Related papers: MR2-ByteTrack: CNN and Transformer-based Video Obj…
Scene change detection is an image processing problem related to partitioning pixels of a digital image into foreground and background regions. Mostly, visual knowledge-based computer intelligent systems, like traffic monitoring, video…
An increasing share of captured images and videos are transmitted for storage and remote analysis by computer vision algorithms, rather than to be viewed by humans. Contrary to traditional standard codecs with engineered tools, neural…
The Versatile Video Coding (VVC) standard has been recently finalized by the Joint Video Exploration Team (JVET). Compared to the High Efficiency Video Coding (HEVC) standard, VVC offers about 50% compression efficiency gain, in terms of…
Object detection systems based on the deep convolutional neural network (CNN) have recently made ground- breaking advances on several object detection benchmarks. While the features learned by these high-capacity neural networks are…
Previous studies on event camera sensing have demonstrated certain detection performance using dense event representations. However, the accumulated noise in such dense representations has received insufficient attention, which degrades the…
Crack detection on road surfaces is a critical measurement technology in the instrumentation domain, essential for ensuring infrastructure safety and transportation reliability. However, due to limited energy and low-resolution imaging,…
The field of 3D object detection from point clouds is rapidly advancing in computer vision, aiming to accurately and efficiently detect and localize objects in three-dimensional space. Current 3D detectors commonly fall short in terms of…
Intelligent surveillance systems often handle perceptual tasks such as object detection, facial recognition, and emotion analysis independently, but they lack a unified, adaptive runtime scheduler that dynamically allocates computational…
Despite the continued successes of computationally efficient deep neural network architectures for video object detection, performance continually arrives at the great trilemma of speed versus accuracy versus computational resources (pick…
We propose a transformer-based neural network architecture for multi-object 3D reconstruction from RGB videos. It relies on two alternative ways to represent its knowledge: as a global 3D grid of features and an array of view-specific 2D…
Various convolutional neural networks (CNNs) were developed recently that achieved accuracy comparable with that of human beings in computer vision tasks such as image recognition, object detection and tracking, etc. Most of these networks,…
Artifact removal and filtering methods are inevitable parts of video coding. On one hand, new codecs and compression standards come with advanced in-loop filters and on the other hand, displays are equipped with high capacity processing…
Videos take a lot of time to transport over the network, hence running analytics on the live video on embedded or mobile devices has become an important system driver. Considering that such devices, e.g., surveillance cameras or AR/VR…
Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) are two dominant models for image analysis. While CNNs excel at extracting multi-scale features and ViTs effectively capture global dependencies, both suffer from high…
Deep learning inference that needs to largely take place on the 'edge' is a highly computational and memory intensive workload, making it intractable for low-power, embedded platforms such as mobile nodes and remote security applications.…
Deploying object detection on microcontrollers (MCUs) enables intelligent edge devices but current models cannot learn new object categories after deployment. Existing continual learning methods require storing raw images far exceeding MCU…
In this paper, we study Multiscale Vision Transformers (MViTv2) as a unified architecture for image and video classification, as well as object detection. We present an improved version of MViT that incorporates decomposed relative…
Recently, deep learning based video object detection has attracted more and more attention. Compared with object detection of static images, video object detection is more challenging due to the motion of objects, while providing rich…
We develop a deep learning algorithm for contour detection with a fully convolutional encoder-decoder network. Different from previous low-level edge detection, our algorithm focuses on detecting higher-level object contours. Our network is…
Deep learning has been demonstrated to achieve excellent results for image classification and object detection. However, the impact of deep learning on video analysis (e.g. action detection and recognition) has been limited due to…