Object (computer science)

About: Object (computer science) is a research topic. Over the lifetime, 106024 publications have been published within this topic receiving 1360115 citations. The topic is also known as: obj & Rq.

RepMet: Representative-Based Metric Learning for Classification and Few-Shot Object Detection

Abstract: Distance metric learning (DML) has been successfully applied to object classification, both in the standard regime of rich training data and in the few-shot scenario, where each category is represented by only a few examples. In this work, we propose a new method for DML that simultaneously learns the backbone network parameters, the embedding space, and the multi-modal distribution of each of the training categories in that space, in a single end-to-end training process. Our approach outperforms state-of-the-art methods for DML-based object classification on a variety of standard fine-grained datasets. Furthermore, we demonstrate the effectiveness of our approach on the problem of few-shot object detection, by incorporating the proposed DML architecture as a classification head into a standard object detection model. We achieve the best results on the ImageNet-LOC dataset compared to strong baselines, when only a few training examples are available. We also offer the community a new episodic benchmark based on the ImageNet dataset for the few-shot object detection task.

Messaging system and method

Abstract: A method of cross-platform messaging including receiving, by a messaging system, at least one initial message having a message format, an initial message layout and data indicative of at least one user associated with the at least one initial message, and before delivery to a destination communication device associated with the at least one user, converting, by the messaging system, an initial message into an adapted message, and facilitating, by the messaging system, delivery of the adapted message to the destination communication device. The adapted message is characterized by, at least, an adapted message layout, and the adapted message layout differs from the initial message layout in a characteristic associated with respective message layout such as number of media objects, a graphical image of a media object, a size of a placeholder related to a media object, and a location of a media object within a respective message layout.

Object and File Management in the EXODUS Extensible Database System

Abstract: This paper describes the design of the object-oriented storage component of EXODUS, an extensible database management system currently under development at the University of Wisconsin. The basic abstraction in the EXODUS storage system is the storage object, an uninterpreted variable-length record of arbitrary size; higher level abstractions such as records and indices are supported via the storage object abstraction. One of the key design features described here is a scheme for managing large dynamic objects, as storage objects can occupy many disk pages and can grow or shrink at arbitrary points. The data structure and algorithms used to support such objects are described, and performance results from a preliminary prototype of the EXODUS large-object management scheme are presented. A scheme for maintaining versions of large objects is also described. The file structure used in the EXODUS storage system, which provides a mechanism for grouping and sequencing through a set of related storage objects and the EXODUS approach to buffer management, concurrency control, and recovery, both for small and large objects are discussed. 30 refs., 13 figs.

A Thousand Frames in Just a Few Words: Lingual Description of Videos through Latent Topics and Sparse Object Stitching

Abstract: The problem of describing images through natural language has gained importance in the computer vision community. Solutions to image description have either focused on a top-down approach of generating language through combinations of object detections and language models or bottom-up propagation of keyword tags from training images to test images through probabilistic or nearest neighbor techniques. In contrast, describing videos with natural language is a less studied problem. In this paper, we combine ideas from the bottom-up and top-down approaches to image description and propose a method for video description that captures the most relevant contents of a video in a natural language description. We propose a hybrid system consisting of a low level multimodal latent topic model for initial keyword annotation, a middle level of concept detectors and a high level module to produce final lingual descriptions. We compare the results of our system to human descriptions in both short and long forms on two datasets, and demonstrate that final system output has greater agreement with the human descriptions than any single level.

Video Object Segmentation Using Space-Time Memory Networks

Abstract: We propose a novel solution for semi-supervised video object segmentation. By the nature of the problem, available cues (e.g. video frame(s) with object masks) become richer with the intermediate predictions. However, the existing methods are unable to fully exploit this rich source of information. We resolve the issue by leveraging memory networks and learn to read relevant information from all available sources. In our framework, the past frames with object masks form an external memory, and the current frame as the query is segmented using the mask information in the memory. Specifically, the query and the memory are densely matched in the feature space, covering all the space-time pixel locations in a feed-forward fashion. Contrast to the previous approaches, the abundant use of the guidance information allows us to better handle the challenges such as appearance changes and occlussions. We validate our method on the latest benchmark sets and achieved the state-of-the-art performance (overall score of 79.4 on Youtube-VOS val set, J of 88.7 and 79.2 on DAVIS 2016/2017 val set respectively) while having a fast runtime (0.16 second/frame on DAVIS 2016 val set).