computer Society, 2018.","title":"Path aggregation network for instance segmentation","authors":"Shu Liu, Lu Qi, Haifang Qin, Jianping Shi, Jiaya Jia","year":"2018","venue":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","doi":null,"url":null,"internal_url":null},{"position":41,"raw":"[Liu et al., 2020] Yifan Liu, Changyong Shu, Jingdong Wang, and Chunhua Shen. Structured knowledge distillation for dense pre- diction. IEEE transactions on pattern analysis and machine in- telligence (TPAMI), 2020.","title":"Structured knowledge distillation for dense prediction","authors":"Yifan Liu, Changyong Shu, Jingdong Wang, Chunhua Shen","year":"2020","venue":"IEEE transactions on pattern analysis and machine intelligence","doi":null,"url":null,"internal_url":null},{"position":42,"raw":"[Mirzadeh et al., 2020] Seyed Iman Mirzadeh, Mehrdad Fara- jtabar, Ang Li, Nir Levine, Akihiro Matsukawa, and Hassan Ghasemzadeh. Improved knowledge distillation via teacher as- sistant. In Proceedings of the AAAI conference on artificial intel- ligence (AAAI), pages 5191-5198, 2020.","title":"Improved knowledge distillation via teacher assistant","authors":"Mehrdad Seyed Iman Mirzadeh, Ang Farajtabar, Nir Li, Akihiro Levine, Hassan Matsukawa, Ghasemzadeh","year":"2020","venue":"Proceedings of the AAAI conference on artificial intelligence (AAAI)","doi":null,"url":null,"internal_url":null},{"position":43,"raw":"[Rezatofighi et al., 2019] Hamid Rezatofighi, Nathan Tsoi, JunY- oung Gwak, Amir Sadeghian, Ian D. Reid, and Silvio Savarese. Generalized intersection over union: A metric and a loss for bounding box regression. In IEEE Conference on Computer Vi- sion and Pattern Recognition (CVPR), pages 658-666, 2019.","title":"Generalized intersection over union: A metric and a loss for bounding box regression","authors":"Hamid Rezatofighi, Nathan Tsoi, Junyoung Gwak, Amir Sadeghian, Ian D Reid, Silvio Savarese","year":"2019","venue":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","doi":null,"url":null,"internal_url":null},{"position":44,"raw":"[Sun et al., 2021] Guanxiong Sun, Yang Hua, Guosheng Hu, and Neil Robertson. MAMBA: multi-level aggregation via memory bank for video object detection. In Proceedings of AAAI Confer- ence on Artificial Intelligence, (AAAI), pages 2620-2627, 2021.","title":"MAMBA: multi-level aggregation via memory bank for video object detection","authors":"Guanxiong Sun, Yang Hua, Guosheng Hu, Neil Robertson","year":"2021","venue":"Proceedings of AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":45,"raw":"[Tan et al., 2020] Mingxing Tan, Ruoming Pang, and Quoc V. Le. Efficientdet: Scalable and efficient object detection. In 2020 IEEE/CVF Conference on Computer Vision and Pattern Recog- nition (CVPR), pages 10778-10787, 2020.","title":"Efficientdet: Scalable and efficient object detection","authors":"Mingxing Tan, Ruoming Pang, V Quoc, Le","year":"2020","venue":"IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","doi":null,"url":null,"internal_url":null},{"position":46,"raw":"[Tu et al., 2023] Shuyuan Tu, Qi Dai, Zuxuan Wu, Zhi-Qi Cheng, Han Hu, and Yu-Gang Jiang. Implicit temporal modeling with learnable alignment for video recognition. arXiv preprint arXiv:2304.10465, 2023.","title":"Implicit temporal modeling with learnable alignment for video recognition","authors":"Shuyuan Tu, Qi Dai, Zuxuan Wu, Zhi-Qi Cheng, Han Hu, Yu-Gang Jiang","year":"2023","venue":null,"doi":null,"url":null,"internal_url":null},{"position":47,"raw":"[Vasu et al., 2022] Pavan Kumar Anasosalu Vasu, James Gabriel, Jeff Zhu, Oncel Tuzel, and Anurag Ranjan. An improved one millisecond mobile backbone. CoRR, abs/2206.04040, 2022.","title":"An improved one millisecond mobile backbone","authors":"Pavan Kumar, Anasosalu Vasu, James Gabriel, Jeff Zhu, Oncel Tuzel, Anurag Ranjan","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":48,"raw":"[Wang et al., 2018] Shiyao Wang, Yucong Zhou, Junjie Yan, and Zhidong Deng. Fully motion-aware network for video object de- tection. In Vittorio Ferrari, Martial Hebert, Cristian Sminchis- escu, and Yair Weiss, editors, Proceedings of European Confer- ence on Computer Vision (ECCV), volume 11217, pages 557- 573, 2018.","title":"Fully motion-aware network for video object detection","authors":"Shiyao Wang, Yucong Zhou, Junjie Yan, Zhidong Deng","year":"2018","venue":"Proceedings of European Conference on Computer Vision (ECCV)","doi":null,"url":null,"internal_url":null},{"position":49,"raw":"[Wang et al., 2021] Jingdong Wang, Ke Sun, Tianheng Cheng, Borui Jiang, Chaorui Deng, Yang Zhao, Dong Liu, Yadong Mu, Mingkui Tan, Xinggang Wang, Wenyu Liu, and Bin Xiao. Deep high-resolution representation learning for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI), 43(10):3349- 3364, 2021.","title":"Deep high-resolution representation learning for visual recognition","authors":"Jingdong Wang, Ke Sun, Tianheng Cheng, Borui Jiang, Chaorui Deng, Yang Zhao, Dong Liu, Yadong Mu, Mingkui Tan, Xinggang Wang, Wenyu Liu, Bin Xiao","year":"2021","venue":"IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI)","doi":null,"url":null,"internal_url":null},{"position":50,"raw":"[Wang et al., 2022] Chien-Yao Wang, Alexey Bochkovskiy, and Hong-Yuan Mark Liao. Yolov7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. CoRR, abs/2207.02696, 2022.","title":"Yolov7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors","authors":"Chien-Yao Wang, Alexey Bochkovskiy, Hong-Yuan Mark Liao","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":51,"raw":"[Yang et al., 2022a] Jinrong Yang, Songtao Liu, Zeming Li, Xiaop- ing Li, and Jian Sun. Real-time object detection for streaming perception. In Proceedings of the Conference on Computer Vi- sion and Pattern Recognition (CVPR), pages 5385-5395, 2022.","title":"Real-time object detection for streaming perception","authors":"Yang","year":"2022","venue":"Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR)","doi":null,"url":null,"internal_url":null},{"position":52,"raw":"[Yang et al., 2022b] Zhendong Yang, Zhe Li, Xiaohu Jiang, Yuan Gong, Zehuan Yuan, Danpei Zhao, and Chun Yuan. Focal and global knowledge distillation for detectors. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recog- nition (CVPR), pages 4643-4652, 2022.","title":"Focal and global knowledge distillation for detectors","authors":"Yang","year":"2022","venue":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","doi":null,"url":null,"internal_url":null},{"position":53,"raw":"[Yao et al., 2021] Lewei Yao, Renjie Pi, Hang Xu, Wei Zhang, Zhenguo Li, and Tong Zhang. G-detkd: Towards general distilla- tion framework for object detectors via contrastive and semantic- guided feature imitation. In Proceedings of the IEEE/CVF Inter- national Conference on Computer Vision (ICCV), pages 3591- 3600, 2021.","title":"G-detkd: Towards general distillation framework for object detectors via contrastive and semanticguided feature imitation","authors":"Lewei Yao, Renjie Pi, Hang Xu, Wei Zhang, Zhenguo Li, Tong Zhang","year":"2021","venue":"Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)","doi":null,"url":null,"internal_url":null},{"position":54,"raw":"[Zhou et al., 2022] Yuxuan Zhou, Chao Li, Zhi-Qi Cheng, Yifeng Geng, Xuansong Xie, and Margret Keuper. Hypergraph trans- former for skeleton-based action recognition. arXiv preprint arXiv:2211.09590, 2022.","title":"Hypergraph transformer for skeleton-based action recognition","authors":"Yuxuan Zhou, Chao Li, Zhi-Qi Cheng, Yifeng Geng, Xuansong Xie, Margret Keuper","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null},{"position":55,"raw":"[Zhu et al., 2017a] Xizhou Zhu, Yujie Wang, Jifeng Dai, Lu Yuan, and Yichen Wei. Flow-guided feature aggregation for video ob- ject detection. In Proceedings of IEEE Conference on Computer Vision (ICCV), pages 408-417, 2017.","title":"Flow-guided feature aggregation for video object detection","authors":"Zhu","year":"2017","venue":"Proceedings of IEEE Conference on Computer Vision (ICCV)","doi":null,"url":null,"internal_url":null},{"position":56,"raw":"[Zhu et al., 2017b] Xizhou Zhu, Yuwen Xiong, Jifeng Dai, Lu Yuan, and Yichen Wei. Deep feature flow for video recog- nition. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 4141-4150, 2017.","title":"Deep feature flow for video recognition","authors":"Zhu","year":"2017","venue":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}