Computer Vision ECCV 2024 Workshops: Milan, Italy, September 29October 4, 2024, Proceedings, Part XIV [Pehme köide]

.- AirLetters: An Open Video Dataset of Characters Drawn in the Air.
.- RegionGrasp: A Novel Task for Contact Region Controllable Hand
Grasp Generation.
.- Generative Hierarchical Temporal Transformer for Hand Pose and
Action Modeling.
.- Adaptive Multi-Modal Control of Digital Human Hand Synthesis Using a
Region-Aware Cycle Loss.


.- Conditional Hand Image Generation using Latent Space Supervision in Random
Variable Variational Autoencoders.
.- ChildPlay-Hand: A Dataset of Hand Manipulations in the Wild.
.- EMAG: Ego-motion Aware and Generalizable 2D Hand Forecasting
from Egocentric Videos.
.- Disentangling Planning, Driving and Rendering for Photorealistic
Avatar Agents.
.- RGMIM: Region-Guided Masked Image Modeling for Learning
Meaningful Representations from X-Ray Images.
.- A Biologically-inspired Approach to Biomedical Image Segmentation.
.- Human-based Low-Level Visual Processing Neural Network for Image
Segmentation.
.- Glia Cell Inspired Reinforcement Learning Agent for Neural Network
Optimization.
.- Growing Deep Neural Network Considering with Similarity between Neurons.
.- Representation Learning in a Decomposed Encoder Design for
Bio-inspired Hebbian Learning.
.- Reducing Catastrophic Forgetting in Online Class Incremental Learning
Using Self-Distillation.
.- What makes a face look like a hat: Decoupling low-level and high-level
visual properties with image triplets.
.- ScanDDM: Generalised Zero-Shot Neuro-Dynamical Modelling of GoalDirected
Attention.
.- Limited but consistent gains in adversarial robustness by co-training
object recognition models with human EEG.
.- Online Learning via Memory: Retrieval-Augmented Detector Adaptation.
.- AHMF: Adaptive Hybrid-Memory-Fusion Model for Driver Attention
Prediction.
.- Accuracy Improvement of Cell Image Segmentation Using Feedback Former.
.- Variable resolution improves visual question answering under a limited
pixel budget.
.- MOSAIC: Skeleton-based human motion recognition with compositional
representations.
.- Adapting Large Language Model for Cross-Subject Semantic Decoding
from Video-Stimulated fMRI.
.- A System 1 and System 2 Perspective on Continual Learning for Practical
Implementation.
.- Connectivity-Inspired Network for Context-Aware Recognition.
.- Generalizability analysis of deep learning predictions of human brain
responses to augmented and semantically novel visual stimuli.