UP - logo

Rezultati iskanja

Osnovno iskanje    Izbirno iskanje   
Iskalna
zahteva
Knjižnica

Trenutno NISTE avtorizirani za dostop do e-virov UPUK. Za polni dostop se PRIJAVITE.

3 4 5 6 7
zadetkov: 225.415
41.
  • A survey on online learning... A survey on online learning for visual tracking
    Abbass, Mohammed Y.; Kwon, Ki-Chul; Kim, Nam ... The Visual computer, 05/2021, Letnik: 37, Številka: 5
    Journal Article
    Recenzirano

    Visual object tracking has become one of the most active research topics in computer vision, which has been growing in commercial development as well as academic research. Many visual trackers have ...
Celotno besedilo
42.
  • Group Normalization Group Normalization
    Wu, Yuxin; He, Kaiming International journal of computer vision, 03/2020, Letnik: 128, Številka: 3
    Journal Article
    Recenzirano

    Batch Normalization (BN) is a milestone technique in the development of deep learning, enabling various networks to train. However, normalizing along the batch dimension introduces problems—BN’s ...
Celotno besedilo
43.
  • HOTA: A Higher Order Metric... HOTA: A Higher Order Metric for Evaluating Multi-object Tracking
    Luiten, Jonathon; Os̆ep, Aljos̆a; Dendorfer, Patrick ... International journal of computer vision, 02/2021, Letnik: 129, Številka: 2
    Journal Article
    Recenzirano
    Odprti dostop

    Multi-object tracking (MOT) has been notoriously difficult to evaluate. Previous metrics overemphasize the importance of either detection or association. To address this, we present a novel MOT ...
Celotno besedilo

PDF
44.
  • Compositional Convolutional... Compositional Convolutional Neural Networks: A Robust and Interpretable Model for Object Recognition Under Occlusion
    Kortylewski, Adam; Liu, Qing; Wang, Angtian ... International journal of computer vision, 03/2021, Letnik: 129, Številka: 3
    Journal Article
    Recenzirano
    Odprti dostop

    Computer vision systems in real-world applications need to be robust to partial occlusion while also being explainable. In this work, we show that black-box deep convolutional neural networks (DCNNs) ...
Celotno besedilo

PDF
45.
  • Knowledge Distillation: A S... Knowledge Distillation: A Survey
    Gou, Jianping; Yu, Baosheng; Maybank, Stephen J. ... International journal of computer vision, 06/2021, Letnik: 129, Številka: 6
    Journal Article
    Recenzirano
    Odprti dostop

    In recent years, deep neural networks have been successful in both industry and academia, especially for computer vision tasks. The great success of deep learning is mainly due to its scalability to ...
Celotno besedilo

PDF
46.
  • Deep Learning Based Recomme... Deep Learning Based Recommender System
    Zhang, Shuai; Yao, Lina; Sun, Aixin ... ACM computing surveys, 02/2019, Letnik: 52, Številka: 1
    Journal Article
    Recenzirano
    Odprti dostop

    With the growing volume of online information, recommender systems have been an effective strategy to overcome information overload. The utility of recommender systems cannot be overstated, given ...
Celotno besedilo

PDF
47.
  • Human Action Recognition an... Human Action Recognition and Prediction: A Survey
    Kong, Yu; Fu, Yun International journal of computer vision, 05/2022, Letnik: 130, Številka: 5
    Journal Article
    Recenzirano
    Odprti dostop

    Derived from rapid advances in computer vision and machine learning, video analysis tasks have been moving from inferring the present state to predicting the future state. Vision-based action ...
Celotno besedilo
48.
  • Semantic Understanding of S... Semantic Understanding of Scenes Through the ADE20K Dataset
    Zhou, Bolei; Zhao, Hang; Puig, Xavier ... International journal of computer vision, 03/2019, Letnik: 127, Številka: 3
    Journal Article
    Recenzirano
    Odprti dostop

    Semantic understanding of visual scenes is one of the holy grails of computer vision. Despite efforts of the community in data collection, there are still few image datasets covering a wide range of ...
Celotno besedilo

PDF
49.
  • Recent Advances of Monocula... Recent Advances of Monocular 2D and 3D Human Pose Estimation: A Deep Learning Perspective
    Liu, Wu; Bao, Qian; Sun, Yu ... ACM computing surveys, 11/2022, Letnik: 55, Številka: 4
    Journal Article
    Recenzirano
    Odprti dostop

    Estimation of the human pose from a monocular camera has been an emerging research topic in the computer vision community with many applications. Recently, benefiting from the deep learning ...
Celotno besedilo
50.
  • Exposing Semantic Segmentat... Exposing Semantic Segmentation Failures via Maximum Discrepancy Competition
    Yan, Jiebin; Zhong, Yu; Fang, Yuming ... International journal of computer vision, 05/2021, Letnik: 129, Številka: 5
    Journal Article
    Recenzirano
    Odprti dostop

    Semantic segmentation is an extensively studied task in computer vision, with numerous methods proposed every year. Thanks to the advent of deep learning in semantic segmentation, the performance on ...
Celotno besedilo

PDF
3 4 5 6 7
zadetkov: 225.415

Nalaganje filtrov