Related papers: High-Performance Transformer Tracking
Aiming at the limitation that deep long and short-term memory network(DLSTM) algorithm cannot perform parallel computing and cannot obtain global information, in this paper, feature extraction and feature processing are firstly carried out…
Multimodal object detection leverages diverse modal information to enhance the accuracy and robustness of detectors. By learning long-term dependencies, Transformer can effectively integrate multimodal features in the feature extraction…
While the Transformer architecture has become ubiquitous in the machine learning field, its adaptation to 3D shape recognition is non-trivial. Due to its quadratic computational complexity, the self-attention operator quickly becomes…
Traditional multiple object tracking methods divide the task into two parts: affinity learning and data association. The separation of the task requires to define a hand-crafted training goal in affinity learning stage and a hand-crafted…
Multi-modal fusion is proven to be an effective method to improve the accuracy and robustness of speaker tracking, especially in complex scenarios. However, how to combine the heterogeneous information and exploit the complementarity of…
Siamese tracking has achieved groundbreaking performance in recent years, where the essence is the efficient matching operator cross-correlation and its variants. Besides the remarkable success, it is important to note that the heuristic…
Semantic segmentation is one of the core tasks in the field of computer vision, and its goal is to accurately classify each pixel in an image. The traditional Unet model achieves efficient feature extraction and fusion through an…
The ability to learn robust multi-modality representation has played a critical role in the development of RGBT tracking. However, the regular fusion paradigm and the invariable tracking template remain restrictive to the feature…
Transformer-based multi-object tracking (MOT) methods have captured the attention of many researchers in recent years. However, these models often suffer from slow inference speeds due to their structure or other issues. To address this…
Transformers have attracted increasing interests in computer vision, but they still fall behind state-of-the-art convolutional networks. In this work, we show that while Transformers tend to have larger model capacity, their generalization…
Sparse attention methods exploit the inherent sparsity in attention to speed up the prefilling phase of long-context inference, mitigating the quadratic complexity of full attention computation. While existing sparse attention methods rely…
In the recent literature, on the one hand, many 3D multi-object tracking (MOT) works have focused on tracking accuracy and neglected computation speed, commonly by designing rather complex cost functions and feature extractors. On the other…
Attention-based models, exemplified by the Transformer, can effectively model long range dependency, but suffer from the quadratic complexity of self-attention operation, making them difficult to be adopted for high-resolution image…
Processing 3D data efficiently has always been a challenge. Spatial operations on large-scale point clouds, stored as sparse data, require extra cost. Attracted by the success of transformers, researchers are using multi-head attention for…
Existing deep trackers mainly use convolutional neural networks pre-trained for generic object recognition task for representations. Despite demonstrated successes for numerous vision tasks, the contributions of using pre-trained deep…
Though U-Net has achieved tremendous success in medical image segmentation tasks, it lacks the ability to explicitly model long-range dependencies. Therefore, Vision Transformers have emerged as alternative segmentation structures recently,…
More powerful feature representations derived from deep neural networks benefit visual tracking algorithms widely. However, the lack of exploitation on temporal information prevents tracking algorithms from adapting to appearances changing…
Object detectors are conventionally trained by a weighted sum of classification and localization losses. Recent studies (e.g., predicting IoU with an auxiliary head, Generalized Focal Loss, Rank & Sort Loss) have shown that forcing these…
Feature tracking is the building block of many applications such as visual odometry, augmented reality, and target tracking. Unfortunately, the state-of-the-art vision-based tracking algorithms fail in surgical images due to the challenges…
This thesis examines self-attention training through the lens of Optimal Transport (OT) and develops an OT-based alternative for tabular classification. The study tracks intermediate projections of the self-attention layer during training…