Related papers: DeDelayed: Deleting Remote Inference Delay via On-…

Rate control is widely adopted during video streaming to provide both high video qualities and low latency under various network conditions. However, despite that many work have been proposed, they fail to tackle one major problem: previous…

Recognizing the surrounding environment at low latency is critical in autonomous driving. In real-time environment, surrounding environment changes when processing is over. Current detection models are incapable of dealing with changes in…

Inferring the quality of streaming video applications is important for Internet service providers, but the fact that most video streams are encrypted makes it difficult to do so. We develop models that infer quality metrics (\ie, startup…

Real-time object detection is critical for the decision-making process for many real-world applications, such as collision avoidance and path planning in autonomous driving. This work presents an innovative real-time streaming perception…

Radar sensors offer power-efficient solutions for always-on smart devices, but processing the data streams on resource-constrained embedded platforms remains challenging. This paper presents novel techniques that leverage the temporal…

Interlacing is a widely used technique, for television broadcast and video recording, to double the perceived frame rate without increasing the bandwidth. But it presents annoying visual artifacts, such as flickering and silhouette…

Real-time object detection takes an essential part in the decision-making process of numerous real-world applications, including collision avoidance and path planning in autonomous driving systems. This paper presents a novel real-time…

Decentralized Federated learning is a distributed edge intelligence framework by exchanging parameter updates instead of training data among participators, in order to retrain or fine-tune deep learning models for mobile intelligent…

State-of-the-art digital circuit design tools almost exclusively rely on pure and inertial delay for timing simulations. While these provide reasonable estimations at very low execution time in the average case, their ability to cover…

Video frame transmission delay is critical in real-time applications such as online video gaming, live show, etc. The receiving deadline of a new frame must catch up with the frame rendering time. Otherwise, the system will buffer a while,…

We study distributed stochastic convex optimization under the delayed gradient model where the server nodes perform parameter updates, while the worker nodes compute stochastic gradients. We discuss, analyze, and experiment with a setup…

Though action recognition in videos has achieved great success recently, it remains a challenging task due to the massive computational cost. Designing lightweight networks is a possible solution, but it may degrade the recognition…

The rapid advancements in machine learning techniques have led to significant achievements in various real-world robotic tasks. These tasks heavily rely on fast and energy-efficient inference of deep neural network (DNN) models when…

Models for low-latency, streaming applications could benefit from the knowledge capacity of larger models, but edge devices cannot run these models due to resource constraints. A possible solution is to transfer hints during inference from…

Let us rethink the real-world scenarios that require human motion prediction techniques, such as human-robot collaboration. Current works simplify the task of predicting human motions into a one-off process of forecasting a short future…

Encoder-decoder transformer models have achieved great success on various vision-language (VL) tasks, but they suffer from high inference latency. Typically, the decoder takes up most of the latency because of the auto-regressive decoding.…

In this paper, we consider a remote inference system, where a neural network is used to infer a time-varying target (e.g., robot movement), based on features (e.g., video clips) that are progressively received from a sensing node (e.g., a…

Autonomous driving systems require real-time environmental perception to ensure user safety and experience. Streaming perception is a task of reporting the current state of the world, which is used to evaluate the delay and accuracy of…

Deep learning has been widely adopted to tackle various code-based tasks by building deep code models based on a large amount of code snippets. While these deep code models have achieved great success, even state-of-the-art models suffer…

Learning algorithms can be significantly improved by routing complex or uncertain inputs to specialized experts, balancing accuracy with computational cost. This approach, known as learning to defer, is essential in domains like natural…