Search alternatives:
tracking algorithm » tracking algorithms (Expand Search), training algorithms (Expand Search), making algorithm (Expand Search)
based algorithms » based algorithm (Expand Search)
update algorithm » pass algorithm (Expand Search), data algorithms (Expand Search), ipca algorithm (Expand Search)
element update » element data (Expand Search)
data tracking » path tracking (Expand Search), data backing (Expand Search), uav tracking (Expand Search)
develop based » developed based (Expand Search), develop masld (Expand Search), development based (Expand Search)
Showing 1 - 20 results of 4,874 for search '(( data tracking algorithm ) OR ((( develop based algorithms ) OR ( element update algorithm ))))', query time: 0.58s Refine Results
  1. 1
    Assignment of Hungarian Algorithm.

    Assignment of Hungarian Algorithm. by Yibin Zhang (1426579)

    Published 2025
    “…In this paper, a new tracking mechanism is proposed for real-time tracking, which is based on the 2D LiDAR data structure with the Simple Online and Real-Time Tracking (SORT) algorithm. …”
    Save to List
    Saved in:
  2. 2
    Visual representation of how Cell-TRACTR uses track queries to track cells and detect divisions.

    Visual representation of how Cell-TRACTR uses track queries to track cells and detect divisions. by Owen M. O’Connor (11965460)

    Published 2025
    Subjects:
    Save to List
    Saved in:
  3. 3
    Supporting data for “Developing algorithms to optimize recommender system for self-regulated learning promotion in online contexts: a design-based study”

    Supporting data for “Developing algorithms to optimize recommender system for self-regulated learning promotion in online contexts: a design-based study” by Long Zhang (11129139)

    Published 2025
    Save to List
    Saved in:
  4. 4
    Cell-TRACTR detects cells in the first frame at time t 0. Object queries predicted to be a “cell” are converted to track queries. For Track Group Denoising (TGD), random noise is added to the track queries to get noised track queries. For Query Denoising (QD), random noise is added to the ground truth bounding boxes to generate noised track queries. All queries are processed together by the decoder. Attention masks are used to prevent information leakage between the object and track queries, the noised track queries generated from TGD, and the noised track queries generated from QD. The gray boxes indicate information being blocked between sets of queries while colored boxes indicate the flow of information.

    Cell-TRACTR detects cells in the first frame at time t 0. Object queries predicted to be a “cell” are converted to track queries. For Track Group Denoising (TGD), random noise is a... by Owen M. O’Connor (11965460)

    Published 2025
    Subjects:
    Save to List
    Saved in:
  5. 5
    Cells are initially detected in frame t<sub>0</sub> and then tracked to frame t<sub>1</sub>. Object queries are processed in the first layer of the decoder for object detection. In the subsequent decoder layers, track queries are concatenated with the object queries to perform tracking.

    Cells are initially detected in frame t<sub>0</sub> and then tracked to frame t<sub>1</sub>. Object queries are processed in the first layer of the decoder for object detection. In... by Owen M. O’Connor (11965460)

    Published 2025
    Subjects:
    Save to List
    Saved in:
  6. 6
    Overall framework of our proposed tracking algorithm.

    Overall framework of our proposed tracking algorithm. by Yi Tao (178829)

    Published 2025
    Save to List
    Saved in:
  7. 7
    Tracking in challenging conditions.

    Tracking in challenging conditions. by Weheliye H. Weheliye (22022140)

    Published 2025
    Subjects:
    Save to List
    Saved in:
  8. 8
    Excerpts from the raw acquired data set with the tracking algorithm.

    Excerpts from the raw acquired data set with the tracking algorithm. by Hannes Benecke (17409369)

    Published 2025
    Save to List
    Saved in:
  9. 9
    Visualization of tracking results of SiamFC_TDA algorithm and comparison algorithm on challenging sequences.

    Visualization of tracking results of SiamFC_TDA algorithm and comparison algorithm on challenging sequences. by Yi Tao (178829)

    Published 2025
    Save to List
    Saved in:
  10. 10
    Performance of the proposed tracking algorithm and comparison algorithms in three datasets. The higher the metrics, the better.

    Performance of the proposed tracking algorithm and comparison algorithms in three datasets. The higher the metrics, the better. by Yi Tao (178829)

    Published 2025
    Save to List
    Saved in:
  11. 11
    Time-lapse microscopy movie from the bacterial mother machine test set processed by Cell-TRACTR.

    Time-lapse microscopy movie from the bacterial mother machine test set processed by Cell-TRACTR. by Owen M. O’Connor (11965460)

    Published 2025
    Subjects:
    Save to List
    Saved in:
  12. 12
    Example illustrating how object and track queries interact using an attention map processed by Cell-TRACTR across two subsequent frames. The schematic displays the actual output alongside the output the from top matching object queries. Extracted from the self-attention mechanism in the decoder, the attention map highlights the strength of interactions among the queries. Lighter colors indicate stronger interactions. The track queries tend to focus on themselves, while the object queries attend to the track query that corresponds most closely in location.

    Example illustrating how object and track queries interact using an attention map processed by Cell-TRACTR across two subsequent frames. The schematic displays the actual output al... by Owen M. O’Connor (11965460)

    Published 2025
    Subjects:
    Save to List
    Saved in:
  13. 13
    (A) Example illustrating the correlation between the final prediction of an object query and where the object query is derived from within the multi-scale features. Colored pixels represent multi-scale features that were classified as “cell” by the decoder. Black pixels represent multi-scale feature pixels that were classified as “no object” by the decoder. The colored pixels are overlaid onto the phase contrast image for visualization purposes. (B) A more complex example illustrating the correlation between the multi-scale features and object queries.

    (A) Example illustrating the correlation between the final prediction of an object query and where the object query is derived from within the multi-scale features. Colored pixels... by Owen M. O’Connor (11965460)

    Published 2025
    Subjects:
    Save to List
    Saved in:
  14. 14
    Heatmap illustrating which multi-scale feature pixels were classified as “cell” by query selection. This data was collected by processing the full test set for the DeepCell dataset. Note that for these movies, Cell-TRACTR preferentially uses pixels from the highest resolution multi-scale features.

    Heatmap illustrating which multi-scale feature pixels were classified as “cell” by query selection. This data was collected by processing the full test set for the DeepCell dataset... by Owen M. O’Connor (11965460)

    Published 2025
    Subjects:
    Save to List
    Saved in:
  15. 15
    The encoder employs deformable self-attention to transform multi-scale features into encoded multi-scale features. Query selection is used to derive the object queries from these encoded multi-scale features. Each encoded image feature undergoes classification, and the top-K features are selected as the content embeddings for the object queries. Additionally, bounding boxes are extracted from the top-K segmentation masks and are subsequently converted into positional embeddings. Following this, the object queries perform self-attention and deformable cross-attention with the encoded multi-scale features to produce the output embeddings. MLP, multi-layer perceptron.

    The encoder employs deformable self-attention to transform multi-scale features into encoded multi-scale features. Query selection is used to derive the object queries from these e... by Owen M. O’Connor (11965460)

    Published 2025
    Subjects:
    Save to List
    Saved in:
  16. 16
    Schematic demonstrating how Cell-TRACTR tracks cells post-division. The dark blue cell at time t<sub>1</sub> is predicted to divide at time t<sub>2</sub>. The content embedding is duplicated for both divided cells. The positional embeddings are generated from each divided cell’s segmentation mask. The content embeddings are shown as squares and the positional embeddings are circles.

    Schematic demonstrating how Cell-TRACTR tracks cells post-division. The dark blue cell at time t<sub>1</sub> is predicted to divide at time t<sub>2</sub>. The content embedding is... by Owen M. O’Connor (11965460)

    Published 2025
    Subjects:
    Save to List
    Saved in:
  17. 17
    Heatmap illustrating which multi-scale feature pixels were classified as “cell” by query selection. This data was collected by processing the full test set containing 29 movies from the bacterial mother machine dataset with Cell-TRACTR. Note that for these movies, the model preferentially uses pixels from the lowest resolution multi-scale features. The black pixel at the top corresponds to the top of the mother machine image where there are not usually cells.

    Heatmap illustrating which multi-scale feature pixels were classified as “cell” by query selection. This data was collected by processing the full test set containing 29 movies fro... by Owen M. O’Connor (11965460)

    Published 2025
    Subjects:
    Save to List
    Saved in:
  18. 18
    Depiction of how predictions are made from the output embeddings. The largest encoded multi-scale feature map is resized and combined with the original multi-scale features to form the pixel embedding map. The dot product of the output embeddings and the pixel embedding map produces the segmentation masks. A linear layer is used to predict the class label and a multi-layer perceptron (MLP) is used to generate the bounding box. For output embeddings classified as “no object”, the bounding boxes and segmentation masks are ignored.

    Depiction of how predictions are made from the output embeddings. The largest encoded multi-scale feature map is resized and combined with the original multi-scale features to form... by Owen M. O’Connor (11965460)

    Published 2025
    Subjects:
    Save to List
    Saved in:
  19. 19
    Effect of segmentation mask resolution on CUDA memory usage and performance metrics. (A) Memory usage as a function of queries when Cell-TRACTR produces a segmentation mask with the same resolution as the original image. (B) 1/4 Cell-TRACTR produces a segmentation mask with one-fourth the resolution of the input image.

    Effect of segmentation mask resolution on CUDA memory usage and performance metrics. (A) Memory usage as a function of queries when Cell-TRACTR produces a segmentation mask with th... by Owen M. O’Connor (11965460)

    Published 2025
    Subjects:
    Save to List
    Saved in:
  20. 20
    Diagram illustrating how the iterative bounding box refinement method works with cell divisions. When tracking the cell from t<sub>0</sub> to t<sub>1</sub>, the bounding box from t<sub>0</sub> serves as the initial bounding box that is iteratively refined three times into a bounding box that locates the cell in t<sub>1</sub>. The second bounding box is ignored here since cell division is not predicted at time t<sub>1</sub>. This method consists of predicting a relative offset with respect to the previous bounding box, represented by a chang

    Diagram illustrating how the iterative bounding box refinement method works with cell divisions. When tracking the cell from t<sub>0</sub> to t<sub>1</sub>, the bounding box from t... by Owen M. O’Connor (11965460)

    Published 2025
    Subjects:
    Save to List
    Saved in:

Search Tools: