相关论文: AdaPerceiver: Transformers with Adaptive Width, De…

Multi-UAV collaborative 3D detection enables accurate and robust perception by fusing multi-view observations from aerial platforms, offering significant advantages in coverage and occlusion handling, while posing new challenges for…

Convolutional neural networks have made significant progresses in edge detection by progressively exploring the context and semantic features. However, local details are gradually suppressed with the enlarging of receptive fields. Recently,…

A key challenge for autonomous driving lies in maintaining real-time situational awareness regarding surrounding obstacles under strict latency constraints. The high processing requirements coupled with limited onboard computational…

We present new algorithms for adaptively learning artificial neural networks. Our algorithms (AdaNet) adaptively learn both the structure of the network and its weights. They are based on a solid theoretical analysis, including…

Vision Transformers (ViTs) deliver state-of-the-art accuracy but their quadratic attention cost and redundant computations severely hinder deployment on latency and resource-constrained platforms. Existing pruning approaches treat either…

This work introduces a novel and adaptable architecture designed for real-time occupancy forecasting that outperforms existing state-of-the-art models on the Waymo Open Motion Dataset in Soft IOU. The proposed model uses recursive latent…

Although convolutional networks (ConvNets) have enjoyed great success in computer vision (CV), it suffers from capturing global information crucial to dense prediction tasks such as object detection and segmentation. In this work, we…

Most popular optimizers for deep learning can be broadly categorized as adaptive methods (e.g. Adam) and accelerated schemes (e.g. stochastic gradient descent (SGD) with momentum). For many models such as convolutional neural networks…

Time series classification is one of the most critical and challenging problems in data mining, existing widely in various fields and holding significant research importance. Despite extensive research and notable achievements with…

Temporal modelling is the key for efficient video action recognition. While understanding temporal information can improve recognition accuracy for dynamic actions, removing temporal redundancy and reusing past features can significantly…

Transformers, known for their attention mechanisms, have proven highly effective in focusing on critical elements within complex data. This feature can effectively be used to address the time-varying channels in wireless communication…

Vision Transformer (ViT) is emerging as the state-of-the-art architecture for image recognition. While recent studies suggest that ViTs are more robust than their convolutional counterparts, our experiments find that ViTs trained on…

Large-scale vision-language pre-trained models have shown promising transferability to various downstream tasks. As the size of these foundation models and the number of downstream tasks grow, the standard full fine-tuning paradigm becomes…

This research presents a novel depth estimation algorithm based on a Transformer-encoder architecture, tailored for the NYU and KITTI Depth Dataset. This research adopts a transformer model, initially renowned for its success in natural…

Single Image Super-Resolution is a classic computer vision problem that involves estimating high-resolution (HR) images from low-resolution (LR) ones. Although deep neural networks (DNNs), especially Transformers for super-resolution, have…

Depth estimation attracts widespread attention in the computer vision community. However, it is still quite difficult to recover an accurate depth map using only one RGB image. We observe a phenomenon that existing methods tend to fail in…

It is a challenging task to learn rich and multi-scale spatiotemporal semantics from high-dimensional videos, due to large local redundancy and complex global dependency between video frames. The recent advances in this research have been…

Perception-centric systems are typically implemented with a modular encoder-decoder pipeline: a vision backbone for feature extraction and a separate decoder (or late-fusion module) for task prediction. This raises a central question: is…

Transformers in their common form are inherently limited to operate on whole token sequences rather than on one token at a time. Consequently, their use during online inference on time-series data entails considerable redundancy due to the…

Transformers have shown great potential in computer vision tasks. A common belief is their attention-based token mixer module contributes most to their competence. However, recent works show the attention-based module in Transformers can be…