Cross-Modality Person Re-Identification via Modality Confusion and Center Aggregation
The DOI matches its Crossref record; 60 of the 60 references it cites were found in a registry or an index.
Abstract
Cross-modality person re-identification is a challenging task due to large cross-modality discrepancy and intramodality variations. Currently, most existing methods focus on learning modality-specific or modality-shareable features by using the identity supervision or modality label. Different from existing methods, this paper presents a novel Modality Confusion Learning Network (MCLNet). Its basic idea is to confuse two modalities, ensuring that the optimization is explicitly concentrated on the modality-irrelevant perspective. Specifically, MCLNet is designed to learn modality-invariant features by simultaneously minimizing inter-modality discrepancy while maximizing cross-modality similarity among instances in a single framework. Furthermore, an identity-aware marginal center aggregation strategy is introduced to extract the centralization features, while keeping diversity with a marginal constraint. Finally, we design a camera-aware learning scheme to enrich the discriminability. Extensive experiments on SYSU-MM01 and RegDB datasets show that MCLNet outperforms the state-of-the-art by a large margin. On the large-scale SYSU-MM01 dataset, our model can achieve 65.40 % and 61.98 % in terms of Rank-1 accuracy and mAP value.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 1×
“Base uses ResNet-50 [12] pre-trained on ImageNet [28] as backbone.”
MethodImageNet Large Scale Visual Recognition Challenge
Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., Huang, Z., Karpathy, A., Khosla, A., Bernstein, M., et al. (2015) · International Journal of Computer Vision · doi:10.1007/s11263-015-0816-y · Cited by 39,380 · cited 1×
“Base uses ResNet-50 [12] pre-trained on ImageNet [28] as backbone.”
Method(2008) · Journal of Machine Learning Research · Cited by 33,051
Labaca-Castro, R. (2023) · Machine Learning under Malware Attack · doi:10.1007/978-3-658-40442-0_9 · Cited by 19,272
A Discriminative Feature Learning Approach for Deep Face Recognition
Wen, Y., Zhang, K., Li, Z., & Qiao, Y. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46478-7_31 · Cited by 4,077 · cited 2×
“Center loss [38] can be represented as: where x i denotes the i th input sample, c y i is the y ith class center, f x i is the embedding extracted by feature extractor.”
BackgroundMethodRandom Erasing Data Augmentation
Zhong, Z., Zheng, L., Kang, G., Li, S., & Yang, Y. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i07.7000 · Cited by 3,617
Random Erasing Data Augmentation
Zhong, Z., Zheng, L., Kang, G., Li, S., & Yang, Y. (2017) · arXiv · doi:10.48550/arxiv.1708.04896 · Cited by 3,617 · cited 1×
“AGW* means AGW uses random erasing [56]. input images are first resized to 288 × 144, then we adopt random crop with zero-padding, random horizontal flipping and random erasing for data augmentation [56].”
MethodBeyond Part Models: Person Retrieval with Refined Part Pooling (and A Strong Convolutional Baseline)
Sun, Y., Zheng, L., Yang, Y., Tian, Q., & Wang, S. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01225-0_30 · Cited by 2,522
Deep Learning for Person Re-Identification: A Survey and Outlook
Ye, M., Shen, J., Lin, G., Xiang, T., Shao, L., & Hoi, S. C. H. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3054775 · Cited by 2,259
Self-citationBag of Tricks and a Strong Baseline for Deep Person Re-Identification
Luo, H., Gu, Y., Liao, X., Lai, S., & Jiang, W. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw.2019.00190 · Cited by 1,584 · cited 1×
“To handle this problem, most existing methods adopt center loss [21] to simultaneously learn a center of each class for feature embeddings, and penalize the distances between the samples and their corresponding classes.”
MethodDeng, W., Zheng, L., Ye, Q., Kang, G., Yang, Y., & Jiao, J. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00110 · Cited by 1,011
A Discriminatively Learned CNN Embedding for Person Reidentification
Zheng, Z., Zheng, L., & Yang, Y. (2018) · ACM Transactions on Multimedia Computing, Communications, and Applications · doi:10.1145/3159171 · Cited by 874 · cited 1×
“Certainly, a conventional loss function consisting of identity loss (ID loss [55]) Lid and weighted regularization triplet (WRT) loss [47] Lwrt is designed to learn dicriminative representation:”
BackgroundRGB-Infrared Cross-Modality Person Re-identification
Wu, A., Zheng, W.-S., Yu, H.-X., Gong, S., & Lai, J. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.575 · Cited by 862 · cited 6×
“SYSU-MM01 [40] is the first large-scale benchmark dataset for cm-ReID collected by 6 cameras, consisting of 4 visible and 2 infrared cameras.”
BackgroundMethodInfluentialNguyen, D., Hong, H., Kim, K., & Park, K. (2017) · Sensors · doi:10.3390/s17030605 · Cited by 790 · cited 2×
“RegDB [24] is collected by a dual-camera system, including one visible and one infrared camera.”
BackgroundMethodRelation-Aware Global Attention for Person Re-Identification
Zhang, Z., Lan, C., Zeng, W., Jin, X., & Chen, Z. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00325 · Cited by 652 · cited 1×
“Compared to the widely studied single-modality ReID [5, 52], the cm-ReID is much more challenging due to large visual differences between the two modalities and different camera environments.”
MethodTransferable Joint Attribute-Identity Deep Learning for Unsupervised Person Re-identification
Wang, J., Zhu, X., Gong, S., & Li, W. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00242 · Cited by 637
Camera Style Adaptation for Person Re-identification
Zhong, Z., Zheng, L., Zheng, Z., Li, S., & Yang, Y. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00541 · Cited by 635
ABD-Net: Attentive but Diverse Person Re-Identification
Chen, T., Ding, S., Xie, J., Yuan, Y., Chen, W., Yang, Y., Ren, Z., & Wang, Z. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00844 · Cited by 561 · cited 2×
“Compared to the widely studied single-modality ReID [5, 52], the cm-ReID is much more challenging due to large visual differences between the two modalities and different camera environments.”
BackgroundMethodRGB-Infrared Cross-Modality Person Re-Identification via Joint Pixel and Feature Alignment
Wang, G., Zhang, T., Cheng, J., Liu, S., Yang, Y., & Hou, Z. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00372 · Cited by 559 · cited 6×
“[7] applies GAN to handle the lack of insufficient discriminative information and the issue of large scale cross-modality metric learning.”
BackgroundMethodInfluentialDynamic Dual-Attentive Aggregation Learning for Visible-Infrared Person Re-identification
Ye, M., Shen, J., J. Crandall, D., Shao, L., & Luo, J. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58520-4_14 · Cited by 523
Self-citationHigh-Order Information Matters: Learning Relation and Topology for Occluded Person Re-Identification
Wang, G., Yang, S., Liu, H., Wang, Z., Yang, Y., Wang, S., Yu, G., Zhou, E., & Sun, J. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00648 · Cited by 512 · cited 1×
“Existing works have shown desirable performance on the widely-used datasets with deep learning technique [50, 18, 58, 14, 32, 2, 59, 20].”
BackgroundComputational and Performance Aspects of PCA-Based Face-Recognition Algorithms
Moon, H., & Phillips, P. J. (2001) · Perception · doi:10.1068/p2896 · Cited by 509 · cited 1×
“The cumulative matching characteristics (CMC) [23], mean average precision (mAP) and mean inverse negative penalty [47] (mINP) are used as evaluation metrics.”
MethodLearning to Reduce Dual-Level Discrepancy for Infrared-Visible Person Re-Identification
Wang, Z., Wang, Z., Zheng, Y., Chuang, Y.-Y., & Satoh, S. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00071 · Cited by 493 · cited 4×
“Different from existing methods utilizing GAN [7, 37, 33, 34] to transfer sample domains between modalities by generating cross-modality images, we apply the confusion learn-16385 ing mechanism for deceiving the network into confounding the visible modality with the infrared one.”
BackgroundMethodInfluentialInfrared-Visible Cross-Modal Person Re-Identification with an X Modality
Li, D., Wei, X., Hong, X., & Gong, Y. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i04.5891 · Cited by 431 · cited 3×
“Besides, some methods generate a common intermediate modality [16] to eliminate the influences caused by modality discrepancy.”
BackgroundMethodPyramidal Person Re-IDentification via Multi-Loss Dynamic Training
Zheng, F., Deng, C., Sun, X., Jiang, X., Guo, X., Yu, Z., Huang, F., & Ji, R. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00871 · Cited by 428 · cited 2×
“Some methods are aware of local information and global information [35, 31, 30, 53], which can improve the performance when they are combined.”
BackgroundStyle Normalization and Restitution for Generalizable Person Re-Identification
Jin, X., Lan, C., Zeng, W., Chen, Z., & Zhang, L. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00321 · Cited by 426
Cross-Modality Person Re-Identification with Generative Adversarial Training
Dai, P., Ji, R., Wang, H., Wu, Q., & Huang, Y. (2018) · Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2018/94 · Cited by 425 · cited 3×
“[7] applies GAN to handle the lack of insufficient discriminative information and the issue of large scale cross-modality metric learning.”
BackgroundMethodCross-Modality Person Re-Identification With Shared-Specific Feature Transfer
Lu, Y., Wu, Y., Liu, B., Zhang, T., Li, B., Chu, Q., & Yu, N. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01339 · Cited by 418
Hierarchical Discriminative Learning for Visible Thermal Person Re-Identification
Ye, M., Lan, X., Li, J., & Yuen, P. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.12293 · Cited by 405 · cited 2×
“Following the evaluation protocol proposed by [44], we randomly select 206 identities for training and another 206 identities for testing.”
BackgroundMethodSelf-citationSun, Y., Xu, Q., Li, Y., Zhang, C., Li, Y., Wang, S., & Sun, J. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00048 · Cited by 388 · cited 1×
“Some methods are aware of local information and global information [35, 31, 30, 53], which can improve the performance when they are combined.”
BackgroundLearning to rank in person re-identification with metric ensembles
Paisitkriangkrai, S., Shen, C., & van den Hengel, A. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298794 · Cited by 385 · cited 1×
“A few methods propose to solve person re-identification as ranking problems [25, 3].”
MethodHi-CMD: Hierarchical Cross-Modality Disentanglement for Visible-Infrared Person Re-Identification
Choi, S., Lee, S., Kim, Y., Kim, T., & Kim, C. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.01027 · Cited by 368
Cross-Modality Paired-Images Generation for RGB-Infrared Person Re-Identification
Wang, G.-A., Zhang, T., Yang, Y., Cheng, J., Chang, J., Liang, X., & Hou, Z.-G. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i07.6894 · Cited by 347
Bi-Directional Center-Constrained Top-Ranking for Visible Thermal Person Re-Identification
Ye, M., Lan, X., Wang, Z., & Yuen, P. C. (2020) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2019.2921454 · Cited by 331 · cited 2×
“Two-stream networks [45, 47, 44, 46] can learn both the modality-shared features and the modality-specific information.”
BackgroundSelf-citationAD-Cluster: Augmented Discriminative Clustering for Domain Adaptive Person Re-Identification
Zhai, Y., Lu, S., Ye, Q., Shan, X., Chen, J., Ji, R., & Tian, Y. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00904 · Cited by 318
Visible-Infrared Person Re-Identification via Homogeneous Augmented Tri-Modal Learning
Ye, M., Shen, J., & Shao, L. (2021) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2020.3001665 · Cited by 305
Self-citationLearning Modality-Specific Representations for Visible-Infrared Person Re-Identification
Feng, Z., Lai, J., & Xie, X. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2019.2928126 · Cited by 291 · cited 1×
“To narrow the gap between two modalities, existing methods mainly focus on learning shareable common feature representations, via either one [37, 40] or two-stream networks [45, 9].”
BackgroundHSME: Hypersphere Manifold Embedding for Visible Thermal Person Re-Identification
Hao, Y., Wang, N., Li, J., & Gao, X. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33018385 · Cited by 281
Dissecting Person Re-Identification From the Viewpoint of Viewpoint
Sun, X., & Zheng, L. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00070 · Cited by 271 · cited 1×
“Similar to single-modality person re-identification, the appearance of persons in cm-ReID is also easily affected by clothing, scale, shielding, attitude and viewpoints [49, 29], which makes the ReID task more difficult.”
BackgroundRe-Identification With Consistent Attentive Siamese Networks
Zheng, M., Karanam, S., Wu, Z., & Radke, R. J. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00588 · Cited by 261 · cited 1×
“[51, 4, 54, 41] utilize attention information to enhance representation learning.”
MethodSecond-Order Non-Local Attention Networks for Person Re-Identification
Bryan, B., Gong, Y., Zhang, Y., & Poellabauer, C. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00386 · Cited by 235 · cited 1×
“Besides, [59, 5, 36, 42, 53] focused on the loss functions designed for deep learning.”
BackgroundCross-Modality Person Re-Identification via Modality-Aware Collaborative Ensemble Learning
Ye, M., Lan, X., Leng, Q., & Shen, J. (2020) · IEEE Transactions on Image Processing · doi:10.1109/tip.2020.2998275 · Cited by 235 · cited 1×
“A modality-aware learning method [43] handles the modality discrepancy at the classifier level.”
MethodSelf-citationRGB-IR Person Re-identification by Cross-Modality Similarity Preservation
Wu, A., Zheng, W.-S., Gong, S., & Lai, J. (2020) · International Journal of Computer Vision · doi:10.1007/s11263-019-01290-1 · Cited by 172
Person Re-identification with Cascaded Pairwise Convolutions
Wang, Y., Chen, Z., Wu, F., & Wang, G. (2018) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2018.00159 · Cited by 166 · cited 1×
“Besides, [59, 5, 36, 42, 53] focused on the loss functions designed for deep learning.”
BackgroundZhang, Z., Lan, C., Zeng, W., & Chen, Z. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.01042 · Cited by 160
Self-Critical Attention Learning for Person Re-Identification
Chen, G., Lin, C., Ren, L., Lu, J., & Zhou, J. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00973 · Cited by 160 · cited 1×
“[51, 4, 54, 41] utilize attention information to enhance representation learning.”
MethodSpectral Feature Transformation for Person Re-Identification
Luo, C., Chen, Y., Wang, N., & Zhang, Z.-X. (2019) · 2019 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00508 · Cited by 158 · cited 1×
“Existing works have shown desirable performance on the widely-used datasets with deep learning technique [50, 18, 58, 14, 32, 2, 59, 20].”
BackgroundCOCAS: A Large-Scale Clothes Changing Person Dataset for Re-Identification
Yu, S., Li, S., Chen, D., Zhao, R., Yan, J., & Qiao, Y. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.00346 · Cited by 124
Pu, N., Chen, W., Liu, Y., Bakker, E. M., & Lew, M. S. (2020) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3394171.3413673 · Cited by 123 · cited 1×
“[26] applies a dual Gaussian-based variational auto-encoder, to disentangle an identity-discriminable and an identity-ambiguous cross-modality feature subspace.”
MethodZhou, S., Wang, F., Huang, Z., & Wang, J. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00813 · Cited by 123 · cited 2×
“Existing works have shown desirable performance on the widely-used datasets with deep learning technique [50, 18, 58, 14, 32, 2, 59, 20].”
BackgroundRe-Ranking via Metric Fusion for Object Retrieval and Person Re-Identification
Bai, S., Tang, P., Torr, P. H. S., & Latecki, L. J. (2019) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr.2019.00083 · Cited by 119 · cited 1×
“A few methods propose to solve person re-identification as ranking problems [25, 3].”
MethodSDL: Spectrum-Disentangled Representation Learning for Visible-Infrared Person Re-Identification
Kansal, K., Subramanyam, A. V., Wang, Z., & Satoh, S. (2020) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2019.2963721 · Cited by 114 · cited 1×
“[15] designs a spectrum dispelling branch to eliminate the influence of the spectrum.”
BackgroundSecond-order Non-local Attention Networks for Person Re-identificationPreprint
Bryan, B., Xia, Gong, Y., Zhang, Y., & Poellabauer, C. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.00295 · Cited by 104 · cited 1×
“Besides, [59, 5, 36, 42, 53] focused on the loss functions designed for deep learning.”
BackgroundA Similarity Inference Metric for RGB-Infrared Cross-Modality Person Re-identification
Jia, M., Zhai, Y., Lu, S., Ma, S., & Zhang, J. (2020) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2020/143 · Cited by 79
Person Re-Identification by Context-Aware Part Attention and Multi-Head Collaborative Learning
Wu, D., Ye, M., Lin, G., Gao, X., & Shen, J. (2021) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2021.3075894 · Cited by 75 · cited 1×
“[51, 4, 54, 41] utilize attention information to enhance representation learning.”
MethodSelf-citationView Confusion Feature Learning for Person Re-Identification
Liu, F., & Zhang, L. (2019) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2019.00674 · Cited by 72 · cited 2×
“Existing works have shown desirable performance on the widely-used datasets with deep learning technique [50, 18, 58, 14, 32, 2, 59, 20].”
BackgroundMethodZhou, J., Su, B., & Wu, Y. N. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.00298 · Cited by 59 · cited 1×
“Existing works have shown desirable performance on the widely-used datasets with deep learning technique [50, 18, 58, 14, 32, 2, 59, 20].”
BackgroundWePerson: Learning a Generalized Re-identification Model from All-weather Virtual Data
Li, H., Ye, M., & Du, B. (2021) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3474085.3475455 · Cited by 34 · cited 1×
“Person re-identification (ReID) is a technique that uses computer vision technology to determine whether there is a specific person from a gallery set captured by surveillance cameras [17].”
MethodSelf-citationCamera On-Boarding for Person Re-Identification Using Hypothesis Transfer Learning
Ahmed, S. M., Lejbølle, A. R., Panda, R., & Roy–Chowdhury, A. K. (2020) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr42600.2020.01216 · Cited by 31
TICNet: A Target-Insight Correlation Network for Object Tracking
Ruan, W., Ye, M., Wu, Y., Liu, W., Chen, J., Liang, C., Li, G., & Lin, C. (2021) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2021.3070677 · Cited by 16 · cited 1×
“MCLNet minimizes inter-modality discrepancy while maximizing cross-modality similarity among instances through the min-max game [27].”
MethodSelf-citation
Cited by
Zhang, Y., & Wang, H. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.00214 · Cited by 322
Lu, H., Zou, X., & Zhang, P. (2023) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v37i2.25273 · Cited by 190
Metadata
- Authors
- Hao, X., Zhao, S., Ye, M., & Shen, J.
- Venue
- 2021 IEEE/CVF International Conference on Computer Vision (ICCV)
- Publisher
- IEEE
- Published
- 2021-10
- Pages
- 16383-16392
- OpenAlex
- W3202788649
- Cited by
- 214
- References
- 60
- FWCI
- 12.13
- Type
- conference paper
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.