Related papers: TrackFormer: Multi-Object Tracking with Transforme…
Detection Transformers represent end-to-end object detection approaches based on a Transformer encoder-decoder architecture, exploiting the attention mechanism for global relation modeling. Although Detection Transformers deliver results on…
In video transformers, the time dimension is often treated in the same way as the two spatial dimensions. However, in a scene where objects or the camera may move, a physical point imaged at one location in frame $t$ may be entirely…
In applications such as object tracking, time-series data inevitably carry missing observations. Following the success of deep learning-based models for various sequence learning tasks, these models increasingly replace classic approaches…
Graphs offer a natural way to formulate Multiple Object Tracking (MOT) within the tracking-by-detection paradigm. However, they also introduce a major challenge for learning methods, as defining a model that can operate on such…
Despite the success of many advanced tracking methods in this area, tracking targets with drastic variation of appearance such as deformation, view change and partial occlusion in video sequences is still a challenge in practical…
Graphs offer a natural way to formulate Multiple Object Tracking (MOT) and Multiple Object Tracking and Segmentation (MOTS) within the tracking-by-detection paradigm. However, they also introduce a major challenge for learning methods, as…
Predicting trajectories of pedestrians based on goal information in highly interactive scenes is a crucial step toward Intelligent Transportation Systems and Autonomous Driving. The challenges of this task come from two key sources: (1)…
Different from existing MOT (Multi-Object Tracking) techniques that usually aim at improving tracking accuracy and average FPS, real-time systems such as autonomous vehicles necessitate new requirements of MOT under limited computing…
State-of-the-art multi-object tracking~(MOT) methods follow the tracking-by-detection paradigm, where object trajectories are obtained by associating per-frame outputs of object detectors. In crowded scenes, however, detectors often fail to…
Transformer architecture has been showing its great strength in visual object tracking, for its effective attention mechanism. Existing transformer-based approaches adopt the pixel-to-pixel attention strategy on flattened image features and…
Continual learning allows a model to learn multiple tasks sequentially while retaining the old knowledge without the training data of the preceding tasks. This paper extends the scope of continual learning research to class-incremental…
Multiple Object Tracking (MOT) has rapidly progressed in recent years. Existing works tend to design a single tracking algorithm to perform both detection and association. Though ensemble learning has been exploited in many tasks, i.e,…
3D Multi-Object Tracking (MOT) provides the trajectories of surrounding objects, assisting robots or vehicles in smarter path planning and obstacle avoidance. Existing 3D MOT methods based on the Tracking-by-Detection framework typically…
We propose the task Future Object Detection, in which the goal is to predict the bounding boxes for all visible objects in a future video frame. While this task involves recognizing temporal and kinematic patterns, in addition to the…
The DEtection TRansformer (DETR) opened new possibilities for object detection by modeling it as a translation task: converting image features into object-level representations. Previous works typically add expensive modules to DETR to…
Multi-object tracking (MOT) is a core task in computer vision that involves detecting objects in video frames and associating them across time. The rise of deep learning has significantly advanced MOT, particularly within the…
There exists no comprehensive metric for describing the complexity of Multi-Object Tracking (MOT) sequences. This lack of metrics decreases explainability, complicates comparison of datasets, and reduces the conversation on tracker…
Joint Detection and Embedding (JDE) trackers have demonstrated excellent performance in Multi-Object Tracking (MOT) tasks by incorporating the extraction of appearance features as auxiliary tasks through embedding Re-Identification task…
In unknown cluttered and dynamic environments such as disaster scenes, mobile robots need to perform target-driven navigation in order to find people or objects of interest, while being solely guided by images of the targets. In this paper,…
Recent approaches for high accuracy detection and tracking of object categories in video consist of complex multistage solutions that become more cumbersome each year. In this paper we propose a ConvNet architecture that jointly performs…