Related papers: LAPX: Lightweight Hourglass Network with Global Co…
Estimating 3D poses from a monocular video is still a challenging task, despite the significant progress that has been made in recent years. Generally, the performance of existing methods drops when the target person is too small/large, or…
The quadratic cost of attention limits the scalability of long-context LLMs, especially under limited hardware memory budgets. While attention is often sparse, existing static sparse methods cannot adapt to task- or input-dependent…
Lane segment topology reasoning provides comprehensive bird's-eye view (BEV) road scene understanding, which can serve as a key perception module in planning-oriented end-to-end autonomous driving systems. Existing lane topology reasoning…
Development of human machine interface has become a necessity for modern day machines to catalyze more autonomy and more efficiency. Gaze driven human intervention is an effective and convenient option for creating an interface to alleviate…
Currently, lightweight hybrid backbone networks have partially alleviated the issue of computational saturation, but the imbalance in computational efficiencys between convolutional neural networks (CNNs) and attention mechanisms is…
Recent advances in unsupervised learning for object detection, segmentation, and tracking hold significant promise for applications in robotics. A common approach is to frame these tasks as inference in probabilistic latent-variable models.…
State-of-the-art machine-learning methods for event cameras treat events as dense representations and process them with conventional deep neural networks. Thus, they fail to maintain the sparsity and asynchronous nature of event data,…
Recent research on human pose estimation exploits complex structures to improve performance on benchmark datasets, ignoring the resource overhead and inference speed when the model is actually deployed. In this paper, we lighten the…
Target tracking is a popular problem with many potential applications. There has been a lot of effort on improving the quality of the detection of targets using cameras through different techniques. In general, with higher computational…
Real-time object detection in AR/VR systems faces critical computational constraints, requiring sub-10\,ms latency within tight power budgets. Inspired by biological foveal vision, we propose a two-stage pipeline that combines…
We analyzed the network structure of real-time object detection models and found that the features in the feature concatenation stage are very rich. Applying an attention module here can effectively improve the detection accuracy of the…
The importance of higher-order relations is widely recognized in a large number of real-world systems. However, annotating them is a tedious and sometimes impossible task. Consequently, current approaches for data modelling either ignore…
Convolution exploits locality for efficiency at a cost of missing long range context. Self-attention has been adopted to augment CNNs with non-local interactions. Recent works prove it possible to stack self-attention layers to obtain a…
Learning to capture human motion is essential to 3D human pose and shape estimation from monocular video. However, the existing methods mainly rely on recurrent or convolutional operation to model such temporal information, which limits the…
Accurately predicting end-to-end network latency is essential for enabling reliable task offloading in real-time edge computing applications. This paper introduces a lightweight latency prediction scheme based on rational modelling that…
Estimating 3D human poses from a monocular video is still a challenging task. Many existing methods' performance drops when the target person is occluded by other objects, or the motion is too fast/slow relative to the scale and speed of…
We present a real-time gaze tracking system that directly acquires task-relevant latent features using a fully passive optical encoder. Instead of forming and processing full-resolution images, our approach leverages a microlens array with…
Event cameras provide sequential visual data with spatial sparsity and high temporal resolution, making them attractive for low-latency object detection. Existing asynchronous event-based neural networks realize this low-latency advantage…
Although existing 3D perception algorithms have demonstrated significant improvements in performance, their deployment on edge devices continues to encounter critical challenges due to substantial runtime latency. We propose a new benchmark…
Lattices are an efficient and effective method to encode ambiguity of upstream systems in natural language processing tasks, for example to compactly capture multiple speech recognition hypotheses, or to represent multiple linguistic…