Related papers: Feature Pyramid Transformer
Image matching that finding robust and accurate correspondences across images is a challenging task under extreme conditions. Capturing local and global features simultaneously is an important way to mitigate such an issue but recent…
This paper presents a Refinement Pyramid Transformer (RePFormer) for robust facial landmark detection. Most facial landmark detectors focus on learning representative image features. However, these CNN-based feature representations are not…
As the scale of vision models continues to grow, the emergence of Visual Prompt Tuning (VPT) as a parameter-efficient transfer learning technique has gained attention due to its superior performance compared to traditional full-finetuning.…
Recent state-of-the-art performances of Vision Transformers (ViT) in computer vision tasks demonstrate that a general-purpose architecture, which implements long-range self-attention, could replace the local feature learning operations of…
Incomplete-view computed tomography (CT) can shorten the data acquisition time and allow scanning of large objects, including sparse-view and limited-angle scenarios, each with various settings, such as different view numbers or angular…
Traditional learning from demonstration (LfD) generally demands a cumbersome collection of physical demonstrations, which can be time-consuming and challenging to scale. Recent advances show that robots can instead learn from human videos…
Pedestrian crossing intention prediction is essential for autonomous vehicles to improve pedestrian safety and reduce traffic accidents. However, accurate pedestrian intention prediction in urban environments remains challenging due to the…
Convolutional neural networks (CNNs) and vision transformers (ViTs) have achieved remarkable success in various vision tasks. However, many architectures do not consider interactions between feature maps from different stages and scales,…
Image pyramids are widely adopted in top-performing methods to obtain multi-scale features for precise visual perception and understanding. However, current image pyramids use the same large-scale model to process multiple resolutions of…
Foundation models (FMs) are large neural networks trained on broad datasets, excelling in downstream tasks with minimal fine-tuning. Human activity recognition in video has advanced with FMs, driven by competition among different…
We present Multiscale Vision Transformers (MViT) for video and image recognition, by connecting the seminal idea of multiscale feature hierarchies with transformer models. Multiscale Transformers have several channel-resolution scale…
Foundation models are vital tools in various Computer Vision applications. They take as input a single RGB image and output a deep feature representation that is useful for various applications. However, in case we have multiple views of…
Semantic segmentation in cataract surgery has a wide range of applications contributing to surgical outcome enhancement and clinical risk reduction. However, the varying issues in segmenting the different relevant structures in these…
The dominant multi-camera 3D detection paradigm is based on explicit 3D feature construction, which requires complicated indexing of local image-view features via 3D-to-2D projection. Other methods implicitly introduce geometric positional…
Most of existing RGB-D salient object detection (SOD) methods follow the CNN-based paradigm, which is unable to model long-range dependencies across space and modalities due to the natural locality of CNNs. Here we propose the Hierarchical…
In recent years, attention mechanisms have significantly enhanced the performance of object detection by focusing on key feature information. However, prevalent methods still encounter difficulties in effectively balancing local and global…
Capturing interaction of hands with objects is important to autonomously detect human actions from egocentric videos. In this work, we present a pyramid video transformer with a dynamic class token generator for egocentric action…
Currently, convolutional neural networks (CNN) (e.g., U-Net) have become the de facto standard and attained immense success in medical image segmentation. However, as a downside, CNN based methods are a double-edged sword as they fail to…
Effective point cloud processing is crucial to LiDARbased autonomous driving systems. The capability to understand features at multiple scales is required for object detection of intelligent vehicles, where road users may appear in…
Transformer architectures show spectacular performance on NLP tasks and have recently also been used for tasks such as image completion or image classification. Here we propose to use a sequential image representation, where each prefix of…