Full Description
The multi-volume set of LNCS books with volume numbers 15301-15333 constitutes the refereed proceedings of the 27th International Conference on Pattern Recognition, ICPR 2024, held in Kolkata, India, during December 1-5, 2024.
The 963 papers presented in these proceedings were carefully reviewed and selected from a total of 2106 submissions. They deal with topics such as Pattern Recognition; Artificial Intelligence; Machine Learning; Computer Vision; Robot Vision; Machine Vision; Image Processing; Speech Processing; Signal Processing; Video Processing; Biometrics; Human-Computer Interaction (HCI); Document Analysis; Document Recognition; Biomedical Imaging; Bioinformatics
Contents
Optimizing Personalized Robot Actions with Ranking of Trajectories.- Synthesizing operationally safe controllers for human-in-the-loop human-in-the-plant hybrid close loop systems.- Multi-Frequency Fine-Grained Matching for Audio-Visual Segmentation.- Confidence-Guided Feature Alignment for Cloth-Changing Person Re-identification.- Fair Latent Representation Learning with Adaptive Reweighing.- FineFACE: Fair Facial Attribute Classification Leveraging Fine-grained Features.- One-factor Cancelable Biometric Template Protection Scheme for Real-valued Features.- Multi-Teacher Invariance Distillation for Domain-Generalized Action Recognition.- ALS-HAR: Harnessing Wearable Ambient Light Sensors to Enhance IMU-based Human Activity Recognition.- Spatio-Temporal Domain-Aware Network for Skeleton-based Action Representation Learning.- Project and Pool: An Action Localization network for localizing actions in Untrimmed Videos.- Multi-Teacher Importance Preserving Knowledge Distillation for Early Violence Prediction.- Improving Temporal Action Segmentation and Detection with Hierarchical Task Grammar.- Hybrid Human Action Anomaly Detection based on Lightweight GNNs and Machine Learning.- Zero-Shot Spatio-Temporal Action Detection by Enhancing Context-Relation Capability of Vision-Language Models.- Nonlinear progressive denoising: a universal regularized denoising strategy for low PSNR images.- Unified-EGformer: Exposure Guided Lightweight Transformer for Mixed-Exposure Image Enhancement.- Composite Concept Extraction through Backdooring.- Guided SAM: Label-Efficient Part Segmentation.- Multidimensional Cross-Reconstructed Networks for Few-Shot Fine-Grained Image Classification.- Symmetric masking strategy enhances the performance of Masked Image Modeling.- Multiplicative RMSprop using gradient normalization for learning acceleration.- TADIL: Task-Agnostic Domain-Incremental Learning through Task-ID Inference using Transformer Nearest-Centroid Embeddings.- Evidential Federated Learning for Skin Lesion Image Classification.- Adaptive Text Feature Updating for Visual-Language Tracking.- TrajDiffuse: A Conditional Diffusion Model for Environment-Aware Trajectory Prediction.- Principal Graph Neighborhood Aggregation for Underwater Moving Object Detection.- Dynamic Loss Decay based Robust Oriented Object Detection on Remote Sensing Images with Noisy Labels.- Environment-Independent Fusion for Robust Object Detection in Adverse Environments.- Transformer-based RGB and LiDAR Fusion for Enhanced Object Detection.
