Related papers: High-Performance Transformer Tracking
In this paper, we consider the problem of long-term point tracking, which requires consistent identification of points across multiple frames in a video, despite changes in appearance, lighting, perspective, and occlusions. We target online…
Recently, correlation filter-based trackers have received extensive attention due to their simplicity and superior speed. However, such trackers perform poorly when the target undergoes occlusion, viewpoint change or other challenging…
Transformer is a powerful architecture that achieves superior performance on various sequence learning tasks, including neural machine translation, language understanding, and sequence prediction. At the core of the Transformer is the…
In the same vein of discriminative one-shot learning, Siamese networks allow recognizing an object from a single exemplar with the same class label. However, they do not take advantage of the underlying structure of the data and the…
During the recent years, correlation filters have shown dominant and spectacular results for visual object tracking. The types of the features that are employed in these family of trackers significantly affect the performance of visual…
Sensor fusion is an essential topic in many perception systems, such as autonomous driving and robotics. Transformers-based detection head and CNN-based feature encoder to extract features from raw sensor-data has emerged as one of the best…
State-of-the-art results on neural machine translation often use attentional sequence-to-sequence models with some form of convolution or recursion. Vaswani et al. (2017) propose a new architecture that avoids recurrence and convolution…
Distributed radar sensors enable robust human activity recognition. However, scaling the number of coordinated nodes introduces challenges in feature extraction from large datasets, and transparent data fusion. We propose an end-to-end…
Visual tracking plays an important role in perception system, which is a crucial part of intelligent transportation. Recently, Siamese network is a hot topic for visual tracking to estimate moving targets' trajectory, due to its superior…
Over the past few decades, the hydrology community has witnessed notable advancements in streamflow prediction, particularly with the introduction of cutting-edge machine-learning algorithms. Recurrent neural networks, especially Long…
LiDAR-based 3D single object tracking is a challenging issue in robotics and autonomous driving. Currently, existing approaches usually suffer from the problem that objects at long distance often have very sparse or partially-occluded point…
Existing Transformer-based RGBT tracking methods either use cross-attention to fuse the two modalities, or use self-attention and cross-attention to model both modality-specific and modality-sharing information. However, the significant…
Siamese trackers based on 3D region proposal network (RPN) have shown remarkable success with deep Hough voting. However, using a single seed point feature as the cue for voting fails to produce high-quality 3D proposals. Additionally, the…
One-shot object detection aims at detecting novel objects according to merely one given instance. With extreme data scarcity, current approaches explore various feature fusions to obtain directly transferable meta-knowledge. Yet, their…
The challenging task of multi-object tracking (MOT) requires simultaneous reasoning about track initialization, identity, and spatio-temporal trajectories. We formulate this task as a frame-to-frame set prediction problem and introduce…
Siamese trackers turn tracking into similarity estimation between a template and the candidate regions in the frame. Mathematically, one of the key ingredients of success of the similarity function is translation equivariance.…
Object Detection with Transformers (DETR) and related works reach or even surpass the highly-optimized Faster-RCNN baseline with self-attention network architectures. Inspired by the evidence that pure self-attention possesses a strong…
Multi-Object Tracking (MOT) aims to detect and associate all targets of given classes across frames. Current dominant solutions, e.g. ByteTrack and StrongSORT++, follow the hybrid pipeline, which first accomplish most of the associations in…
In this paper, we provide an intuitive viewing to simplify the Siamese-based trackers by converting the tracking task to a classification. Under this viewing, we perform an in-depth analysis for them through visual simulations and real…
Transformer-based methods have achieved remarkable results in image super-resolution tasks because they can capture non-local dependencies in low-quality input images. However, this feature-intensive modeling approach is computationally…