Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 20 of 28 for “"Object proposals"”.

  1. Object Proposals in Computer Vision

    Object recognition is a central problem in computer vision which deals with both localizing and identifying objects in images. Object proposals have recently become an important part of the object recognition process. Object proposals are algorithms used for localizing objects in images. This …

    vt Repository record for Object Proposals in Computer Vision (opens in a new tab)

  2. Learning to Generate and Refine Object Proposals

    Visual object recognition is a fundamental and challenging problem in computer vision. To build a practical recognition system, one is first confronted with high computation complexity due to an enormous search space from an image, which is caused by large variations in object appearance, pose and …

    anu Repository record for Learning to Generate and Refine Object Proposals (opens in a new tab)

  3. Refining Object Proposals and Temporal Consistency in Unsupervised Video Object Segmentation

    … supervision during inference, and the number of objects, to streamline VS. However, these assumptions can limit the applicability of the subtasks to real-world problems. In this thesis, we aim to improve multi-object Unsupervised Video Object Segmentation (UVOS), which is one of the subtasks of …

    sask Repository record for Refining Object Proposals and Temporal Consistency in Unsupervised Video Object Segmentation (opens in a new tab)

  4. Generating Discriminative Objective Proposals via Submodular Ranking

    Object recognition has long been a core problem in computer vision. To improve object spatial support and speed up object localization for object recognition, generating high-quality category-independent object proposals as the input for object recognition system has drawn attention recently. Given …

    maryland Repository record for Generating Discriminative Objective Proposals via Submodular Ranking (opens in a new tab)

  5. Improving the utilization of training samples in visual recognition

    … methods. Two visual recognition tasks namely object detection and action recognition and are considered in this thesis. Active learning utilizes selected subsets of the training dataset as training samples. Active learning methods select the most informative training samples in each iteration, …

    unsw Repository record for Improving the utilization of training samples in visual recognition (opens in a new tab)

  6. Object understanding in generalized video segmentation

    Spatio-temporal object representation is a key component in video understanding and is important for tasks like generalized video segmentation. Current methods often fail to represent objects spatio-temporally, by failing to capture the motion and interactions of objects over time, leading to …

    uiuc Repository record for Object understanding in generalized video segmentation (opens in a new tab)

  7. Spatiotemporal Graphs for Object Segmentation and Human Pose Estimation in Videos

    … solutions. The first problem we explore is video object segmentation. The goal is to segment the primary moving objects in the videos. This problem is important for many applications, such as content based video retrieval, video summarization, activity understanding and targeted content …

    ucf Repository record for Spatiotemporal Graphs for Object Segmentation and Human Pose Estimation in Videos (opens in a new tab)

  8. A Unified Multiscale Encoder-Decoder Transformer for Video Segmentation

    … of feature encoding, context encoding and object decoding in an encoder-decoder model. Correspondingly, we present a Multiscale Encoder-Decoder Video Transformer (MED-VT) that uses multiscale representation throughout and employs an optional input beyond video (e.g., audio), when available, …

    york Repository record for A Unified Multiscale Encoder-Decoder Transformer for Video Segmentation (opens in a new tab)

  9. Deep neural networks for animal object detection and recognition in the wild

    … vision algorithms for efficient and accurate object detection and sequence-level classification from natural scene camera-trap images. This work addresses the following five major tasks: (1) Human-animal detection. We develop a fast and accurate scheme for human-animal detection from highly …

    missouri Repository record for Deep neural networks for animal object detection and recognition in the wild (opens in a new tab)

  10. Sensor Fusion for Object Detection and Tracking in Autonomous Vehicles

    … and perform a variety of tasks such as object detection and object tracking. Combining the outputs of different sensors to obtain a more reliable and robust outcome is called sensor fusion. This dissertation studies the problem of sensor fusion for object detection and object tracking in …

    utk-theses Repository record for Sensor Fusion for Object Detection and Tracking in Autonomous Vehicles (opens in a new tab)

  11. Leveraging Multiple Features for Image Retrieval and Matching

    … retrieval and matching is to find and locate object instances in images from a large-scale image database. While visual features are abundant, how to combine them to improve performance by individual features remains a challenging task. In this work, we focus on leveraging multiple features …

    maryland Repository record for Leveraging Multiple Features for Image Retrieval and Matching (opens in a new tab)

  12. Integrating textual queries with aI-based object detection: a compositional prompt-guided approach

    In the field of computer vision, object detection and recognition play a central role in many applications that support automated decision-making. Over recent years, new algorithms and methodologies have emerged to further enhance the automatic identification of target objects. In particular, the …

    brazil-ufrn Repository record for Integrating textual queries with aI-based object detection: a compositional prompt-guided approach (opens in a new tab)

  13. A Graph Convolutional Neural Network Based Approach for Object Tracking Using Augmented Detections With Optical Flow

    … thesis presents a novel method for online Multi-Object Tracking (MOT) using Graph Convolutional Neural Network (GCNN) based feature extraction and end-to-end feature matching for object association. The Graph based approach incorporates both appearance and geometry of objects at past frames as …

    vt Repository record for A Graph Convolutional Neural Network Based Approach for Object Tracking Using Augmented Detections With Optical Flow (opens in a new tab)

  14. Semantically Consistent Alignment for Novel Object Discovery in Open-Vocabulary 3D Object Detection

    3D object detection is a fundamental task in the autonomous driving perception pipeline, where identifying and localizing objects within the surrounding environment is critical for safe and robust decision-making. However, traditional 3D object detectors are limited by their reliance on a closed …

    waterloo Repository record for Semantically Consistent Alignment for Novel Object Discovery in Open-Vocabulary 3D Object Detection (opens in a new tab)

  15. An Instance-Conditioned Faster R-CNN: Modulating Supervision and Feature Representation Based on Instance-Specific Cues for Small Object Detection

    Object detection is used in applications ranging from aerial surveillance to industrial inspection. Its effectiveness depends on accurate feature representation and training supervision. Feature representation must retain information to identify and localize small objects, while training …

    calgary Repository record for An Instance-Conditioned Faster R-CNN: Modulating Supervision and Feature Representation Based on Instance-Specific Cues for Small Object Detection (opens in a new tab)

  16. Detection and incremental object learning in videos

    … facility for learning visual representations of objects through a combination of self-directed visual exploration and access to a sparse supervisory signal in the form of spoken object names. Studies of infant development have shown that children are able to locate, track, and differentiate novel …

    gatech Repository record for Detection and incremental object learning in videos (opens in a new tab)

  17. Real-time 3D Object Detection for Autonomous Driving

    … focuses on advancing the state-of-the-art 3D object detection and localization in autonomous driving. An autonomous vehicle requires operating within a very unpredictable and dynamic environment. Hence a robust perception system is essential. This work proposes a novel architecture, AVOD, an …

    waterloo Repository record for Real-time 3D Object Detection for Autonomous Driving (opens in a new tab)

  18. Zero-Shot Monocular Motion Segmentation: A Fusion of Deep Learning and Geometric Approaches

    Identifying and segmenting moving objects from a moving monocular camera is difficult when there is unknown camera motion, different types of object motions and complex scene structures. Deep learning methods achieve impressive results for generic motion segmentation, but they require massive …

    waterloo Repository record for Zero-Shot Monocular Motion Segmentation: A Fusion of Deep Learning and Geometric Approaches (opens in a new tab)

  19. RGB-DEPTH IMAGE SEGMENTATION AND OBJECT RECOGNITION FOR INDOOR SCENES

    … low level (image segmentation, class agnostic object proposals) and high level (object detection, semantic segmentation) computer vision tasks. To firstly understand whether and how depth information is helpful for improving computer vision performances, I start research on the image …

    temple Repository record for RGB-DEPTH IMAGE SEGMENTATION AND OBJECT RECOGNITION FOR INDOOR SCENES (opens in a new tab)

  20. Robust deep fusion models for self-driving cars

    … the shortcomings of an RGB camera. Additional object proposals lead the detector to attain higher accuracies in finding and locating road users like cars, pedestrians, and cyclists. Our algorithm further benefits from LIDAR's advantage and shows improved robustness against different lighting …

    texas Repository record for Robust deep fusion models for self-driving cars (opens in a new tab)

Page 1 of 2