Related papers: EdgeOAR: Real-time Online Action Recognition On Ed…
Efficiently modeling spatial-temporal information in videos is crucial for action recognition. To achieve this goal, state-of-the-art methods typically employ the convolution operator and the dense interaction modules such as non-local…
Edge computing enables data processing closer to the source, significantly reducing latency, an essential requirement for real-time vision-based analytics such as object detection in surveillance and smart city environments. However, these…
The problem of Online Human Behaviour Recognition in untrimmed videos, aka Online Action Detection (OAD), needs to be revisited. Unlike traditional offline action detection approaches, where the evaluation metrics are clear and well…
We aim to tackle a novel task in action detection - Online Detection of Action Start (ODAS) in untrimmed, streaming videos. The goal of ODAS is to detect the start of an action instance, with high categorization accuracy and low detection…
Real-time video inference on edge devices like mobile phones and drones is challenging due to the high computation cost of Deep Neural Networks. We present Adaptive Model Streaming (AMS), a new approach to improving performance of efficient…
Emerging Internet of Things (IoT) and mobile computing applications are expected to support latency-sensitive deep neural network (DNN) workloads. To realize this vision, the Internet is evolving towards an edge-computing architecture,…
We formulate the problem of online temporal action detection in live streaming videos, acknowledging one important property of live streaming videos that there is normally a broadcast delay between the latest captured frame and the actual…
Most machine learning (ML) systems assume stationary and matching data distributions during training and deployment. This is often a false assumption. When ML models are deployed on real devices, data distributions often shift over time due…
This paper proposes the first generic fast convergence result in general function approximation for offline decision making problems, which include offline reinforcement learning (RL) and off-policy evaluation (OPE) as special cases. To…
Online action detection (OAD) is a practical yet challenging task, which has attracted increasing attention in recent years. A typical OAD system mainly consists of three modules: a frame-level feature extractor which is usually based on…
Accelerating Human Action Recognition (HAR) efficiently for real-time surveillance and robotic systems on edge chips remains a challenging research field, given its high computational and memory requirements. This paper proposed an…
We introduce an efficient video segmentation system for resource-limited edge devices leveraging heterogeneous compute. Specifically, we design network models by searching across multiple dimensions of specifications for the neural…
Temporal action proposal generation (TAPG) is a challenging task, which requires localizing action intervals in an untrimmed video. Intuitively, we as humans, perceive an action through the interactions between actors, relevant objects, and…
Good temporal representations are crucial for video understanding, and the state-of-the-art video recognition framework is based on two-stream networks. In such framework, besides the regular ConvNets responsible for RGB frame inputs, a…
Fast and accurate video object recognition, which relies on frame-by-frame video analytics, remains a challenge for resource-constrained devices such as traffic cameras. Recent advances in mobile edge computing have made it possible to…
Temporal action detection (TAD) with end-to-end training often suffers from the pain of huge demand for computing resources due to long video duration. In this work, we propose an efficient temporal action detector (ETAD) that can train…
Open-world video anomaly detection (OWVAD) aims to detect and explain abnormal events under different anomaly definitions, which is important for applications such as intelligent surveillance and live-streaming content moderation. Recent…
Real-time video analytics on edge devices for changing scenes remains a difficult task. As edge devices are usually resource-constrained, edge deep neural networks (DNNs) have fewer weights and shallower architectures than general DNNs. As…
Addressing the challenges of irregularity and concept drift in streaming time series is crucial for real-world predictive modelling. Previous studies in time series continual learning often propose models that require buffering long…
Edge service caching can significantly mitigate latency and reduce communication and computing overhead by fetching and initializing services (applications) from clouds. The freshness of cached service data is critical when providing…