LEARNING SCENE HIERARCHY: FROM CATEGORY-LEVEL SIMILARITY TO ATTRIBUTE-LEVEL SIMILARITY

LEARNING SCENE HIERARCHY: FROM CATEGORY-LEVEL SIMILARITY TO ATTRIBUTE-LEVEL SIMILARITY

Ph.D

Saved in:

書目詳細資料
主要作者:	LENG YUSONG
其他作者:	INTEGRATIVE SCIENCES & ENGINEERING PROG
出版:	2019
主題:	scene hierarchy, scene understanding, metric learning, triplet loss, deep embedding, interpretable embedding
在線閱讀:	https://scholarbank.nus.edu.sg/handle/10635/163066
標簽:	添加標簽沒有標簽, 成為第一個標記此記錄!

相似書籍

DEEP VISUAL SCENE UNDERSTANDING: CLASSIFICATION, SEGMENTATION AND PREDICTION
由: JIN XIAOJIE
出版: (2018)

Toward holistic scene understanding: Feedback enabled cascaded classification models
由: Li C., et al.
出版: (2018)

TOWARDS INTELLIGENT SURGERY: SURGICAL SCENE UNDERSTANDING WITH DEEP LEARNING
由: XU MENGYA
出版: (2024)

LEARNING STRUCTURED REPRESENTATIONS OF VISUAL SCENES
由: CHIOU MENG-JIUN
出版: (2022)

DeepStyle: User style embedding for authorship attribution of short texts
由: HU, Zhiqiang, et al.
出版: (2020)

3D reasoning from blocks to stability
由: Jia Z., et al.
出版: (2018)

HUMAN-CENTERED SOCIAL SCENE UNDERSTANDING
由: XU BINGJIE
出版: (2019)

An efficient approach for scene categorization based on discriminative codebook learning in bag-of-words framework
由: Li, Zhen, et al.
出版: (2016)

Hybrid DNN training using both synthetic and real construction images to overcome training data shortage
由: Kim, Jinwoo, et al.
出版: (2023)

AI-ASSISTED 3D RECONSTRUCTION AND SCENE UNDERSTANDING FOR ROBOTIC NAVIGATION IN INDOOR ENVIRONMENTS
由: HU DIFENG
出版: (2025)

Visual Attention Prediction Using Saliency Determination of Scene Understanding for Social Robots
由: He, H., et al.
出版: (2014)

Using camera settings templates ("Scene Modes") for image scene classification of photographs taken on manual/expert settings
由: Ku, W., et al.
出版: (2013)

SCENE UNDERSTANDING THROUGH MULTIMODAL REASONING FOR ROBOTIC SURGERY
由: SEENIVASAN LALITHKUMAR
出版: (2024)

Revisiting depth layers from occlusions
由: Kowdle A., et al.
出版: (2018)

Ensemble of pruned models for low-complexity acoustic scene classification
由: Ooi, Kenneth, et al.
出版: (2021)

Detection and rectification of arbitrary shaped scene texts by using text keypoints and links
由: Xue, Chuhui, et al.
出版: (2022)

RAPID SCENE PERCEPTION DURING ABRUPT SCENE CHANGES
由: ESTHER WU XIU WEN
出版: (2016)

Age-related differences in functional connectivity during scene encoding
由: Leow, Dayton Wei Yang
出版: (2014)

Visual attention and perception in scene understanding for social robotics
由: HE HONGSHENG
出版: (2012)

Occlusion-free road segmentation leveraging semantics for autonomous vehicles
由: Wang, Kewei, et al.
出版: (2020)

Beyond Bag-of-Words: combining generative and discriminative models for scene categorization
由: Li, Zhen, et al.
出版: (2016)

3D SHAPE COMPLETION WITH DEEP NEURAL NETWORKS
由: WANG XIAOGANG
出版: (2021)

Toward achieving robust low-level and high-level scene parsing
由: Shuai, Bing, et al.
出版: (2020)

A new run length based method for scene text detection
由: Basavanna, M., et al.
出版: (2013)

The Excluded Minors for Isometric Realizability in the Plane
由: Fiorini, Samuel, et al.
出版: (2017)

Context-Aware REpresentation: Jointly learning item features and selection from triplets
由: ALVES, Rodrigo, et al.
出版: (2024)

Scene recognition by semantic visual words
由: Farahzadeh, Elahe, et al.
出版: (2015)

Visual navigation with multiple goals based on deep reinforcement learning
由: Rao, Zhenhuan, et al.
出版: (2022)

A framework for video scene boundary detection
由: Wang, J., et al.
出版: (2013)

Visiting the Invisible: layer-by-layer completed scene decomposition
由: Zheng, Chuanxia, et al.
出版: (2023)

RIM: Reconfigurable Instruction Memory Hierarchy for Embedded Systems
由: GE ZHIGUO
出版: (2010)

A cinematic-based framework for scene boundary detection in video
由: Wang, J., et al.
出版: (2013)

Real scene sign recognition
由: Li, L., et al.
出版: (2013)

Fast scene labeling via structural inference
由: ZHANG, Huaidong, et al.
出版: (2021)

Discovering Class-Specific Spatial Layouts for Scene Recognition
由: Weng, Chaoqun, et al.
出版: (2017)

SceneDreamer: unbounded 3D scene generation from 2D image collections
由: Chen, Zhaoxi, et al.
出版: (2024)

Hierarchical object groups for scene classification
由: Sadovnik A., et al.
出版: (2018)

A saliency-driven robotic head with bio-inspired saccadic behaviors for social robotics
由: He, H., et al.
出版: (2014)

New edge characteristics for scene and object classification
由: Shivakumara, P., et al.
出版: (2013)

Constructing holistic spatio-temporal scene graph for video semantic role labeling
由: ZHAO, Yu, et al.
出版: (2023)