-
摘要: 對深度學習在行人重識別領域的應用現狀進行總結與評價。首先，對行人重識別進行介紹，包括行人重識別的應用場景、數據集與評價指標，并對基于深度學習的行人重識別的基本方法進行總結。之后，針對行人重識別的研究現狀，將近年來國內外學者的研究工作歸納為基于局部特征、基于生成對抗網絡、基于視頻以及基于重排序4個方向，并對每個方向所使用的方法分別進行梳理、性能對比以及總結。最后，對行人重識別領域現存的問題進行了分析與討論，并探討了行人重識別未來的發展方向。Abstract: Person re-identification is an important part of multi-target tracking across cameras; its aim is to identify the same person across different cameras. Given a query image, the purpose of person re-identification is to find the best match for the query image in an image set. Person re-identification is a key component in an intelligent security system; it is beneficial for building a smart bank or smart factory and plays a crucial role in the construction of a smart city. Nowadays, with the development of artificial intelligence and increasing demand for precise identification in practical scenarios, deep learning-based person re-identification technology has become a popular research topic; this technology has achieved state-of-the-art results in comparison with conventional approaches. Although there are many recently proposed networks with stronger representation ability and a high level of accuracy for person re-identification, there also exist some problems that should be considered and solved. These include the insufficient generalization ability of various poses, the inability to fully utilize the temporal information, and the ineffective identification of occluded objects. As a result, many scholars have researched this field and have pointed out some promising solutions to cope with the aforementioned problems. This paper aims to summarize the application of deep learning in the field of person re-identification along with its advantages and shortcomings. First, the background of person re-identification is introduced, including the application scenarios, datasets, and evaluation indicators. Additionally, some basic methods of person re-identification based on deep learning are summarized. According to the existing research on person re-identification, the main approaches proposed by scholars worldwide can be summarized into four aspects, which are based on local features, generative adversarial networks, video data, and re-ranking. A detailed comparative study of these four methods is then conducted. Finally, the existing problems and future studies that can be done in the field of person re-identification are analyzed and discussed.
-
Key words:
- deep learning /
- person re-identification /
- local feature /
- generating adversarial networks /
- video data /
- reranking
-
圖 1 行人重識別的應用場景示例
Figure 1. An example of person re-identification application scenarios
圖 2 基于深度學習的行人重識別研究問題與方法歸納
Figure 2. Research problems and methods of person re-identification based on deep learning
圖 3 行人重識別研究方法框架
Figure 3. Research method framework of person re-identification methods
表 3 各數據集的性能最優模型以及精度數據
Table 3. State-of-the-art
models and their precision for each dataset Dataset SOTA Rank-1 accuracy mAP Market-1501[4] St-ReID(RE, RK)[20] 97.20 86.70 Viewpoint-Aware Loss[21] 96.79 95.43 DG-Net[22] 94.80 84.00 DukeMTMC-reID[5] St-ReID(RE, RK, Cam)[20] 94.50 92.70 ABD-Net(ResNet-50)[23] 89.00 78.95 Viewpoint-Aware Loss[21] 93.90 91.80 CUHK03[3,6] FD-GAN[19] 92.60 91.30 OSNet[24] 67.80 — DG-Net[22] 61.10 — MSMT17[9] ABD-Net(ResNet-50)[23] 82.30 60.80 OSNet[24] 78.70 52.90 DG-Net[22] 77.20 52.30 
下載: 導出CSV
表 4 基于局部特征的行人重識別方法的性能表現
Table 4. Performance of person re-identification method based on local feature
Methods Year Market-1501 DukeMTMC-reID CUHK03 Rank-1 mAP Rank-1 mAP Rank-1 mAP PCB+RPP[46] 2018 93.8 81.6 83.3 69.2 63.7 57.5 SPReID+re-ranking[48] 2018 94.6 90.9 88.9 84.9 — — RNLSTMA[54] 2019 90.3 76.4 77.0 62.1 86.1 83.6 mGD+ RNLSTMA[56] 2020 91.3 77.9 80.8 63.9 88.0 84.2 SMC-ReID[49] 2020 95.3 93.0 — — — — HOReID[53] 2020 94.2 84.9 86.9 75.6 — — ISP[50] 2020 95.3 88.6 89.6 80.0 — —
下載: 導出CSV
表 5 基于生成對抗網絡的行人重識別方法的性能表現
Table 5. Performance of person re-identification method based on GAN
下載: 導出CSV
中文字幕在线观看表 6 基于視頻的的行人重識別方法的性能表現
Table 6. Performance of video-based person re-identification method
Methods Year Rank-1 MARS DukeMTMC VideoReID[15] PRID2011[7] iLIDS-VID[8] Rank-1 mAP Rank-1 mAP CNN+RNN+Temporal Pooling[77] 2016 70.0 58.0 — — Deep RCN[78]+KISSME 2016 69.0 46.1 RFA-Net[80] 2016 58.2 49.3 SCAN+ResNet50[81] 2018 92.0 81.3 86.6 76.7 ResNet3D-50+Non-Local[82] 2018 91.2 81.3 84.3 77.0 Spatial Attention+Temporal Attention[83] 2018 93.2 80.2 82.3 65.8 AP3D[84] 2020 — 86.7 90.1 85.1 96.3 95.6 STCNet[86] 2020 — 83.4 88.5 82.3 95.0 93.5 MGH[88] 2020 94.8 85.6 90.0 85.8
下載: 導出CSV
-
參考文獻
[1] Ye M, Shen J B, Lin G J, et al. Deep learning for person re-identification: a survey and outlook [J/OL]. Arxiv Perprint (2020-01-13) [2020-12-22]. https://arxiv.org/abs/2001.04193 [2] Karanam S, Gou M R, Wu Z Y, et al. A systematic evaluation and benchmark for person re-identification: Features, metrics, and datasets. IEEE Trans Pattern Anal Mach Intell, 2019, 41(3): 523 doi: 10.1109/TPAMI.2018.2807450 [3] Li W, Zhao R, Xiao T, et al. DeepReID: Deep filter pairing neural network for person re-identification // Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Columbus, 2014: 152 [4] Zheng L, Shen L, Tian L, et al. Scalable person re-identification: a Benchmark // 2015 IEEE International Conference on Computer Vision. Santiago, 2015: 1116 [5] Zheng Z D, Zheng L, Yang Y. Unlabeled samples generated by GAN improve the person re-identification baseline in vitro // 2017 IEEE International Conference on Computer Vision (ICCV). Venice, 2017: 3774 [6] Zhong Z, Zheng L, Cao D L, et al. Re-ranking person re-identification with k-reciprocal encoding // 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu, 2017: 3652 [7] Hirzer M, Beleznai C, Roth P M, et al. Person re-identification by descriptive and discriminative classification // Scandinavian Conference on Image Analysis. Ystad Sal, 2011: 91 [8] Wang T Q, Gong S G, Zhu X T, et al. Person re-identification by discriminative selection in video ranking. IEEE Trans Pattern Anal Mach Intell, 2016, 38(12): 2501 doi: 10.1109/TPAMI.2016.2522418 [9] Wei L H, Zhang S L, Gao W, et al. Person transfer GAN to bridge domain gap for person re-identification // 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, 2018: 79 [10] Song G L, Leng B, Liu Y, et al. Region-based quality estimation network for large-scale person re-identification [J/OL]. Arxiv Perprint (2017-11-23) [2020-12-22]. https://arxiv.org/abs/1711.08766 [11] Yu S J, Li S H, Chen D P, et al. COCAS: A large-scale clothes changing person dataset for Re-identification // 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Seattle, 2020: 3397 [12] Wang G R, Wang G C, Zhang X J, et al. Weakly supervised person Re-ID: Differentiable graphical learning and a new benchmark [J/OL]. arXiv preprint arXiv (2019-04-08) [2020-12-22]. https://arxiv.org/abs/1904.03845 [13] Wang Y N, Liao S C, Shao L. Surpassing real-world source training data: Random 3D characters for generalizable person re-identification // Proceedings of the 28th ACM International Conference on Multimedia. Seattle, 2020: 3422 [14] Xu B Q, He L X, Liao X Y, et al. Black Re-ID: A Head-shoulder descriptor for the challenging problem of person re-identification // Proceedings of the 28th ACM International Conference on Multimedia. Seattle, 2020: 673 [15] Wu Y, Lin Y T, Dong X Y, et al. Exploit the unknown gradually: One-shot video-based person re-identification by stepwise learning // 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, 2018: 5177 [16] Zheng L, Bie Z, Sun Y, et al. Mars: A video benchmark for large-scale person re-identification // Proceedings of the European Conference on Computer Vision. Amsterdam, 2016: 868 [17] Basaran E, Tesfaye Y T, Shah M. EgoReID Dataset: Person re-identification in videos acquired by mobile devices with first-person point-of-view [J/OL]. arXiv preprint arXiv (2018-12-22) [2020-12-22].https://arxiv.org/abs/1812.09570 [18] Li J, Wang J, Tian Q, et al. Global-local temporal representations for video person re-identification // Proceedings of the IEEE International Conference on Computer Vision. Seoul, 2019: 3958 [19] Ge Y X, Li Z W, Zhao H Y, et al. FD-GAN: Pose-guided feature distilling GAN for robust person re-identification. [J/OL]. arXiv preprint arXiv (2018-10-06) [2021-5-5]. https://arxiv.org/abs/1810.02936 [20] Wang G C, Lai J H, Huang P G, et al. Spatial-temporal person re-identification // Proceedings of the AAAI conference on artificial intelligence. Hawaii, 2019, 33(1): 8933 [21] Zhu Z H, Jiang X Y, Zheng F, et al. Viewpoint-aware loss with angular regularization for person re-identification [J/OL]. arXiv preprint arXiv (2019-12-03) [2020-12-22]. https://arxiv.org/abs/1912.01300v1 [22] Zheng Z D, Yang X D, Yu Z D, et al. Joint discriminative and generative learning for person Re-identification // 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Long Beach, 2019: 2133 [23] Chen T L, Ding S J, Xie J Y, et al. ABD-net: Attentive but diverse person Re-identification // 2019 IEEE/CVF International Conference on Computer Vision (ICCV). Seoul, 2019: 8350 [24] Zhou K Y, Yang Y X, Cavallaro A, et al. Omni-scale feature learning for person re-identification // 2019 IEEE/CVF International Conference on Computer Vision (ICCV). Seoul, 2019: 3701 [25] Szegedy C, Liu W, Jia Y Q, et al. Going deeper with convolutions // 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Boston, 2015: 1 [26] He K M, Zhang X Y, Ren S Q, et al. Deep residual learning for image recognition // 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, 2016: 770 [27] Huang G, Liu Z, Der Maaten L V, et al. Densely connected convolutional networks // 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu, 2017: 2261 [28] Filkovi? I, Kalafati? Z, Hrka? T. Deep metric learning for person re-identification and de-identification // 2016 39th International Convention on Information and Communication Technology, Electronics and Microelectronics. Opatija, 2016: 1360 [29] Yi D, Lei Z, Liao S C, et al. Deep metric learning for person Re-identification // 2014 22nd International Conference on Pattern Recognition. Stockholm, 2014: 34 [30] Ahmed E, Jones M, Marks T K. An improved deep learning architecture for person re-identification // 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Boston, 2015: 3908 [31] Wu L, Shen C H, Hengel A V D. PersonNet: Person re-identification with deep convolutional neural networks [J/OL]. Arxiv Perprint (2016-01-27) [2020-12-22]. https://arxiv.org/abs/1601.07255 [32] Wang Y C, Chen Z Z, Wu F, et al. Person re-identification with cascaded pairwise convolutions // 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, 2018: 1470 [33] Wang F Q, Zuo W M, Lin L, et al. Joint learning of single-image and cross-image representations for person re-identification // 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, 2016: 1288 [34] Xiong W, Xiong Z J, Yang D C, et al. Pedestrian re-identification based on deep feature fusion. Comput Eng Sci, 2020, 42(2): 358 doi: 10.3969/j.issn.1007-130X.2020.02.022熊煒, 熊子婕, 楊荻椿, 等. 基于深層特征融合的行人重識別方法. 計算機工程與科學, 2020, 42(2):358 doi: 10.3969/j.issn.1007-130X.2020.02.022 [35] Xiong W, Yang D C, Xiong Z J, et al. Person re-identification algorithm based on global feature stitching. Appl Res Comput, 2021, 38(1): 316熊煒, 楊荻椿, 熊子婕, 等. 基于全局特征拼接的行人重識別算法研究. 計算機應用研究, 2021, 38(1):316 [36] Chen W, Chen X, Zhang J, et al. A Multi-task deep network for person re-identification // Proceedings of the AAAI Conference on Artificial Intelligence. San Francisco, 2017: 3988 [37] Chen H R, Wang Y W, Shi Y M, et al. Deep transfer learning for person Re-identification // 2018 IEEE Fourth International Conference on Multimedia Big Data (BigMM). Xi'an, 2018: 1 [38] Ding S Y, Lin L, Wang G R, et al. Deep feature learning with relative distance comparison for person re-identification. Pattern Recognit, 2015, 48(10): 2993 doi: 10.1016/j.patcog.2015.04.005 [39] Shi H L, Yang Y, Zhu X Y, et al. Embedding deep metric for person re-identification: A study against large variations // Proceedings of the European Conference on Computer Vision. Amsterdam, 2016: 732 [40] Su C, Zhang S L, Xing J L, et al. Deep attributes driven multi-camera person re-identification // Proceedings of the European Conference on Computer Vision. Amsterdam, 2016: 475 [41] Schroff F, Kalenichenko D, Philbin J. FaceNet: A unified embedding for face recognition and clustering // 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Boston, 2015: 815 [42] Hermans A, Beyer L, Leibe B, et al. In defense of the triplet loss for person re-identification [J/OL]. Arxiv Perprint (2017-03-22) [2020-12-22].https://arxiv.org/abs/1703.07737 [43] Cheng D, Gong Y H, Zhou S P, et al. Person re-identification by multi-channel parts-based CNN with improved triplet loss function // 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, 2016: 1335 [44] Chen W H, Chen X T, Zhang J G, et al. Beyond triplet loss: A deep quadruplet network for person Re-identification // 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu, 2017: 1320 [45] Luo H, Gu Y Z, Liao X Y, et al. Bag of tricks and a strong baseline for deep person Re-identification // 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). Long Beach, 2019: 1487 [46] Sun Y F, Zheng L, Yang Y, et al. Beyond part models: Person retrieval with refined part pooling (and a strong convolutional baseline) // Proceedings of the European Conference on Computer Vision. Munich, 2018: 501 [47] Li D W, Chen X T, Zhang Z, et al. Learning deep context-aware features over body and latent parts for person Re-identification // 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu, 2017: 7398 [48] Kalayeh M M, Basaran E, G?kmen M, et al. Human semantic parsing for person Re-identification // 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, 2018: 1062 [49] Xu L Z, Peng L, Zhu F Z. Pedestrian re-identification method based on multi-task pyramid overlapping matching. Comput Eng, 2021, 47(1): 239徐龍壯, 彭力, 朱鳳增. 多任務金字塔重疊匹配的行人重識別方法. 計算機工程, 2021, 47(1):239 [50] Zhu K, Guo H Y, Liu Z W, et al. Identity-guided human semantic parsing for person re-identification [J/OL]. ArXiv Preprint (2020-07-27) [2020-12-22].https://arxiv.org/abs/2007.13467 [51] Zhao L M, Li X, Zhuang Y T, et al. Deeply-learned part-aligned representations for person re-identification // 2017 IEEE International Conference on Computer Vision (ICCV). Venice, 2017: 3239 [52] Dong Y C, Liu H Z, Xu C. Person re-identification method based on saliency multi-scale feature collaborative fusion [J/OL]. Computr Engineering, https://doi.org/10.19678/j.issn.1000-3428.0057938董亞超, 劉宏哲, 徐成. 基于顯著性多尺度特征協作融合的行人重識別方法[J/OL]. 計算機工程, https://doi.org/10.19678/j.issn.1000-3428.0057938 [53] Wang G A, Yang S, Liu H Y, et al. High-order information matters: Learning relation and topology for occluded person Re-identification // 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Seattle, 2020: 6448 [54] Yang W X, Yan Y, Chen S. Adaptive deep metric embeddings for person re-identification under occlusions. Neurocomputing, 2019, 340: 125 doi: 10.1016/j.neucom.2019.02.042 [55] Hochreiter S, Schmidhuber J. Long short-term memory. Neural Comput, 1997, 9(8): 1735 doi: 10.1162/neco.1997.9.8.1735 [56] Varior R R, Haloi M, Wang G, et al. Gated Siamese convolutional neural network architecture for human re-identification // Proceedings of the European Conference on Computer Vision. Amsterdam, 2016: 791 [57] Yang W X, Yan Y, Chen S, et al. Multi-scale generative adversarial network for person Re-identification under occlusion. J Softw, 2020, 31(7): 1943楊婉香, 嚴嚴, 陳思, 等. 基于多尺度生成對抗網絡的遮擋行人重識別方法. 軟件學報, 2020, 31(7):1943 [58] Goodfellow I J, Pouget-Abadie J, Mirza M, et al. Generative Adversarial Nets // Conference and Workshop on Neural Information Processing Systems. Montreal, 2014: 2672 [59] Radford A, Metz L, Chintala S, et al. Unsupervised representation learning with deep convolutional generative adversarial networks [J/OL]. Arxiv Preprint (2015-11-19) [2020-12-22]. https//arxiv. org/abs/1511.06434 [60] Zhong Z, Zheng L, Zheng Z D, et al. Camera style adaptation for person Re-identification // 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, 2018: 5157 [61] Zhu J Y, Park T, Isola P, et al. Unpaired image-to-image translation using cycle-consistent adversarial networks // 2017 IEEE International Conference on Computer Vision (ICCV). Venice, 2017: 2242 [62] Deng W J, Zheng L, Ye Q X, et al. Image-image domain adaptation with preserved self-similarity and domain-dissimilarity for person Re-identification // 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, 2018: 994 [63] Li Y T, Xue R N, Zhu M M, et al. ReadNet: Towards accurate ReID with limited and noisy samples [J/OL]. ArXiv Preprint (2020-05-12) [2020-12-22].https://arxiv.org/abs/2005.05740 [64] Zhai Y P, Lu S J, Ye Q X, et al. AD-cluster: Augmented discriminative clustering for domain adaptive person re-identification // 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Seattle, 2020: 9018 [65] Zhang X W, Lü M Q, Li H. Cross-domain person re-identification based on partial semantic feature invariance. J Beijing Univ Aeronaut Astronaut, 2020, 46(9): 1682張曉偉, 呂明強, 李慧. 基于局部語義特征不變性的跨域行人重識別. 北京航空航天大學學報, 2020, 46(9):1682 [66] Liu C, Chang X J, Shen Y D. Unity style transfer for person Re-identification // 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Seattle, 2020: 6886 [67] Qian X L, Fu Y W, Xiang T, et al. Pose-normalized image generation for person re-identification // Proceedings of the European Conference on Computer Vision. Munich, 2018: 661 [68] Liu J X, Ni B B, Yan Y C, et al. Pose transferrable person re-identification // 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, 2018: 4099 [69] Cao Z, Simon T, Wei S H, et al. Realtime multi-person 2D pose estimation using part affinity fields // 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu, 2017: 1302 [70] Mirza M, Osindero S. Conditional generative adversarial nets [J/OL]. ArXiv Preprint (2014-11-06) [2020-12-22]. https://arxiv.org/abs/1411.1784 [71] Farenzena M, Bazzani L, Perina A, et al. Person re-identification by symmetry-driven accumulation of local features // 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Francisco, 2010: 2360 [72] Kviatkovsky I, Adam A, Rivlin E. Color invariants for person re-identification. IEEE Trans Pattern Anal Mach Intell, 2013, 35(7): 1622 doi: 10.1109/TPAMI.2012.246 [73] Ma B P, Su Y, Jurie F. Local descriptors encoded by fisher vectors for person re-identification // International Conference on Computer Vision. Barcalona, 2012: 413 [74] Chen D P, Yuan Z J, Chen B D, et al. Similarity learning with spatial constraints for person re-identification // 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, 2016: 1268 [75] K?stinger M, Hirzer M, Wohlhart P, et al. Large scale metric learning from equivalence constraints // 2012 IEEE Conference on Computer Vision and Pattern Recognition. Providence, 2012: 2288 [76] Zaremba W, Sutskever I, Vinyals O, et al. Recurrent neural network regularization [J/OL]. Arxiv Preprint (2014-09-08) [2020-12-22].https://arxiv.org/abs/1409.2329 [77] McLaughlin N, Rincon J M, Miller P. Recurrent convolutional network for video-based person Re-identification // 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, 2016: 1325 [78] Wu L, Shen C H, Den Hengel A, et al. Deep recurrent convolutional networks for video-based person re-identification: An end-to-end approach [J/OL]. ArXiv Preprint (2014-06-11) [2020-12-22].https://arxiv.org/abs/1606.01609v2 [79] Cho K, Van Merrienboer B, Gulcehre C, et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation [J/OL]. ArXiv Preprint (2014-06-03) [2020-12-22]. https://arxiv.org/abs/1406.1078 [80] Yan Y C, Ni B B, Song Z C, et al. Person re-identification via recurrent feature aggregation // Proceedings of the European Conference on Computer Vision. Amsterdam, 2016: 701 [81] Zhang R M, Li J Y, Sun H B, et al. SCAN: Self-and-collaborative attention network for video person re-identification. IEEE Trans Image Process, 2019, 28(10): 4870 doi: 10.1109/TIP.2019.2911488 [82] Liao X Y, He L X, Yang Z W, et al. Video-based person re-identification via 3D convolutional networks and non-local attention // Asian Conference on Computer Vision. Perth, 2018: 620 [83] Li S, Bak S, Carr P, et al. Diversity regularized spatiotemporal attention for video-based person re-identification // 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, 2018: 369 [84] Gu X Q, Chang H, Ma B P, et al. Appearance-preserving 3D convolution for video-based person re-identification // Proceedings of the European Conference on Computer Vision. Glasgow, 2020: 228 [85] Feng Y, Wang Y, Luo J B, et al. Video-based person re-identification using gated convolutional recurrent neural networks [J/OL]. ArXiv Preprint (2020-03-21) [2020-12-22]. https://arxiv.org/abs/2003.09717 [86] Hou R B, Ma B P, Chang H, et al. VRSTC: Occlusion-free video person Re-identification // 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Long Beach, 2019: 7176 [87] Gao S, Wang J Y, Lu H C, et al. Pose-guided visible part matching for occluded person ReID // 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Seattle, 2020: 11741 [88] Yan Y C, Qin J, Chen J X, et al. Learning multi-granular hypergraphs for video-based person re-identification // 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Seattle, 2020: 2896 [89] Zhang Z Z, Lan C L, Zeng W J, et al. Multi-granularity reference-aided attentive feature aggregation for video-based person Re-identification // 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Seattle, 2020: 10404 [90] Liu J, Zha Z, Zhu X, et al. Co-saliency spatio-temporal interaction network for person re-identification in videos [J/OL]. ArXiv Preprint (2020-05-11) [2020-12-22]. https://arxiv.org/abs/2004.04979 [91] Shen X, Lin Z, Brandt J, et al. Object retrieval and localization with spatially-constrained similarity measure and k-nn re-ranking // 2012 IEEE Conference on Computer Vision and Pattern Recognition. Providence, 2012: 3013 [92] Li W, Wu Y, Mukunoki M, et al. Common-near-neighbor analysis for person re-identification // 2012 19th IEEE International Conference on Image Processing. Orlando, , 2012: 1621 [93] Ye M, Chen J, Leng Q M, et al. Coupled-view based ranking optimization for person re-identification // International Conference on Multimedia Modeling. Kaiserslautern, 2015: 105 [94] Wang H X, Gong S G, Zhu X T, et al. Human-in-the-loop person re-identification // Proceedings of the European Conference on Computer Vision. Amsterdam, 2016: 405 [95] Sarfraz M S, Schumann A, Eberle A, et al. A pose-sensitive embedding for person re-identification with expanded cross neighborhood Re-ranking // 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Salt Lake City, 2018: 420 -
點擊查看大圖
圖(5) / 表(6)
計量
- 文章訪問數: 1249
- HTML全文瀏覽量: 729
- PDF下載量: 287
- 被引次數: 0
