Related papers: StreamTinyNet: video streaming analysis with spati…

Streaming video understanding requires models to robustly encode, store, and retrieve information from a continuous video stream to support accurate video question answering (VQA). Existing state-of-the-art approaches rely on key-value…

TinyML has made deploying deep learning models on low-power edge devices feasible, creating new opportunities for real-time perception in constrained environments. However, the adaptability of such deep learning methods remains limited to…

Video streaming analytics is a crucial workload for vision-language model serving, but the high cost of multimodal inference limits scalability. Prior systems reduce inference cost by exploiting temporal and spatial redundancy in video…

Unlike offline processing, streaming video vision-language models face two fundamental constraints: causality and accumulation. Causality prevents access to future frames that offline methods exploit, while accumulation causes tokens to…

High-Definition (HD) maps are essential for the safety of autonomous driving systems. While existing techniques employ camera images and onboard sensors to generate vectorized high-precision maps, they are constrained by their reliance on…

Video understanding tasks have traditionally been modeled by two separate architectures, specially tailored for two distinct tasks. Sequence-based video tasks, such as action recognition, use a video backbone to directly extract…

We present a streaming model for large-scale classification (in the context of $\ell_2$-SVM) by leveraging connections between learning and computational geometry. The streaming model imposes the constraint that only a single pass over the…

Although deep neural networks are typically computationally expensive to use, technological advances in both the design of hardware platforms and of neural network architectures, have made it possible to use powerful models on edge devices.…

The sustained growth of carbon emissions and global waste elicits significant sustainability concerns for our environment's future. The growing Internet of Things (IoT) has the potential to exacerbate this issue. However, an emerging area…

Earth observation (EO) missions traditionally rely on transmitting raw or minimally processed imagery from satellites to ground stations for computationally intensive analysis. This paradigm is infeasible for CubeSat systems due to…

Examples of embedded intelligence include a wide variety of tiny neural networks used on-board wireless sensors and actuators, which are expected to continuously perform inference on time-series of the data they sense. In order to fit…

The explosive growth in video streaming requires video understanding at high accuracy and low computation cost. Conventional 2D CNNs are computationally cheap but cannot capture temporal relationships; 3D CNN-based methods can achieve good…

Real-time, continuous understanding of visual signals is essential for real-world interactive AI applications, and poses a fundamental system-level challenge. Existing research on streaming video understanding, however, typically focuses on…

How to effectively and efficiently deal with spatio-temporal event streams, where the events are generally sparse and non-uniform and have the microsecond temporal resolution, is of great value and has various real-life applications.…

The explosive growth in video streaming gives rise to challenges on performing video understanding at high accuracy and low computation cost. Conventional 2D CNNs are computationally cheap but cannot capture temporal relationships; 3D CNN…

Deep neural networks have consistently shown great performance in several real-world use cases like autonomous vehicles, satellite imaging, etc., effectively leveraging large corpora of labeled training data. However, learning unbiased…

Time series anomaly detection (TSAD) is becoming increasingly vital due to the rapid growth of time series data across various sectors. Anomalies in web service data, for example, can signal critical incidents such as system failures or…

A widely-used tool for binary classification is the Support Vector Machine (SVM), a supervised learning technique that finds the "maximum margin" linear separator between the two classes. While SVMs have been well studied in the batch…

Nowadays, every device connected to the Internet generates an ever-growing stream of data (formally, unbounded). Machine Learning on unbounded data streams is a grand challenge due to its resource constraints. In fact, standard machine…

The recent progress in TinyML technologies triggers the need to address the challenge of balancing inference time and classification quality. TinyML systems are defined by specific constraints in computation, memory and energy. These…