Rgb T Tracking On Lasher
Metrics
Precision
Success
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | Precision | Success |
|---|---|---|
| transformer-rgbt-tracking-with-spatio | 67.4 | 53.7 |
| seqtrack-sequence-to-sequence-learning-for | 74.1 | 58.8 |
| 2408-02222 | 70.0 | 55.6 |
| sdstrack-self-distillation-symmetric-adapter | 66.5 | 53.1 |
| from-two-stream-to-one-stream-efficient-rgb-t | 71.4 | 56.7 |
| challenge-aware-rgbt-tracking | 45.0 | 31.4 |
| onetracker-unifying-visual-object-tracking | 67.2 | 53.8 |
| seqtrack-sequence-to-sequence-learning-for | 70.4 | 55.8 |
| prompting-for-multi-modal-tracking | 50.9 | 42.1 |
| Model 10 | 76.2 | 60.7 |
| sutrack-towards-simple-and-unified-single | 76.9 | 61.9 |
| seqtrack-sequence-to-sequence-learning-for | 76.7 | 61.0 |
| rgb-t-tracking-via-multi-modal-mutual-prompt | 72.0 | 57.1 |
| bridging-search-region-interaction-with | 70.2 | 56.5 |
| rgbt-tracking-via-multi-adapter-network-with | 46.7 | 31.4 |
| generative-based-fusion-mechanism-for-multi | 70.7 | 56.6 |
| seqtrack-sequence-to-sequence-learning-for | 71.5 | 56.2 |
| bi-directional-adapter-for-multi-modal | 70.2 | 56.3 |
| single-model-and-any-modality-for-video | 66.7 | 53.6 |
| mambavt-spatio-temporal-contextual-modeling | 72.7 | 57.5 |
| temporal-adaptive-rgbt-tracking-with-modality | 70.2 | 56.1 |
| visual-prompt-multi-modal-tracking | 65.1 | 52.5 |
| middle-fusion-and-multi-stage-multi-form | 67.3 | 54.2 |
| breaking-modality-gap-in-rgbt-tracking | 73.2 | 58.1 |
| exploiting-multimodal-spatial-temporal | 76.0 | 60.3 |
| mambavt-spatio-temporal-contextual-modeling | 73.0 | 57.9 |
| Model 27 | 73.0 | 58.8 |
| duality-gated-mutual-condition-network-for | 49.0 | 35.5 |
| adaptive-perception-for-unified-visual-multi | 74.1 | 58.9 |
| revisiting-rgbt-tracking-benchmarks-from-the | 72.1 | 57.8 |
| cross-fusion-rgb-t-tracking-with-bi | 73.2 | 58.4 |
| attribute-based-progressive-fusion-network | 50.0 | 36.2 |
| after-attention-based-fusion-router-for-rgbt | 70.3 | 55.1 |
| multi-modal-fusion-for-end-to-end-rgb-t | 44.7 | 34.3 |
| transformer-based-rgb-t-tracking-with-channel | 71.5 | 57.2 |
| efficient-rgb-t-tracking-via-cross-modality | 59.0 | 46.6 |