Person Re Identification On Market 1501
Metriken
Rank-1
mAP
Ergebnisse
Leistungsergebnisse verschiedener Modelle zu diesem Benchmark
Vergleichstabelle
| Modellname | Rank-1 | mAP |
|---|---|---|
| counterfactual-attention-learning-for-fine | 95.5 | 89.5 |
| auto-reid-searching-for-a-part-aware-convnet | 95.4 | 94.2 |
| omni-scale-feature-learning-for-person-re | 94.8 | 84.9 |
| top-db-net-top-dropblock-for-activation | 95.5 | 94.1 |
| body-part-based-representation-learning-for | 95.7 | 89.4 |
| deep-attention-aware-feature-learning-for | 95.1 | 87.9 |
| gated-siamese-convolutional-neural-network | 65.88 | 39.55 |
| circle-loss-a-unified-perspective-of-pair | 96.1 | 87.4 |
| attribute-aware-attention-model-for-fine | 86.54 | 68.97 |
| beyond-human-parts-dual-part-aligned | 95.2 | 85.6 |
| aggregating-deep-pyramidal-representations | 93.6 | 81.7 |
| human-semantic-parsing-for-person-re | 93.6 | 83.3 |
| disassembling-the-dataset-a-camera-alignment | 94.3 | 83.6 |
| enhancing-person-re-identification-via | 96.1 | 92.0 |
| camera-style-adaptation-for-person-re | 85.66 | 65.87 |
| in-defense-of-the-triplet-loss-for-person-re | 81.38 | 60.71 |
| dual-cluster-contrastive-learning-for-person | 95.4 | 89.2 |
| msinet-twins-contrastive-search-of-multi | 95.3 | 89.6 |
| dip-learning-discriminative-implicit-parts | 95.8 | 90.8 |
| keypoint-promptable-re-identification | 95.9 | 89.6 |
| horizontal-pyramid-matching-for-person-re | 94.2 | 82.7 |
| incremental-generative-occlusion-adversarial | - | 84.1 |
| unihcp-a-unified-model-for-human-centric | - | 90.3 |
| person-re-identification-past-present-and | 72.54 | 46.00 |
| image-based-and-partially-categorical | 94.77 | 92.64 |
| cluster-level-feature-alignment-for-person-re | 95.7 | 89.5 |
| deep-representation-learning-with-part-loss | 88.2 | 69.3 |
| learning-discriminative-features-with | 95.7 | 86.9 |
| prototypical-contrastive-learning-based-clip | 96.1 | 91.0 |
| rethinking-person-re-identification-from-a | 96.4 | 95.3 |
| a-pose-sensitive-embedding-for-person-re | 90.3 | 84 |
| deep-attention-aware-feature-learning-for | 96.4 | 95 |
| enhancing-person-re-identification-via | 96.2 | 91.0 |
| understanding-image-retrieval-re-ranking-a | 96.11 | 94.65 |
| unsupervised-tracklet-person-re | 69.2 | 46.2 |
| exciting-inhibition-network-for-person | - | 88.75 |
| attention-network-robustification-for-person | 95.8 | 88.7 |
| a-coarse-to-fine-pyramidal-model-for-person | 95.7 | 88.2 |
| a-strong-baseline-and-batch-normalization | - | 88.2 |
| aggregating-deep-pyramidal-representations | 94.6 | 91.4 |
| ca-jaccard-camera-aware-jaccard-distance-for | 96.2 | 94.5 |
| viewpoint-aware-loss-with-angular | 96.79 | 95.43 |
| circle-loss-a-unified-perspective-of-pair | 94.2 | 84.9 |
| from-poses-to-identity-training-free-person | 95.52 | 93.01 |
| top-db-net-top-dropblock-for-activation | 94.9 | 85.8 |
| 3d-magic-mirror-clothing-reconstruction-from | 95.43 | 88.54 |
| learning-diverse-features-with-part-level | 95.6 | 88.9 |
| resource-aware-person-re-identification | 90.9 | 86.7 |
| an-effective-data-augmentation-for-person-re | 96.9 | 95.6 |
| graph-based-person-signature-for-person-re | 95.2 | 87.8 |
| fpb-feature-pyramid-branch-for-person-re | 96.1 | 90.6 |
| alignedreid-surpassing-human-level | 94.4 | 90.7 |
| re-ranking-person-re-identification-with-k | 77.11 | 63.63 |
| devil-s-in-the-detail-graph-based-key-point | 95.96 | 90.30 |
| person-re-identification-in-the-3d-space | 87.74 | 69.52 |
| unsupervised-pre-training-for-person-re | 97 | 92 |
| disassembling-the-dataset-a-camera-alignment | 91.3 | 77.3 |
| transreid-transformer-based-object-re | 95.2 | 89.5 |
| in-defense-of-the-triplet-loss-for-person-re | 86.67 | 81.07 |
| learning-a-discriminative-null-space-for | 61.02 | 35.68 |
| plip-language-image-pre-training-for-person | - | 91.2 |
| person-re-identification-by-deep-joint | 85.1 | 65.5 |
| person-re-identification-with-deep-similarity | - | 82.8 |
| flipreid-closing-the-gap-between-training-and | 95.8 | 94.7 |
| scalable-person-re-identification-on | 82.21 | 68.80 |
| glad-global-local-alignment-descriptor-for | 89.9 | 73.9 |
| scalable-metric-learning-via-weighted | 45.16 | - |
| learning-to-disentangle-scenes-for-person-re | 96.17 | 94.89 |
| beyond-part-models-person-retrieval-with | 93.8 | 81.6 |
| lightweight-multi-branch-network-for-person | - | - |
| person-re-identification-by-local-maximal | 43.79 | 22.22 |
| aggregating-deep-pyramidal-representations | 95.2 | 86.7 |
| unlabeled-samples-generated-by-gan-improve | 83.97 | 66.07 |
| multi-task-learning-with-coarse-priors-for | 96.4 | 90.1 |
| aggregating-deep-pyramidal-representations | 96.1 | 94.0 |
| improved-person-re-identification-based-on | 92.5 | 80.1 |
| unsupervised-pre-training-for-person-re | - | 96.21 |
| pose-driven-deep-convolutional-model-for | 84.14 | 63.41 |
| large-scale-pre-training-for-person-re | 96.6 | 91.9 |
| pedestrian-alignment-network-for-large-scale | 88.57 | 81.53 |
| deeply-learned-part-aligned-representations | 81.0 | 63.4 |
| identity-guided-human-semantic-parsing-for | 95.3 | 88.6 |
| unsupervised-person-re-identification | 44.7 | 20.1 |
| Modell 84 | 95.64 | 88.75 |
| deep-constrained-dominant-sets-for-person-re | 95.4 | 93.3 |
| person-re-identification-via-attention | 96.2 | 90.5 |
| learning-disentangled-representation-for | 95.2 | 87.1 |
| adaptivereid-adaptive-l2-regularization-in | 95.6 | 88.9 |
| flipreid-closing-the-gap-between-training-and | 95.5 | 89.6 |
| body-part-based-representation-learning-for | 96.4 | 95.3 |
| cross-view-asymmetric-metric-learning-for | 54.5 | 26.3 |
| features-for-multi-target-multi-camera | 89.4 | 75.6 |
| joint-discriminative-and-generative-learning | 94.8 | 86.0 |
| fd-gan-pose-guided-feature-distilling-gan-for | 90.5 | 77.7 |
| keypoint-promptable-re-identification | 96.62 | 93.22 |
| beyond-part-models-person-retrieval-with | 92.3 | 77.4 |
| bags-of-tricks-and-a-strong-baseline-for-deep | 95.43 | 94.24 |
| attention-network-robustification-for-person | 96.2 | 89.7 |
| joint-discriminative-and-generative-learning | 95.4 | 92.49 |
| lightweight-multi-branch-network-for-person | 96.8 | 95.3 |
| a-discriminatively-learned-cnn-embedding-for | 79.51 | 59.87 |
| lightweight-multi-branch-network-for-person | 96.3 | 91.5 |
| unsupervised-person-re-identification-by-soft | 67.7 | 40 |
| person-re-identification-with-bias-controlled | 93.1 | 89.3 |
| beyond-appearance-a-semantic-controllable | 96.7 | 95.6 |
| deep-miner-a-deep-and-multi-branch-network | 95.7 | 90.40 |
| git-graph-interactive-transformer-for-vehicle | 95.7 | 88.9 |
| in-defense-of-the-triplet-loss-for-person-re | 84.59 | 75.62 |
| abd-net-attentive-but-diverse-person-re | 95.6 | 88.28 |
| improved-person-re-identification-based-on | 93.7 | 90.8 |
| beyond-appearance-a-semantic-controllable | 96.9 | 93.9 |
| camera-aware-proxies-for-unsupervised-person | 93.3 | 85.1 |
| adaptivereid-adaptive-l2-regularization-in | 96.0 | 94.4 |
| rethinking-person-re-identification-from-a | 96 | 90.2 |
| in-defense-of-the-triplet-loss-for-person-re | 84.92 | 69.14 |
| remix-training-generalized-person-re | 96.2 | 89.8 |
| learning-instance-level-spatial-temporal | - | 90.8 |
| self-supervised-pre-training-for-transformer | 96.7 | 93.2 |
| towards-better-validity-dispersion-based | - | 41.3 |
| parameter-free-spatial-attention-network-for | 94.7 | 91.7 |
| incremental-learning-in-person-re | 89.3 | 71.8 |
| camera-style-adaptation-for-person-re | 89.49 | 71.55 |
| scalable-person-re-identification-a-benchmark | 34.40 | 14.09 |
| svdnet-for-pedestrian-retrieval | 82.3 | 62.1 |
| attrimeter-an-attribute-guided-metric | 96.1 | 88.8 |
| attention-network-robustification-for-person | 96.2 | - |
| prototypical-contrastive-learning-based-clip | 95.9 | 91.4 |
| from-poses-to-identity-training-free-person | 97.3 | 94.9 |
| clip-reid-exploiting-vision-language-model | 95.4 | 90.5 |
| enhancing-person-re-identification-via | 97 | 94.9 |
| 3d-magic-mirror-clothing-reconstruction-from | 95.07 | 87.80 |
| semi-supervised-domain-generalizable-person | 97.36 | 94.15 |
| spatial-temporal-person-re-identification | 98.0 | 95.5 |
| template-aware-transformer-for-person | 95.8 | 89.7 |
| learning-deep-context-aware-features-over | 80.31 | 57.53 |