Overview of Pedestrian Re-Identification Based on Deep Learning

doi:10.3778/j.issn.1002-8331.2110-0300

Abstract

Abstract: Person re-identification（ReID） aims to retrieve target pedestrians across multiple non-overlapping cameras, which is a challenging research topic in the field of computer vision. The traditional person re-identification methods relying on manual features have low performance and poor robustness, and can not adapt to the information age of data explosion. In recent years, with the emergence of large-scale pedestrian data sets and the rapid development of deep learning, many outstanding results have been achieved in pedestrian re-identification research. This paper first sorts out the research methods of supervised learning with performance close to saturation, and discusses the current situation of weakly supervised learning, cross-modal data and end-to-end pedestrian re-recognition, which has been studied in recent years. After that, comparison and analysis of different types of person re-identification methods and the commonly used data sets are listed. The performance of some classic algorithms is compared on data sets such as Market-1501 and DukeMTMC-ReID. Finally, the future research direction of pedestrian re-recognition is prospected.

Key words: person re-identification, supervised learning, weakly supervised learning, cross-modality, end-to-end

摘要： 行人重识别主要研究在不同摄像机拍摄的图形中检索目标行人的任务，是计算机视觉领域一个极具挑战性的研究课题。传统依赖手工特征的行人重识别方法性能低且鲁棒性差，不能适应数据爆炸增长的信息时代。近年来，随着大规模行人数据集的出现和深度学习的迅速发展，行人重识别研究取得了许多突出成果。梳理了性能接近饱和的有监督学习研究方法，并探讨近几年研究热度较高的弱监督学习、跨模态数据和端到端的行人重识别现状；对不同类型行人重识别方法比较分析，列举了常用数据集，并将部分经典算法在Market-1501、DukeMTMC-ReID等数据集上进行性能比较；对行人重识别的未来研究方向进行了展望。

关键词: 行人重识别, 有监督学习, 弱监督学习, 跨模态, 端到端

YANG Yongsheng, DENG Miaolei, LI Lei, ZHANG Dexian. Overview of Pedestrian Re-Identification Based on Deep Learning[J]. Computer Engineering and Applications, 2022, 58(9): 51-66.

杨永胜, 邓淼磊, 李磊, 张德贤. 基于深度学习的行人重识别综述[J]. 计算机工程与应用, 2022, 58(9): 51-66.

References

[1] ZHENG L，YANG Y，HAUPTMANN A G.Person re-identification：past，present and future[J]arXiv：1610.
02984，2016.
[2] LENG Q，YE M，TIAN Q.A survey of open-world person re-identification[J].IEEE Transactions on Circuits and Systems for Video Technology，2019，30（4）：1092-1108.
[3] 葛雯，史正伟.改进YOLOV3算法在行人识别中的应用[J].计算机工程与应用，2019，55（20）：128-133.
GE W，SHI Z W.Application of improved YOLOV3 algorithm in pedestrian identification[J].Computer Engineering and Applications，2019，55（20）：128-133.
[4] GAO J Y，YANG X S，ZHANG T Z，et al.Robust visual tracking method via deep learning[J].Chinese Journal of Computers，2016，39（7）：1419-1434.
[5] DALAL N，TRIGGS B.Histograms of oriented gradients for human detection[C]//Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Washington DC：IEEE Computer Society，2005：886-893.
[6] KOESTINGER M，HIRZER M，WOHLHART P，et al.Large scale metric learning from equivalence constraints[C]//2012 IEEE Conference on Computer Vision and Pattern Recognition，2012：2288-2295.
[7] MARTINEL N，MICHELONI C，FORESTI G L.Saliency weighted features for person re-identification[C]//European Conference on Computer Vision.Cham：Springer，2014：191-208.
[8] LOWE D G.Object recognition from local scale-invariant features[C]//Proceedings of the Seventh IEEE International Conference on Computer Vision，1999：1150-1157.
[9] ZHENG W S，GONG S，XIANG T.Reidentification by relative distance comparison[J].IEEE Transactions on Pattern Analysis and Machine Intelligence，2012，35（3）：653-668.
[10] LI Z，CHANG S，LIANG F，et al.Learning locally-adaptive decision functions for person verification[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2013：3610-3617.
[11] 李锦明，曲毅，裴禹豪，等.预训练卷积神经网络模型微调的行人重识别[J].计算机工程与应用，2018，54（20）：219-222.
LI J M，QU Y，PEI Y H，et al.Pedestrian re-identification based on fine-tuned pre-trained convolutional neural network model[J].Computer Engineering and Applications，2018，54（20）：219-222.
[12] ZHENG Z，ZHENG L，YANG Y.A discriminatively learned CNN embedding for person reidentification[J].ACM Transactions on Multimedia Computing，Communications，and Applications（TOMM），2017，14（1）：1-20.
[13] HERMANS A，BEYER L，LEIBE B.In defense of the triplet loss for person re-identification[J]arXiv：1703.
07737，2017.
[14] ZHENG L，ZHANG H，SUN S，et al.Person re-identification in the wild[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2017：1367-1376.
[15] YI D，LEI Z，LIAO S，et al.Deep metric learning for person re-identification[C]//2014 22nd International Conference on Pattern Recognition，2014：34-39.
[16] VARIOR R R，HALOI M，WANG G.Gated siamese convolutional neural network architecture for human re-identification[C]//European Conference on Computer Vision.Cham：Springer，2016：791-808.
[17] HE K，ZHANG X，REN S，et al.Deep residual learning for image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2016：770-778.
[18] WANG F，ZUO W，LIN L，et al.Joint learning of single-image and cross-image representations for person re-identification[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2016：1288-1296.
[19] CHEN G，LIN C，REN L，et al.Self-critical attention learning for person re-identification[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision，2019：9637-9646.
[20] XIA B N，GONG Y，ZHANG Y，et al.Second-order non-local attention networks for person re-identification[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision，2019：3760-3769.
[21] SUN Y，ZHENG L，YANG Y，et al.Beyond part models：person retrieval with refined part pooling（and a strong convolutional baseline）[C]//Proceedings of the European Conference on Computer Vision（ECCV），2018：480-496.
[22] 陈璠，彭力.多层级重叠条纹特征融合的行人重识别[J].计算机科学与探索，2021，15（9）：1753-1761.
CHEN F，PENG L.Person re-identification based on multi-level feature fusion with overlapping stripes[J].Journal of Frontiers of Computer Science and Technology，2021，15（9）：1753-1761.
[23] ZHANG Z，ZHANG H，LIU S.Person re-identification using heterogeneous local graph attention networks[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，2021：12136-12145.
[24] TAY C P，ROY S，YAP K H.Aanet：attribute attention network for person re-identifications[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，2019：7134-7143.
[25] ZHU Z，JIANG X，ZHENG F，et al.Aware loss with angular regularization for person re?identification[C]//Proceedings of the AAAI Conference on Artificial Intelligence，2020：13114-13121.
[26] SARFRAZ M S，SCHUMANN A，EBERLE A，et al.A pose-sensitive embedding for person re-identification with expanded cross neighborhood re-ranking[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2018：420-429.
[27] ZHENG Z，ZHENG L，YANG Y.Unlabeled samples generated by ganimprove the person re-identification baseline in vitro[C]//Proceedings of the IEEE International Conference on Computer Vision，2017：3754-3762.
[28] MCLAUGHLIN N，DEL RINCON J M，MILLER P.Recurrent convolutional network for video-based person re-identification[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2016：1325-1334.
[29] XU S，CHENG Y，GU K，et al.Jointly attentive spatial-temporal pooling networks for video-based person re-identification[C]//Proceedings of the IEEE International Conference on Computer Vision，2017：4733-4742.
[30] CHEN D，LI H，XIAO T，et al.Video person re-identification with competitive snippet-similarity aggregation and co-attentive snippet embedding[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2018：1169-1178.
[31] LIU X，ZHANG P，YU C，et al.Watching you：global-guided reciprocal learning for video-based person re-identification[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，2021：13334-13343.
[32] WANG Y，CHEN Z，WU F，et al.Person re-identification with cascaded pairwise convolutions[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2018：1470-1478.
[33] HE S，LUO H，WANG P，et al.Transreid：transformer-based object re-identification[J]arXiv：2102.04378，2021.
[34] JIA M，CHENG X，LU S，et al.Learning disentangled representation implicitly via transformer for occluded person re-identification[J].arXiv：2107.02380，2021.
[35] RAGHU M，UNTERTHINER T，KORNBLITH S，et al.Do vision transformers see like convolutional neural networks?[C]//Thirty-Fifth Conference on Neural Information Processing Systems，2021.
[36] YE M，SHEN J，LIN G，et al.Deep learning for person re?identification：a survey and outlook[J].arXiv：2001.
04193，2020.
[37] CHEN D，XU D，LI H，et al.Group consistent similarity learning via deep crf for person re-identification[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2018：8649-8658.
[38] DENG W，ZHENG L，YE Q，et al.Image-image domain adaptation with preserved self-similarity and domain-dissimilarity for person re-identification[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2018：994-1003.
[39] 周智恒，刘楷怡，黄俊楚，等.一种基于等距度量学习策略的行人重识别改进算法[J].电子与信息学报，2019，41（2）：477-483.
ZHOU Z H，LIU K Y，HUANG J C，et al.Improved metric learning algorithm for person re-identification based on equidistance[J].Journal of Electronics and Information Technology，2019，41（2）：477-483.
[40] 罗浩，姜伟，范星，等.基于深度学习的行人重识别研究进展[J].自动化学报，2019，45（11）：2032-2049.
LUO H，JIANG W，FAN X，et al.Research progress of pedestrian re-recognition based on deep learning[J].Acta Automatica Sinical，2019，45（11）：2032-2049
[41] LUO C，CHEN Y，WANG N，et al.Spectral feature transformation for person re-identification[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision，2019：4976-4985.
[42] ZHOU J，YU P，TANG W，et al.Efficient online local metric adaptation via negative samples for person re-identification[C]//Proceedings of the IEEE International Conference on Computer Vision，2017：2420-2428.
[43] WANG H，GONG S，ZHU X，et al.Human-in-the-loop person re-identification[C]//European Conference on Computer Vision.Cham：Springer，2016：405-422.
[44] BAI S，TANG P，TORR P H S，et al.Re-ranking via metric fusion for object retrieval and person re-identification[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，2019：740-749.
[45] BAK S，CARR P.One-shot metric learning for person re-identification[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2017：2990-2999.
[46] WU Y，LIN Y，DONG X，et al.Exploit the unknown gradually：one-shot video-based person re-identification by stepwise learning[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2018：5177-5186.
[47] WANG X，LIU M，RAYCHAUDHURI D S，et al.Learning person re-identification models from videos with weak supervision[J].IEEE Transactions on Image Processing，2021，30：3017-3028.
[48] KODIROV E，XIANG T，FU Z Y，et al.Person re-identification by unsupervised [l1] graph learning[C]//Proceedings of the 14th European Conference on Computer Vision（ECCV），Amsterdam，The Netherlands，2016：8-16.
[49] LIU Z，WANG D，LU H.Stepwise metric promotion for unsupervised video person re-identification[C]//Proceedings of the IEEE International Conference on Computer Vision，2017：2429-2438.
[50] ZHAO R，OUYANG W，WANG X.Unsupervised salience learning for person re-identification[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2013：3586-3593.
[51] YE M，LI J，MA A J，et al.Dynamic graph co-matching for unsupervised video-based person re-identification[J].IEEE Transactions on Image Processing，2019，28（6）：2976-2990.
[52] WANG X，PANDA R，LIU M，et al.Exploiting global camera network constraints for unsupervised video person re-identification[J].arXiv：1908.10486，2019.
[53] FAN H，ZHENG L，YAN C，et al.Unsupervised person re-identification：clustering and fine-tuning[J].ACM Transactions on Multimedia Computing，Communications，and Applications（TOMM），2018，14（4）：1-18.
[54] ZENG K，NING M，WANG Y，et al.Hierarchical clustering with hard-batch triplet loss for personre-identification[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，2020：13657-13665.
[55] LI M，ZHU X，GONG S.Unsupervised person re-identification by deep learning tracklet association[C]//Proceedings of the European Conference on Computer Vision（ECCV），2018：737-753.
[56] WU A，ZHENG W S，LAI J H.Unsupervised person re-identification by camera-aware similarity consistency learning[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision，2019：6922-6931.
[57] XUAN S，ZHANG S.Intra-inter camera similarity for unsupervised person re-identification[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，2021：11926-11935.
[58] YANG Q，YU H X，WU A，et al.Patch-based discriminative feature learning for unsupervised person re-identification[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，2019：3633-3642.
[59] FU Y，WEI Y，WANG G，et al.Self-similarity grouping：a simple unsupervised cross domain adaptation approach for person re-identification[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision，2019：6112-6121.
[60] MA A J，YUEN P C，LI J.Domain transfer support vector ranking for person re-identification without target camera label information[C]//Proceedings of the IEEE International Conference on Computer Vision，2013：3567-3574.
[61] WEI L，ZHANG S，GAO W，et al.Person transfer gan to bridge domain gap for person re-identification[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2018：79-88.
[62] ZHONG Z，ZHENG L，LI S，et al.Generalizing a person retrieval model hetero-and homogeneously[C]//Proceedings of the European Conference on Computer Vision（ECCV），2018：172-188.
[63] LIU J，ZHA Z J，CHEN D，et al.Adaptive transfer network for cross-domain personre-identification[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，2019：7202-7211.
[64] CHEN Y，ZHU X，GONG S.Instance-guided context rendering for cross-domain personre-identification[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision，2019：232-242.
[65] LI Y J，LIN C S，LIN Y B，et al.Cross-dataset person re-identification via unsupervised pose disentanglement and adaptation[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision，2019：7919-7929.
[66] CHEN H，WANG Y，LAGADEC B，et al.Joint generative and contrastive learning for unsupervised person re-identification[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，2021：2004-2013.
[67] ZHONG Z，ZHENG L，LUO Z，et al.Invariance matters：exemplar memory for domain adaptive person re-identification[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，2019：598-607.
[68] SONG J，YANG Y，SONG Y Z，et al.Generalizable person re-identification by domain-invariant mapping network[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，2019：719-728.
[69] QI L，WANG L，HUO J，et al.A novel unsupervised camera-aware domain adaptation framework for person re-identification[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision，2019：8080-8089.
[70] GE Y，ZHU F，CHEN D，et al.Self-paced contrastive learning with hybrid memory for domain adaptive object re-id[J].arXiv：2006.02713，2020.
[71] ZHENG K，LIU W，HE L，et al.Group-aware label transfer for domain adaptive personre-identification[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，2021：5310-5319.
[72] LV J，CHEN W，LI Q，et al.Unsupervised cross-dataset person re-identification by transfer learning of spatial-temporal patterns[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2018：7948-7956.
[73] LIAO S，SHAO L.Interpretable and generalizable person re-identification with query-adaptive convolution and temporal lifting[J].arXiv：1904.10424，2019.
[74] WU A，ZHENG W S，YU H X，et al.RGB-infrared cross-modality person re-identification[C]//Proceedings of the IEEE International Conference on Computer Vision，2017：5380-5389.
[75] YE M，LAN X，LI J，et al.Hierarchical discriminative learning for visible thermal person re-identification[C]//Proceedings of the AAAI Conference on Artificial Intelligence，2018：7501-7508.
[76] HAO Y，WANG N，LI J，et al.HSME：hypersphere manifold embedding for visible thermal person re-identification[C]//Proceedings of the AAAI Conference on Artificial Intelligence，2019：8385-8392.
[77] WANG Z，WANG Z，ZHENG Y，et al.Learning to reduce dual-level discrepancy for infrared-visible person re-identification[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，2019：618-626.
[78] CHOI S，LEE S，KIM Y，et al.Hi-cmd：hierarchical cross-modality disentanglement for visible-infrared person re-identification[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，2020：10257-10266.
[79] YE M，SHEN J J，CRANDALL D，et al.Dynamic dual-attentive aggregation learning for visible-infrared person re-identification[J].arXiv：2007.09314，2020.
[80] CHEN Y，WAN L，LI Z，et al.Neural feature search for RGB-infrared person re-identification[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，2021：587-597.
[81] HAQUE A，ALAHI A，LI F F.Recurrent attention models for depth-based person identification[J].arXiv：1611.
07212，2016.
[82] WU A，ZHENG W S，LAI J H.Robust depth-based person re-identification[J].IEEE Transactions on Image Processing，2017，26（6）：2588-2603.
[83] BARBOSA I B，CRISTANI M，DEL BUE A，et al.Re-identification with rgb-d sensors[C]//European Conference on Computer Vision.Berlin，Heidelberg：Springer，2012：433-442.
[84] KARIANAKIS N，LIU Z，CHEN Y，et al.Reinforced temporal attention and split-rate transfer for depth-based person re-identification[C]//Proceedings of the European Conference on Computer Vision（ECCV），2018：715-733.
[85] LI S，XIAO T，LI H，et al.Person search with natural language description[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2017：1970-1979.
[86] CHEN D，LI H，LIU X，et al.Improving deep visual representation for person re-identification by global and local image-language association[C]//Proceedings of the European Conference on Computer Vision（ECCV），2018：54-70.
[87] ZHANG Y，LU H.Deep cross-modal projection learning for image-text matching[C]//Proceedings of the European Conference on Computer Vision（ECCV），2018：686-701.
[88] LIU J，ZHA Z J，HONG R，et al.Deep adversarial graph attention convolution network for text-based person search[C]//Proceedings of the 27th ACM International Conference on Multimedia，2019：665-673.
[89] WANG Z，YE M，YANG F，et al.Cascaded SR-GAN for scale-adaptive low resolution person re-identification[C]//27th International Joint Conference on Artificial Intelligence，2018.
[90] LI Y J，CHEN Y C，LIN Y Y，et al.Recover and identify：a generative dual model for cross-resolution person re-identification[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision，2019：8090-8099.
[91] 廖华年，徐新.基于注意力机制的跨分辨率行人重识别[J].北京航空航天大学学报，2021，47（3）：605-612.
LIAO H N，XU X.Cross-resolution person re-identification based on attention mechanism[J].Journal of Beijing University of Aeronautics and Astronautics，2021，47（3）：605-612.
[92] ZHANG G，CHEN Y，LIN W，et al.Low resolution information also matters：learning multi-resolution representations for person re-identification[J]arXiv：2105.
12684，2021.
[93] LIU H，FENG J，JIE Z，et al.Neural person search machines[C]//Proceedings of the IEEE International Conference on Computer Vision，2017：493-501.
[94] YAN Y，ZHANG Q，NI B，et al.Learning context graph for person search[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition，2019：2158-2167.
[95] HAN C，YE J，ZHONG Y，et al.Re-id driven localization refinement for person search[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision，2019：9814-9823.
[96] LAN X，WANG H，GONG S，et al.Deep reinforcement learning attention selection for person re-identification[J].arXiv：1707.02785，2017.
[97] TANG S，ANDRILUKA M，ANDRES B，et al.Multiple people tracking by lifted multicut and person re-identification[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2017：3539-3548.
[98] RISTANI E，TOMASI C.Features for multi-target multi-camera tracking and re-identification[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2018：6036-6046.
[99] HOU Y，ZHENG L，WANG Z，et al.Locality aware appearance metric for multi-target multi-camera tracking[J].arXiv：1911.12037，2019.
[100] YAMAGUCHI M，SAITO K，USHIKU Y，et al.Spatio-temporal person retrieval via natural language queries[C]//Proceedings of the IEEE International Conference on Computer Vision，2017：1453-1462.
[101] GRAY D，TAO H.Viewpoint invariant pedestrian recognition with an ensemble of localized features[C]//European Conference on Computer Vision.Berlin，Heidelberg：Springer，2008：262-275.
[102] ZHENG W S，GONG S，XIANG T.Associating groups of people[C]//British Machine Vision Conference，2009：1-11.
[103] HIRZER M，BELEZNAI C，ROTH P M，et al.Person re-identification by descriptive and discriminative classification[C]//Scandinavian Conference on Image Analysis.Berlin，Heidelberg：Springer，2011：91-102.
[104] LI W，ZHAO R，XIAO T，et al.Deepreid：deep filter pairing neural network for person re-identification[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition，2014：152-159.
[105] ZHENG L，SHEN L，TIAN L，et al.Scalable person re-identification：a benchmark[C]//Proceedings of the IEEE International Conference on Computer Vision，2015：1116-1124.
[106] WANG T，GONG S，ZHU X，et al.Person re-identification by video ranking[C]//European Conference on Computer Vision.Cham：Springer，2014：688-703.
[107] ZHENG L，BIE Z，SUN Y，et al.Mars：a video benchmark for large-scale person re-identification[C]//European Conference on Computer Vision.Cham：Springer，2016：868-884.
[108] NGUYEN D T，HONG H G，KIM K W，et al.Person recognition system based on a combination of body images from visible light and thermal cameras[J].Sensors，2017，17（3）：605?633.
[109] MUNARO M，BASSO A，FOSSATI A，et al.3D reconstruction of freely moving persons for re-identification with a depth sensor[C]//2014 IEEE International Conference on Robotics and Automation（ICRA），2014：4512-4519.
[110] YOUNG P，LAI A，HODOSH M，et al.From image descriptions to visual denotations：new similarity metrics for semantic inference over event descriptions[J].Transactions of the Association for Computational Linguistics，2014，2：67-78.