Computer Vision – ECCV 2020 Workshops

Glasgow, UK, August 23–28, 2020, Proceedings, Part VI

Häftad, Engelska, 2021

719 kr

Beställningsvara. Skickas inom 10-15 vardagar

Fri frakt för medlemmar vid köp för minst 249 kr.

The 6-volume set, comprising the LNCS books 12535 until 12540, constitutes the refereed proceedings of 28 out of the 45 workshops held at the 16th European Conference on Computer Vision, ECCV 2020. The conference was planned to take place in Glasgow, UK, during August 23-28, 2020, but changed to a virtual format due to the COVID-19 pandemic.The 249 full papers, 18 short papers, and 21 further contributions included in the workshop proceedings were carefully reviewed and selected from a total of 467 submissions. The papers deal with diverse computer vision topics. Part VI focusses on reassessing the evaluation of object detection; computer vision problems in plant phenotyping; fair face recognition and analysis; and perception through structured generative models.

Produktinformation

Utgivningsdatum2021-01-05
Mått155 x 235 x undefined mm
FormatHäftad
SpråkEngelska
SerieImage Processing, Computer Vision, Pattern Recognition, and Graphics
Antal sidor560
FörlagSpringer Nature Switzerland AG
ISBN9783030654139

Tillhör följande kategorier

W36 - Beyond mAP: Reassessing the Evaluation of Object Detection.- Assessing Box Merging Strategies and Uncertainty Estimation Methods in Multimodel Object Detection.- Implementing Planning KL-Divergence.- ODIN: an Object Detection and Instance Segmentation Diagnosis Framework.- Shift Equivariance in Object Detection.- Probabilistic Object Detection with an Ensemble of Experts.- EPrOD: Evolved Probabilistic Object Detector with Diverse Samples.- Probabilistic Object Detection via Deep Ensembles.- W37 - Imbalance Problems in Computer Vision.- A Machine Learning Approach to Assess Student Group Collaboration Using Individual Level Behavioral Cues.- Remix: Rebalanced Mixup.- Generalized Many-Way Few-Shot Video Classification.- GAN-Based Anomaly Detection in Imbalance Problems.- Active Class Incremental Learning for Imbalanced Datasets.- Knowledge Distillation for Multi-task Learning.- Mitigating Dataset Imbalance via Joint Generation and Classification.- W40 - Computer Vision Problems inPlant Phenotyping.- Patch-based CNN evaluation for bark classification.- Improving Pixel Embedding Learning through Intermediate Distance Regression Supervision for Instance Segmentation.- Time Series Modeling for Phenotypic Prediction and PhenotypeGenotype Mapping using Neural Networks.- 3D Plant Phenotyping: All You Need is Labelled Point Cloud Data.- Phenotyping problems of parts-per-object count.- Abiotic Stress Prediction from RGB-T Images of Banana Plantlets.- Sorghum Segmentation by Skeleton Extraction.- Towards Confirmable Automated Plant Cover Determination.- Unsupervised Domain Adaptation For Plant Organ Counting.- Automatic Differentiation of Damaged and Unharmed Grapes Using RGB Images and Convolutional Neural Networks.- Germination Detection of Seedlings in Soil: A System, Dataset and Challenge.- Detection in agricultural contexts: Are we close to human level.- AutoCount: Unsupervised Segmentation and Counting of Organs in Field Images.- CorNet: Unsupervised Deep Homography Estimation for Agricultural Aerial Imagery.- Expanding CNN-based Plant Phenotyping Systems to Larger Environments.- Weakly Supervised Minirhizotron Image Segmentation with MIL-CAM.- BTWD: Bag of Tricks for Wheat Detection.- W41 - Fair Face Recognition and Analysis.- FairFace Challenge at ECCV 2020: Analyzing Bias in Face Recognition.- AsArcFace: Asymmetric Additive Angular Margin Loss for Fairface Recognition.- Fair Face Recognition Using Data Balancing, Enhancement and Fusion.- Investigating Bias and Fairness in Facial Expression Recognition.- Disguised Face Verification using Inverse Disguise Quality.- W44 - Perception Through Structured Generative Models.- Toward Continuous-Time Representations of Human Motion.- DisCont: Self-Supervised Visual Attribute Disentanglement using Context Vectors.- 3D Noise and Adversarial Supervision Is All You Need for Multi-Modal Semantic Image Synthesis.