Related papers: DepthFormer: Multimodal Positional Encodings and C…
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…
Multi-task learning has proven to be effective in improving the performance of correlated tasks. Most of the existing methods use a backbone to extract initial features with independent branches for each task, and the exchange of…
One of the common and promising deep learning approaches used for medical image segmentation is transformers, as they can capture long-range dependencies among the pixels by utilizing self-attention. Despite being successful in medical…
Monocular depth estimation and semantic segmentation are two fundamental goals of scene understanding. Due to the advantages of task interaction, many works study the joint task learning algorithm. However, most existing methods fail to…
Transformer-based models have brought a radical change to neural machine translation. A key feature of the Transformer architecture is the so-called multi-head attention mechanism, which allows the model to focus simultaneously on different…
Multi-frame depth estimation improves over single-frame approaches by also leveraging geometric relationships between images via feature matching, in addition to learning appearance-based features. In this paper we revisit feature matching…
There is a recent trend in the LiDAR perception field towards unifying multiple tasks in a single strong network with improved performance, as opposed to using separate networks for each task. In this paper, we introduce a new LiDAR…
Understanding user intent is essential for situational and context-aware decision-making. Motivated by a real-world scenario, this work addresses intent predictions of smart device users in the vicinity of vehicles by modeling sequential…
Visual navigation for autonomous agents is a core task in the fields of computer vision and robotics. Learning-based methods, such as deep reinforcement learning, have the potential to outperform the classical solutions developed for this…
Image-based single-modality compression learning approaches have demonstrated exceptionally powerful encoding and decoding capabilities in the past few years , but suffer from blur and severe semantics loss at extremely low bitrates. To…
Depth information which specifies the distance between objects and current position of the robot is essential for many robot tasks such as navigation. Recently, researchers have proposed depth completion frameworks to provide dense depth…
Recent studies have demonstrated the effectiveness of position encoding in transformer architectures. By incorporating positional information, this approach provides essential guidance for modeling dependencies between elements across…
The fusion of images taken by heterogeneous sensors helps to enrich the information and improve the quality of imaging. In this article, we present a hybrid model consisting of a convolutional encoder and a Transformer-based decoder to fuse…
Transformers have made great progress in dealing with computer vision tasks. However, existing vision transformers do not yet possess the ability of building the interactions among features of different scales, which is perceptually…
Point cloud processing methods leverage local and global point features %at the feature level to cater to downstream tasks, yet they often overlook the task-level context inherent in point clouds during the encoding stage. We argue that…
Driver intention prediction seeks to anticipate drivers' actions by analyzing their behaviors with respect to surrounding traffic environments. Existing approaches primarily focus on late-fusion techniques, and neglect the importance of…
Spatial understanding of the semantics of the surroundings is a key capability needed by autonomous cars to enable safe driving decisions. Recently, purely vision-based solutions have gained increasing research interest. In particular,…
Referring image segmentation segments an image from a language expression. With the aim of producing high-quality masks, existing methods often adopt iterative learning approaches that rely on RNNs or stacked attention layers to refine…
Semantic segmentation assigns labels to pixels in images, a critical yet challenging task in computer vision. Convolutional methods, although capturing local dependencies well, struggle with long-range relationships. Vision Transformers…
Deep imitation learning is promising for solving dexterous manipulation tasks because it does not require an environment model and pre-programmed robot behavior. However, its application to dual-arm manipulation tasks remains challenging.…