Related papers: Duo Streamers: A Streaming Gesture Recognition Fra…

Multi-person articulated pose tracking in unconstrained videos is an important while challenging problem. In this paper, going along the road of top-down approaches, we propose a decent and efficient pose tracker based on pose flows. First,…

Pose-based action recognition is predominantly tackled by approaches which treat the input skeleton in a monolithic fashion, i.e. joints in the pose tree are processed as a whole. However, such approaches ignore the fact that action…

It remains a challenge to efficiently extract spatialtemporal information from skeleton sequences for 3D human action recognition. Although most recent action recognition methods are based on Recurrent Neural Networks which present…

In many emerging applications, data streams are monitored in a network environment. Due to limited communication bandwidth and other resource constraints, a critical and practical demand is to online compress data streams continuously with…

While fulfilling communication tasks, wireless signals can also be used to sense the environment. Among various types of sensing media, WiFi signals offer advantages such as widespread availability, low hardware cost, and strong robustness…

Diffusion models have achieved remarkable success in generating high-fidelity content but suffer from slow, iterative sampling, resulting in high latency that limits their use in interactive applications. We introduce DRiffusion, a parallel…

How can we track synchronized behavior in a stream of time-stamped tuples, such as mobile devices installing and uninstalling applications in the lockstep, to boost their ranks in the app store? We model such tuples as entries in a…

Cloud rendering is widely used in gaming and XR to overcome limited client-side GPU resources and to support heterogeneous devices. Existing systems typically deliver the rendered scene as a 2D video stream, which tightly couples the…

The task of spatial-temporal action detection has attracted increasing attention among researchers. Existing dominant methods solve this problem by relying on short-term information and dense serial-wise detection on each individual frames…

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…

We propose nnstreamer, a software system that handles neural networks as filters of stream pipelines, applying the stream processing paradigm to neural network applications. A new trend with the wide-spread of deep neural network…

A lensless camera is an imaging system that uses a mask in place of a lens, making it thinner, lighter, and less expensive than a lensed camera. However, additional complex computation and time are required for image reconstruction. This…

Hand gestures play a significant role in human interactions where non-verbal intentions, thoughts and commands are conveyed. In Human-Robot Interaction (HRI), hand gestures offer a similar and efficient medium for conveying clear and rapid…

In this paper, we propose a digital twin (DT)-assisted cloud-edge collaborative transcoding scheme to enhance user satisfaction in live streaming. We first present a DT-assisted transcoding workload estimation (TWE) model for the cloud-edge…

Multi-step prediction models, such as diffusion and rectified flow models, have emerged as state-of-the-art solutions for generation tasks. However, these models exhibit higher latency in sampling new frames compared to single-step methods.…

The Transducer (e.g. RNN-Transducer or Conformer-Transducer) generates an output label sequence as it traverses the input sequence. It is straightforward to use in streaming mode, where it generates partial hypotheses before the complete…

Spatial and temporal stream model has gained great success in video action recognition. Most existing works pay more attention to designing effective features fusion methods, which train the two-stream model in a separate way. However, it's…

We design a gesture-recognition pipeline for networks of distributed, resource constrained devices utilising Einsum Networks. Einsum Networks are probabilistic circuits that feature a tractable inference, explainability, and energy…

Despite the success of existing tensor factorization methods, most of them conduct a multilinear decomposition, and rarely exploit powerful modeling frameworks, like deep neural networks, to capture a variety of complicated interactions in…

Convolutional neural networks (CNNs) have demonstrated their superiority in numerous computer vision tasks, yet their computational cost results prohibitive for many real-time applications such as pedestrian detection which is usually…