相关论文: DeepScale: Online Frame Size Adaptation for Multi-…

We consider a network of smart sensors for an edge computing application that sample a time-varying signal and send updates to a base station for remote global monitoring. Sensors are equipped with sensing and compute, and can either send…

Much of the focus in the design of deep neural networks has been on improving accuracy, leading to more powerful yet highly complex network architectures that are difficult to deploy in practical scenarios, particularly on edge devices such…

In recent years, Discriminative Correlation Filter (DCF) based tracking methods have achieved great success in visual tracking. However, the multi-resolution convolutional feature maps trained from other tasks like image classification,…

Sustaining high fidelity and high throughput of perception tasks over vision sensor streams on edge devices remains a formidable challenge, especially given the continuing increase in image sizes (e.g., generated by 4K cameras) and…

Mixed precision training (MPT) is becoming a practical technique to improve the speed and energy efficiency of training deep neural networks by leveraging the fast hardware support for IEEE half-precision floating point that is available in…

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…

Detection-driven real-time video analytics require continuous detection of objects contained in the video frames using deep learning models like YOLOV3, EfficientDet. However, running these detectors on each and every frame in…

Accurately distinguishing each object is a fundamental goal of Multi-object tracking (MOT) algorithms. However, achieving this goal still remains challenging, primarily due to: (i) For crowded scenes with occluded objects, the high overlap…

The goal of this paper is to accelerate the training of machine learning models, a critical challenge since the training of large-scale deep neural models can be computationally expensive. Stochastic gradient descent (SGD) and its variants…

Depth estimation is one of the key technologies for realizing 3D perception in unmanned systems. Monocular depth estimation has been widely researched because of its low-cost advantage, but the existing methods face the challenges of poor…

Purpose: Surgical scene understanding plays a critical role in the technology stack of tomorrow's intervention-assisting systems in endoscopic surgeries. For this, tracking the endoscope pose is a key component, but remains challenging due…

We propose an online tracking algorithm that performs the object detection and data association under a common framework, capable of linking objects after a long time span. This is realized by preserving a large spatio-temporal memory to…

Data collected by IoT devices are often private and have a large diversity across users. Therefore, learning requires pre-training a model with available representative data samples, deploying the pre-trained model on IoT devices, and…

Video object segmentation targets at segmenting a specific object throughout a video sequence, given only an annotated first frame. Recent deep learning based approaches find it effective by fine-tuning a general-purpose segmentation model…

Deep object recognition models have been very successful over benchmark datasets such as ImageNet. How accurate and robust are they to distribution shifts arising from natural and synthetic variations in datasets? Prior research on this…

Multiple Object Tracking (MOT) aims to find bounding boxes and identities of targeted objects in consecutive video frames. While fully-supervised MOT methods have achieved high accuracy on existing datasets, they cannot generalize well on a…

Machine learning at the edge offers great benefits such as increased privacy and security, low latency, and more autonomy. However, a major challenge is that many devices, in particular edge devices, have very limited memory, weak…

Current convolutional neural networks algorithms for video object tracking spend the same amount of computation for each object and video frame. However, it is harder to track an object in some frames than others, due to the varying amount…

Innovative enhancement in embedded system platforms, specifically hardware accelerations, significantly influence the application of deep learning in real-world scenarios. These innovations translate human labor efforts into automated…

Benchmarking multi-object tracking and object detection model performance is an essential step in machine learning model development, as it allows researchers to evaluate model detection and tracker performance on human-generated 'test'…