Related papers: StreamTinyNet: video streaming analysis with spati…
This paper introduces Memory-limited Online Subspace Estimation Scheme (MOSES) for both estimating the principal components of streaming data and reducing its dimension. More specifically, in various applications such as sensor networks,…
We introduce Delayed Streams Modeling (DSM), a flexible formulation for streaming, multimodal sequence-to-sequence learning. Sequence-to-sequence generation is often cast in an offline manner, where the model consumes the complete input…
One of the challenges for Tiny Machine Learning (tinyML) is keeping up with the evolution of Machine Learning models from Convolutional Neural Networks to Transformers. We address this by leveraging a heterogeneous architectural template…
We train and deploy a quantized 1D convolutional neural network model to conduct speech recognition on a highly resource-constrained IoT edge device. This can be useful in various Internet of Things (IoT) applications, such as smart homes…
Do video-text transformers learn to model temporal relationships across frames? Despite their immense capacity and the abundance of multimodal training data, recent work has revealed the strong tendency of video-text models towards…
Existing matching-based approaches perform video object segmentation (VOS) via retrieving support features from a pixel-level memory, while some pixels may suffer from lack of correspondence in the memory (i.e., unseen), which inevitably…
Long-range and short-range temporal modeling are two complementary and crucial aspects of video recognition. Most of the state-of-the-arts focus on short-range spatio-temporal modeling and then average multiple snippet-level predictions to…
Vision agent memory has shown remarkable effectiveness in streaming video understanding. However, storing such memory for videos incurs substantial memory overhead, leading to high costs in both storage and computation. To address this…
Efficient execution of deep learning workloads on dataflow architectures is crucial for overcoming memory bottlenecks and maximizing performance. While streaming intermediate results between computation kernels can significantly improve…
This paper presents a fully autonomous Tiny Machine Learning (TinyML) Z-Score-based anomaly detection system deployed on a low-power microcontroller for real-time monitoring of appliance behavior using power side-channel data. Unlike…
While most work on evaluating machine learning (ML) models focuses on computing accuracy on batches of data, tracking accuracy alone in a streaming setting (i.e., unbounded, timestamp-ordered datasets) fails to appropriately identify when…
Video understanding is a challenging problem with great impact on the abilities of autonomous agents working in the real-world. Yet, solutions so far have been computationally intensive, with the fastest algorithms running for more than…
Anomaly detection plays a key role in industrial quality control, where defects must be identified despite the scarcity of labeled faulty samples. Recent self-supervised approaches, such as GLASS, learn normal visual patterns using only…
Video continues to dominate network traffic, yet operators today have poor visibility into the number, duration, and resolutions of the video streams traversing their domain. Current approaches are inaccurate, expensive, or unscalable, as…
In this paper we introduce ViSiL, a Video Similarity Learning architecture that considers fine-grained Spatio-Temporal relations between pairs of videos -- such relations are typically lost in previous video retrieval approaches that embed…
Video semantic segmentation requires to utilize the complex temporal relations between frames of the video sequence. Previous works usually exploit accurate optical flow to leverage the temporal relations, which suffer much from heavy…
While Test-Time Scaling (TTS) offers a promising direction to enhance video generation without the surging costs of training, current test-time video generation methods based on diffusion models suffer from exorbitant candidate exploration…
The explosion of IoT sensors in industrial, consumer and remote sensing use cases has come with unprecedented demand for computing infrastructure to transmit and to analyze petabytes of data. Concurrently, the world is slowly shifting its…
With the surge of inexpensive computational and memory resources, neural networks (NNs) have experienced an unprecedented growth in architectural and computational complexity. Introducing NNs to resource-constrained devices enables…
Deep learning models have enjoyed great success for image related computer vision tasks like image classification and object detection. For video related tasks like human action recognition, however, the advancements are not as significant…