This book constitutes the proceedings of the 21st International Conference on Advanced Concepts for Intelligent Vision Systems, ACIVS 2023, held in Kumamoto, Japan, during August 2023.
The 31 papers presented in this volume were carefully reviewed and selected from a total of 48 submissions. They were organized in topical sections named: Computer Vision, Affective Computing and Human Interactions, Managing the Biodiversity, Robotics and Drones, Machine Learning.
A hybrid quantum-classical segment-based Stereo Matching
algorithm.- Continuous Exposure for Extreme Low-Light
Imaging.- Semi-supervised Classification and Segmentation of Forest Fire
using Autoencoders.- Descriptive and coherent paragraph generation for image
paragraph captioning using vision transformer and post-processing.- Pyramid
Swin Transformer for Multi-Task: Expanding to more computer vision
tasks.- Person activity classification from an aerial sensor based on a
multi-level deep features.- Person Quick-Search Approach based on a Facial
Semantic Attributes Description.- Age-Invariant Face Recognition using Face
Feature Vectors and Embedded Prototype Subspace Classifiers.- BENet: A
lightweight bottom-up framework for context-aware emotion
recognition.- Yolopoint: Joint Keypoint and Object Detection.- Less-than-one
shot 3d segmentation hijacking a pre-trained space-time memory
network.- Segmentation of Range-Azimuth Maps of FMCW radars with a deep
convolutional neural network.- Segmentation of Range-Azimuth Maps of FMCW
radars with a deep convolutional neural network.- A Single Image
Neuro-Geometric Depth Estimation.- Wave-shaping Neural Activation for
Improved 3D Model Reconstruction from Sparse Point Clouds.- A Deep Learning
Approach to Segment High-Content Images of the E.coli Bacteria.- Multimodal
Emotion Recognition System Through Three Different Channels
(MER-3C).- Multi-Modal Obstacle Avoidance in USVs via Anomaly Detection and
Cascaded Datasets.- A Contrario Mosaic Analysis for Image Forensics.- IRIS
SEGMENTATION TECHNIQUE USING IRIS-UNet METHOD.- Image Acquisition by Image
Retrieval with Color Aesthetics.- Improved Obstructed Facial Feature
Reconstruction for Emotion Recognition with Minimal Change
CycleGANs.- Quality assessment for high dynamic range stereoscopic
omnidirectional image system.- Genetic Programming with Convolutional
Operators for Albatross Nest Detection from Satellite Imaging.- Reinforcement
Learning for truck Eco-driving: a serious game as driving assistance
system.- Underwater mussel segmentation using smoothed shape descriptors with
random forest.- A 2D Cortical Flat Map Space for Computationally Efficient
Mammalian Brain simulation.- Construction of a novel data set for pedestrian
tree species detection using google street view data.- Texture-based Data
Augmentation for Small Datasets.- Multimodal Representations for
Teacher-Guided Compositional Visual Reasoning.- Enhanced Color QR Codes with
Resilient Error Correction for Dirt-Prone Surfaces.
