Related papers: YolactEdge: Real-time Instance Segmentation on the…
We introduce YOLO9000, a state-of-the-art, real-time object detection system that can detect over 9000 object categories. First we propose various improvements to the YOLO detection method, both novel and drawn from prior work. The improved…
Previous state-of-the-art real-time object detectors have been reported on GPUs which are extremely expensive for processing massive data and in resource-restricted scenarios. Therefore, high efficiency object detectors on CPU-only devices…
Online zero-shot 3D instance segmentation of a progressively reconstructed scene is both a critical and challenging task for embodied applications. With the success of visual foundation models (VFMs) in the image domain, leveraging 2D…
In this paper, we propose a conceptually novel, efficient, and fully convolutional framework for real-time instance segmentation. Previously, most instance segmentation methods heavily rely on object detection and perform mask prediction…
Real-time perception on edge platforms faces a core challenge: executing high-resolution object detection under stringent latency constraints on limited computing resources. Canvas-based attention scheduling was proposed in earlier work as…
Interactive segmentation enables users to extract binary masks of target objects through simple interactions such as clicks, scribbles, and boxes. However, existing methods often support only limited interaction forms and struggle to…
Autonomous driving (AD) systems relying solely on onboard sensors may fail to detect distant or obstacle hazards, potentially causing preventable collisions; however, existing transformer-based Vehicle-to-Everything (V2X) approaches, which…
Long Video Temporal Grounding (LVTG) aims at identifying specific moments within lengthy videos based on user-provided text queries for effective content retrieval. The approach taken by existing methods of dividing video into clips and…
This paper presents LiteEval, a simple yet effective coarse-to-fine framework for resource efficient video recognition, suitable for both online and offline scenarios. Exploiting decent yet computationally efficient features derived at a…
Most approaches for instance-aware semantic labeling traditionally focus on accuracy. Other aspects like runtime and memory footprint are arguably as important for real-time applications such as autonomous driving. Motivated by this…
Predicting a binary mask for an object is more accurate but also more computationally expensive than a bounding box. Polygonal masks as developed in CenterPoly can be a good compromise. In this paper, we improve over CenterPoly by enhancing…
Recent success of semantic segmentation approaches on demanding road driving datasets has spurred interest in many related application fields. Many of these applications involve real-time prediction on mobile platforms such as cars, drones…
We introduce a lightweight and accurate architecture for resource-efficient visual correspondence. Our method, dubbed XFeat (Accelerated Features), revisits fundamental design choices in convolutional neural networks for detecting,…
In this contribution we use an ensemble deep-learning method for combining the prediction of two individual one-stage detectors (i.e., YOLOv4 and Yolact) with the aim to detect artefacts in endoscopic images. This ensemble strategy enabled…
In this study, we introduce EdgeSegNet, a compact deep convolutional neural network for the task of semantic segmentation. A human-machine collaborative design strategy is leveraged to create EdgeSegNet, where principled network design…
Video instance segmentation aims to detect, segment, and track objects in a video. Current approaches extend image-level segmentation algorithms to the temporal domain. However, this results in temporally inconsistent masks. In this work,…
Despite significant efforts, cutting-edge video segmentation methods still remain sensitive to occlusion and rapid movement, due to their reliance on the appearance of objects in the form of object embeddings, which are vulnerable to these…
Video instance segmentation is a challenging task that extends image instance segmentation to the video domain. Existing methods either rely only on single-frame information for the detection and segmentation subproblems or handle tracking…
This dissertation advances the state of the art for AR/VR tracking systems by increasing the tracking frequency by orders of magnitude and proposes an efficient algorithm for the problem of edge-aware optimization. AR/VR is a natural way of…
Modern applications such as autonomous vehicles, intelligent surveillance, and smart city systems increasingly require object detection on resource-constrained edge devices. Yet, there is still limited understanding of how different object…