Related papers: AiATrack: Attention in Attention for Transformer V…
Flight trajectory prediction for multiple aircraft is essential and provides critical insights into how aircraft navigate within current air traffic flows. However, predicting multi-agent flight trajectories is inherently challenging. One…
We propose the notion of Attention-Aware Visualizations (AAVs) that track the user's perception of a visual representation over time and feed this information back to the visualization. Such context awareness is particularly useful for…
Although transformer networks are recently employed in various vision tasks with outperforming performance, extensive training data and a lengthy training time are required to train a model to disregard an inductive bias. Using trainable…
Tracking multiple particles in noisy and cluttered scenes remains challenging due to a combinatorial explosion of trajectory hypotheses, which scales super-exponentially with the number of particles and frames. The transformer architecture…
Tracking specific targets, such as pedestrians and vehicles, has been the focus of recent vision-based multitarget tracking studies. However, in some real-world scenarios, unseen categories often challenge existing methods due to…
Vision Transformers (ViTs) have been shown to enhance visual recognition through modeling long-range dependencies with multi-head self-attention (MHSA), which is typically formulated as Query-Key-Value computation. However, the attention…
Although attention mechanisms have become fundamental components of deep learning models, they are vulnerable to perturbations, which may degrade the prediction performance and model interpretability. Adversarial training (AT) for attention…
Refining visual representations by eliminating their internal feature-level redundancy is crucial for simultaneously optimizing the performance and computational cost of models in visual tracking. To enhance their performance, many…
The self-attention-based model, transformer, is recently becoming the leading backbone in the field of computer vision. In spite of the impressive success made by transformers in a variety of vision tasks, it still suffers from heavy…
The attention mechanism lies at the core of the transformer architecture, providing an interpretable model-internal signal that has motivated a growing interest in attention-based model explanations. Although attention weights do not…
Local Transformer-based classification models have recently achieved promising results with relatively low computational costs. However, the effect of aggregating spatial global information of local Transformer-based architecture is not…
Multiple object tracking (MOT) is the task containing detection and association. Plenty of trackers have achieved competitive performance. Unfortunately, for the lack of informative exchange on these subtasks, they are often biased toward…
In this paper we delve deep in the Transformer architecture by investigating two of its core components: self-attention and contextual embeddings. In particular, we study the identifiability of attention weights and token embeddings, and…
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…
Object tracking based on hyperspectral video attracts increasing attention to the rich material and motion information in the hyperspectral videos. The prevailing hyperspectral methods adapt pretrained RGB-based object tracking networks for…
Although attention mechanisms have been applied to a variety of deep learning models and have been shown to improve the prediction performance, it has been reported to be vulnerable to perturbations to the mechanism. To overcome the…
Transformer-based models have emerged as a leading architecture for natural language processing, natural language generation, and image generation tasks. A fundamental element of the transformer architecture is self-attention, which allows…
The CenterTrack tracking algorithm achieves state-of-the-art tracking performance using a simple detection model and single-frame spatial offsets to localize objects and predict their associations in a single network. However, this joint…
Vision Transformers are very popular nowadays due to their state-of-the-art performance in several computer vision tasks, such as image classification and action recognition. Although their performance has been greatly enhanced through…
We present an attention-based modular neural framework for computer vision. The framework uses a soft attention mechanism allowing models to be trained with gradient descent. It consists of three modules: a recurrent attention module…