Título :	15th Asian Conference on Computer Vision, Kyoto, Japan, November 30 – December 4, 2020, Revised Selected Papers, Part VI
Tipo de documento:	documento electrónico
Autores:	Ishikawa, Hiroshi, ; Liu, Cheng-Lin, ; Pajdla, Tomas, ; Shi, Jianbo,
Mención de edición:	1 ed.
Editorial:	[s.l.] : Springer
Fecha de publicación:	2021
Número de páginas:	XVIII, 705 p. 262 ilustraciones, 252 ilustraciones en color.
ISBN/ISSN/DL:	978-3-030-69544-6
Nota general:	Libro disponible en la plataforma SpringerLink. Descarga y lectura en formatos PDF, HTML y ePub. Descarga completa o por capítulos.
Palabras clave:	Visión por computador  Ingeniería Informática  Red de computadoras  Inteligencia artificial  Sistemas de reconocimiento de patrones  Software de la aplicacion  Ingeniería Informática y Redes  Reconocimiento de patrones automatizado  Aplicaciones informáticas y de sistemas de información
Índice Dewey:	006.37 Visión artificial
Resumen:	El conjunto de seis volúmenes de LNCS 12622-12627 constituye las actas de la 15.ª Conferencia asiática sobre visión artificial, ACCV 2020, celebrada en Kioto (Japón) en noviembre/diciembre de 2020.* El total de 254 contribuciones se revisó cuidadosamente y se seleccionó de 768 presentaciones durante dos rondas de revisión y mejora. Los artículos se centran en los siguientes temas: Parte I: visión artificial en 3D; segmentación y agrupamiento Parte II: visión de bajo nivel, procesamiento de imágenes; movimiento y seguimiento Parte III: reconocimiento y detección; optimización, métodos estadísticos y aprendizaje; visión robótica Parte IV: aprendizaje profundo para visión artificial, modelos generativos para visión artificial Parte V: rostro, pose, acción y gesto; análisis de vídeo y reconocimiento de eventos; análisis de imágenes biomédicas Parte VI: aplicaciones de la visión artificial; visión para X; conjuntos de datos y análisis de rendimiento *La conferencia se celebró de forma virtual.
Nota de contenido:	Applications of Computer Vision, Vision for X -- Query by Strings and Return Ranking Word Regions with Only One Look -- Single-Image Camera Response Function Using Prediction Consistency and Gradual Refinement -- FootNet: An efficient convolutional network for multiview 3D foot reconstruction -- Synthetic-to-real domain adaptation for lane detection -- RAF-AU Database: In-the-Wild Facial Expressions with Subjective Emotion Judgement and Objective AU Annotations -- DoFNet: Depth of Field Difference Learning for Detecting Image Forgery -- Explaining image classifiers by removing input features using generative models -- Do We Need Sound for Sound Source Localization? -- Modular Graph Attention Network for Complex Visual Relational Reasoning -- CloTH-VTON: Clothing Three-dimensional reconstruction for Hybrid image-based Virtual Try-ON -- Multi-label X-ray Imagery Classification via Bottom-up Attention and Meta Fusion -- Learning End-to-End Action Interaction by Paired-Embedding Data Augmentation -- Sketch-to-Art: Synthesizing Stylized Art Images From Sketches -- Road Obstacle Detection Method Based on an Autoencoder with Semantic Segmentation -- SpotPatch: Parameter-Efficient Transfer Learning for Mobile Object Detection -- Trainable Structure Tensors for Autonomous Baggage Threat Detection Under Extreme Occlusion -- Audiovisual Transformer with Instance Attention for Audio-Visual Event Localization -- Watch, read and lookup: learning to spot signs from multiple supervisors -- Domain-transferred Face Augmentation Network -- Pose Correction Algorithm for Relative Frames between Keyframes in SLAM -- Dense-Scale Feature Learning in Person Re-Identification -- Class-incremental Learning with Rectified Feature-Graph Preservation -- Patch SVDD: Patch-level SVDD for Anomaly Detection and Segmentation -- Towards Robust Fine-grained Recognition by Maximal Separation of Discriminative Features -- Visually Guided Sound Source Separation using Cascaded Opponent Filter Network -- Channel Recurrent Attention Networks for Video Pedestrian Retrieval -- In Defense of LSTMs for Addressing Multiple Instance Learning Problems -- Addressing Class Imbalance in Scene Graph Parsing by Learning to Contrast and Score -- Show, Conceive and Tell: Image Captioning with Prospective Linguistic Information -- Datasets and Performance Analysis -- RGB-T Crowd Counting from Drone: A Benchmark and MMCCN Network -- Webly Supervised Semantic Embeddings for Large Scale Zero-Shot Learning -- Compensating for the Lack of Extra Training Data by Learning Extra Representation -- Class-Wise Difficulty-Balanced Loss for Solving Class-Imbalance -- OpenTraj: Assessing Prediction Complexity in Human Trajectories Datasets -- Pre-training without Natural Images -- TTPLA: An Aerial-Image Dataset for Detection and Segmentation of Transmission Towers and Power Lines -- A Day on Campus - An Anomaly Detection Dataset for Events in a Single Camera -- A Benchmark and Baseline for Language-Driven Image Editing -- Self-supervised Learning of Orc-Bert Augmentator for Recognizing Few-Shot Oracle Characters -- Understanding Motion in Sign Language: A New Structured Translation Dataset -- FreezeNet: Full Performance by Reduced Storage Costs.
En línea:	https://link-springer-com.biblioproxy.umanizales.edu.co/referencework/10.1007/97 [...]
Link:	https://biblioteca.umanizales.edu.co/ils/opac_css/index.php?lvl=notice_display&i

15th Asian Conference on Computer Vision, Kyoto, Japan, November 30 – December 4, 2020, Revised Selected Papers, Part VI [documento electrónico] / Ishikawa, Hiroshi, ; Liu, Cheng-Lin, ; Pajdla, Tomas, ; Shi, Jianbo,  . -  1 ed.  . - [s.l.] : Springer, 2021 . - XVIII, 705 p. 262 ilustraciones, 252 ilustraciones en color.
ISBN : 978-3-030-69544-6
Libro disponible en la plataforma SpringerLink. Descarga y lectura en formatos PDF, HTML y ePub. Descarga completa o por capítulos.

Palabras clave:	Visión por computador  Ingeniería Informática  Red de computadoras  Inteligencia artificial  Sistemas de reconocimiento de patrones  Software de la aplicacion  Ingeniería Informática y Redes  Reconocimiento de patrones automatizado  Aplicaciones informáticas y de sistemas de información
Índice Dewey:	006.37 Visión artificial
Resumen:	El conjunto de seis volúmenes de LNCS 12622-12627 constituye las actas de la 15.ª Conferencia asiática sobre visión artificial, ACCV 2020, celebrada en Kioto (Japón) en noviembre/diciembre de 2020.* El total de 254 contribuciones se revisó cuidadosamente y se seleccionó de 768 presentaciones durante dos rondas de revisión y mejora. Los artículos se centran en los siguientes temas: Parte I: visión artificial en 3D; segmentación y agrupamiento Parte II: visión de bajo nivel, procesamiento de imágenes; movimiento y seguimiento Parte III: reconocimiento y detección; optimización, métodos estadísticos y aprendizaje; visión robótica Parte IV: aprendizaje profundo para visión artificial, modelos generativos para visión artificial Parte V: rostro, pose, acción y gesto; análisis de vídeo y reconocimiento de eventos; análisis de imágenes biomédicas Parte VI: aplicaciones de la visión artificial; visión para X; conjuntos de datos y análisis de rendimiento *La conferencia se celebró de forma virtual.
Nota de contenido:	Applications of Computer Vision, Vision for X -- Query by Strings and Return Ranking Word Regions with Only One Look -- Single-Image Camera Response Function Using Prediction Consistency and Gradual Refinement -- FootNet: An efficient convolutional network for multiview 3D foot reconstruction -- Synthetic-to-real domain adaptation for lane detection -- RAF-AU Database: In-the-Wild Facial Expressions with Subjective Emotion Judgement and Objective AU Annotations -- DoFNet: Depth of Field Difference Learning for Detecting Image Forgery -- Explaining image classifiers by removing input features using generative models -- Do We Need Sound for Sound Source Localization? -- Modular Graph Attention Network for Complex Visual Relational Reasoning -- CloTH-VTON: Clothing Three-dimensional reconstruction for Hybrid image-based Virtual Try-ON -- Multi-label X-ray Imagery Classification via Bottom-up Attention and Meta Fusion -- Learning End-to-End Action Interaction by Paired-Embedding Data Augmentation -- Sketch-to-Art: Synthesizing Stylized Art Images From Sketches -- Road Obstacle Detection Method Based on an Autoencoder with Semantic Segmentation -- SpotPatch: Parameter-Efficient Transfer Learning for Mobile Object Detection -- Trainable Structure Tensors for Autonomous Baggage Threat Detection Under Extreme Occlusion -- Audiovisual Transformer with Instance Attention for Audio-Visual Event Localization -- Watch, read and lookup: learning to spot signs from multiple supervisors -- Domain-transferred Face Augmentation Network -- Pose Correction Algorithm for Relative Frames between Keyframes in SLAM -- Dense-Scale Feature Learning in Person Re-Identification -- Class-incremental Learning with Rectified Feature-Graph Preservation -- Patch SVDD: Patch-level SVDD for Anomaly Detection and Segmentation -- Towards Robust Fine-grained Recognition by Maximal Separation of Discriminative Features -- Visually Guided Sound Source Separation using Cascaded Opponent Filter Network -- Channel Recurrent Attention Networks for Video Pedestrian Retrieval -- In Defense of LSTMs for Addressing Multiple Instance Learning Problems -- Addressing Class Imbalance in Scene Graph Parsing by Learning to Contrast and Score -- Show, Conceive and Tell: Image Captioning with Prospective Linguistic Information -- Datasets and Performance Analysis -- RGB-T Crowd Counting from Drone: A Benchmark and MMCCN Network -- Webly Supervised Semantic Embeddings for Large Scale Zero-Shot Learning -- Compensating for the Lack of Extra Training Data by Learning Extra Representation -- Class-Wise Difficulty-Balanced Loss for Solving Class-Imbalance -- OpenTraj: Assessing Prediction Complexity in Human Trajectories Datasets -- Pre-training without Natural Images -- TTPLA: An Aerial-Image Dataset for Detection and Segmentation of Transmission Towers and Power Lines -- A Day on Campus - An Anomaly Detection Dataset for Events in a Single Camera -- A Benchmark and Baseline for Language-Driven Image Editing -- Self-supervised Learning of Orc-Bert Augmentator for Recognizing Few-Shot Oracle Characters -- Understanding Motion in Sign Language: A New Structured Translation Dataset -- FreezeNet: Full Performance by Reduced Storage Costs.
En línea:	https://link-springer-com.biblioproxy.umanizales.edu.co/referencework/10.1007/97 [...]
Link:	https://biblioteca.umanizales.edu.co/ils/opac_css/index.php?lvl=notice_display&i