Track Anything: Segment Anything Meets Videos
Paper • 2304.11968 • Published
YAML Metadata Warning:The pipeline tag "video-object-tracking" is not in the official list: text-classification, token-classification, table-question-answering, question-answering, zero-shot-classification, translation, summarization, feature-extraction, text-generation, fill-mask, sentence-similarity, text-to-speech, text-to-audio, automatic-speech-recognition, audio-to-audio, audio-classification, audio-text-to-text, voice-activity-detection, depth-estimation, image-classification, object-detection, image-segmentation, text-to-image, image-to-text, image-to-image, image-to-video, unconditional-image-generation, video-classification, reinforcement-learning, robotics, tabular-classification, tabular-regression, tabular-to-text, table-to-text, multiple-choice, text-ranking, text-retrieval, time-series-forecasting, text-to-video, image-text-to-text, image-text-to-image, image-text-to-video, visual-question-answering, document-question-answering, zero-shot-image-classification, graph-ml, mask-generation, zero-shot-object-detection, text-to-3d, image-to-3d, image-feature-extraction, video-text-to-text, keypoint-detection, visual-document-retrieval, any-to-any, video-to-video, other
Track-Anything: Optimized for Qualcomm Devices
Track-Anything is a video based machine learning model to track an object in a video.
This is based on the implementation of Track-Anything found here. This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the Qualcomm® AI Hub Models library to export with custom configurations. More details on model performance across various devices, can be found here.
Qualcomm AI Hub Models uses Qualcomm AI Hub Workbench to compile, profile, and evaluate this model. Sign up to run these models on a hosted Qualcomm® device.
Getting Started
There are two ways to deploy this model on your device:
Option 1: Download Pre-Exported Models
Below are pre-exported model assets ready for deployment.
| Runtime | Precision | Chipset | SDK Versions | Download |
|---|---|---|---|---|
| ONNX | float | Universal | QAIRT 2.42, ONNX Runtime 1.24.1 | Download |
| TFLITE | float | Universal | QAIRT 2.43, TFLite 2.17.0 | Download |
For more device-specific assets and performance metrics, visit Track-Anything on Qualcomm® AI Hub.
Option 2: Export with Custom Configurations
Use the Qualcomm® AI Hub Models Python library to compile and export the model with your own:
- Custom weights (e.g., fine-tuned checkpoints)
- Custom input shapes
- Target device and runtime configurations
This option is ideal if you need to customize the model beyond the default configuration provided here.
See our repository for Track-Anything on GitHub for usage instructions.
Model Details
Model Type: Model_use_case.video_object_tracking
Model Stats:
- Model checkpoint: xmem
- Input resolution: 320x568
- Number of parameters (TrackAnythingEncodeKeyWithShrinkage): 9.72M
- Model size (TrackAnythingEncodeKeyWithShrinkage) (float): 37.1 MB
- Number of parameters (TrackAnythingEncodeValue): 23.3M
- Model size (TrackAnythingEncodeValue) (float): 88.8 MB
- Number of parameters (TrackAnythingEncodeKeyWithoutShrinkage): 9.71M
- Model size (TrackAnythingEncodeKeyWithoutShrinkage) (float): 37.1 MB
- Number of parameters (TrackAnythingSegment): 30.1M
- Model size (TrackAnythingSegment) (float): 115 MB
Performance Summary
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit |
|---|---|---|---|---|---|---|
| TrackAnythingEncodeKeyWithShrinkage | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.384 ms | 1 - 177 MB | NPU |
| TrackAnythingEncodeKeyWithShrinkage | ONNX | float | Snapdragon® X2 Elite | 2.813 ms | 18 - 18 MB | NPU |
| TrackAnythingEncodeKeyWithShrinkage | ONNX | float | Snapdragon® X Elite | 5.608 ms | 19 - 19 MB | NPU |
| TrackAnythingEncodeKeyWithShrinkage | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 3.664 ms | 0 - 202 MB | NPU |
| TrackAnythingEncodeKeyWithShrinkage | ONNX | float | Qualcomm® QCS8550 (Proxy) | 5.166 ms | 0 - 21 MB | NPU |
| TrackAnythingEncodeKeyWithShrinkage | ONNX | float | Qualcomm® QCS9075 | 9.464 ms | 10 - 13 MB | NPU |
| TrackAnythingEncodeKeyWithShrinkage | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 2.948 ms | 1 - 166 MB | NPU |
| TrackAnythingEncodeKeyWithShrinkage | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.441 ms | 0 - 191 MB | NPU |
| TrackAnythingEncodeKeyWithShrinkage | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 4.085 ms | 1 - 213 MB | NPU |
| TrackAnythingEncodeKeyWithShrinkage | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 31.167 ms | 3 - 180 MB | NPU |
| TrackAnythingEncodeKeyWithShrinkage | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 5.935 ms | 3 - 6 MB | NPU |
| TrackAnythingEncodeKeyWithShrinkage | TFLITE | float | Qualcomm® SA8775P | 9.553 ms | 0 - 178 MB | NPU |
| TrackAnythingEncodeKeyWithShrinkage | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 11.742 ms | 3 - 197 MB | NPU |
| TrackAnythingEncodeKeyWithShrinkage | TFLITE | float | Qualcomm® SA7255P | 31.167 ms | 3 - 180 MB | NPU |
| TrackAnythingEncodeKeyWithShrinkage | TFLITE | float | Qualcomm® SA8295P | 10.378 ms | 3 - 165 MB | NPU |
| TrackAnythingEncodeKeyWithShrinkage | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 3.289 ms | 0 - 180 MB | NPU |
| TrackAnythingEncodeKeyWithoutShrinkage | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.494 ms | 1 - 216 MB | NPU |
| TrackAnythingEncodeKeyWithoutShrinkage | ONNX | float | Snapdragon® X2 Elite | 3.947 ms | 65 - 65 MB | NPU |
| TrackAnythingEncodeKeyWithoutShrinkage | ONNX | float | Snapdragon® X Elite | 6.955 ms | 66 - 66 MB | NPU |
| TrackAnythingEncodeKeyWithoutShrinkage | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 5.056 ms | 63 - 271 MB | NPU |
| TrackAnythingEncodeKeyWithoutShrinkage | ONNX | float | Qualcomm® QCS8550 (Proxy) | 6.835 ms | 58 - 77 MB | NPU |
| TrackAnythingEncodeKeyWithoutShrinkage | ONNX | float | Qualcomm® QCS9075 | 11.477 ms | 62 - 64 MB | NPU |
| TrackAnythingEncodeKeyWithoutShrinkage | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 4.361 ms | 61 - 253 MB | NPU |
| TrackAnythingEncodeKeyWithoutShrinkage | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.559 ms | 0 - 226 MB | NPU |
| TrackAnythingEncodeKeyWithoutShrinkage | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 5.373 ms | 19 - 241 MB | NPU |
| TrackAnythingEncodeKeyWithoutShrinkage | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 33.113 ms | 9 - 193 MB | NPU |
| TrackAnythingEncodeKeyWithoutShrinkage | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 7.509 ms | 20 - 23 MB | NPU |
| TrackAnythingEncodeKeyWithoutShrinkage | TFLITE | float | Qualcomm® SA8775P | 11.353 ms | 20 - 206 MB | NPU |
| TrackAnythingEncodeKeyWithoutShrinkage | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 14.098 ms | 20 - 222 MB | NPU |
| TrackAnythingEncodeKeyWithoutShrinkage | TFLITE | float | Qualcomm® SA7255P | 33.113 ms | 9 - 193 MB | NPU |
| TrackAnythingEncodeKeyWithoutShrinkage | TFLITE | float | Qualcomm® SA8295P | 12.71 ms | 20 - 186 MB | NPU |
| TrackAnythingEncodeKeyWithoutShrinkage | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 4.413 ms | 18 - 209 MB | NPU |
| TrackAnythingEncodeValue | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 6.596 ms | 0 - 166 MB | NPU |
| TrackAnythingEncodeValue | ONNX | float | Snapdragon® X2 Elite | 6.023 ms | 39 - 39 MB | NPU |
| TrackAnythingEncodeValue | ONNX | float | Snapdragon® X Elite | 12.457 ms | 38 - 38 MB | NPU |
| TrackAnythingEncodeValue | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 9.879 ms | 12 - 220 MB | NPU |
| TrackAnythingEncodeValue | ONNX | float | Qualcomm® QCS8550 (Proxy) | 15.632 ms | 0 - 45 MB | NPU |
| TrackAnythingEncodeValue | ONNX | float | Qualcomm® QCS9075 | 18.755 ms | 6 - 14 MB | NPU |
| TrackAnythingEncodeValue | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 8.398 ms | 7 - 175 MB | NPU |
| TrackAnythingEncodeValue | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 6.27 ms | 1 - 209 MB | NPU |
| TrackAnythingEncodeValue | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 8.318 ms | 3 - 293 MB | NPU |
| TrackAnythingEncodeValue | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 51.385 ms | 3 - 225 MB | NPU |
| TrackAnythingEncodeValue | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 11.877 ms | 3 - 6 MB | NPU |
| TrackAnythingEncodeValue | TFLITE | float | Qualcomm® SA8775P | 17.446 ms | 3 - 220 MB | NPU |
| TrackAnythingEncodeValue | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 22.471 ms | 3 - 286 MB | NPU |
| TrackAnythingEncodeValue | TFLITE | float | Qualcomm® SA7255P | 51.385 ms | 3 - 225 MB | NPU |
| TrackAnythingEncodeValue | TFLITE | float | Qualcomm® SA8295P | 19.759 ms | 3 - 233 MB | NPU |
| TrackAnythingEncodeValue | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 7.187 ms | 2 - 203 MB | NPU |
| TrackAnythingSegment | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 10.468 ms | 8 - 221 MB | NPU |
| TrackAnythingSegment | ONNX | float | Snapdragon® X2 Elite | 11.788 ms | 38 - 38 MB | NPU |
| TrackAnythingSegment | ONNX | float | Snapdragon® X Elite | 23.51 ms | 37 - 37 MB | NPU |
| TrackAnythingSegment | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 17.508 ms | 0 - 241 MB | NPU |
| TrackAnythingSegment | ONNX | float | Qualcomm® QCS8550 (Proxy) | 23.222 ms | 0 - 45 MB | NPU |
| TrackAnythingSegment | ONNX | float | Qualcomm® QCS9075 | 39.325 ms | 21 - 45 MB | NPU |
| TrackAnythingSegment | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 13.838 ms | 5 - 221 MB | NPU |
| TrackAnythingSegment | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 10.8 ms | 0 - 227 MB | NPU |
| TrackAnythingSegment | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 17.715 ms | 0 - 288 MB | NPU |
| TrackAnythingSegment | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 103.692 ms | 2 - 197 MB | NPU |
| TrackAnythingSegment | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 23.394 ms | 2 - 4 MB | NPU |
| TrackAnythingSegment | TFLITE | float | Qualcomm® SA8775P | 33.678 ms | 2 - 202 MB | NPU |
| TrackAnythingSegment | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 54.382 ms | 2 - 286 MB | NPU |
| TrackAnythingSegment | TFLITE | float | Qualcomm® SA7255P | 103.692 ms | 2 - 197 MB | NPU |
| TrackAnythingSegment | TFLITE | float | Qualcomm® SA8295P | 38.758 ms | 2 - 210 MB | NPU |
| TrackAnythingSegment | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 13.3 ms | 1 - 206 MB | NPU |
License
- The license for the original implementation of Track-Anything can be found here.
References
Community
- Join our AI Hub Slack community to collaborate, post questions and learn more about on-device AI.
- For questions or feedback please reach out to us.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support