Pattern Recognition 27th International Conference, ICPR 2024, Kolkata, India, December 1–5, 2024, Proceedings, Part III

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.

Deep Multi-order Context-aware Kernel Network for Multi-label Classification.- Classifier Enhanced Deep Learning Model for Erythroblast Differentiation with Limited Data.- PiExtract: An End-to-End Data Extraction pipeline for Pie-Charts.- Machine Learning Solutions for Predicting Bankruptcy  in Indian Firms.- Efficient Object Detection via Fine-grained Regularization with Global Initialization.- On Trace of PGD-Like Adversarial Attacks.- CAB-KWS: Contrastive Augmentation: An Unsupervised Learning Approach for Keyword Spotting in Speech Technology.- Deep Learning in Automated Worm Identification and Tracking for C. Elegan Mating Behaviour Analysis.- Interactive-Time Text-Guided Editing of 3D Face.- Unlearning Vision Transformers without Retaining Data via Low-Rank Decompositions.- gWaveNet: Classification of Gravity Waves from Noisy Satellite Data using Custom Kernel Integrated Deep Learning Method.- Neural-Code PIFu: High-Fidelity Single Image 3D Human Reconstruction via Neural Code Integration.- Sea-ShipNet: Detect Any Ship in SAR Images.- Semantic Correlation Adaptation for Union-Set Multi-Label Image Recognition.- FedSC: Federated Generalized Face Anti-Spoofing via Shuffled Codebook.- LoHoSC: Low Order High Order Style Consistency for Syn-to-Real Domain Generalized Semantic Segmentation.- Incorporating Spatial Locality into Self-Attention for Training Vision Transformer on Small-Scale Datasets.- Cross-Domain Calibration and Boundary Denoising Network for Weakly Supervised Semantic Segmentation.- EFLLD-NET: Enhancing Few-Shot Learning With Local Descriptors.- Using Multiscale Information for Improved Optimization-based Image Attribution.- Split-DNN Computing for Video Analytics.- Task-Aware Local Descriptors Reconstruction Network for Few-Shot Find-Grained Image Classification.- TRIGS: Trojan Identification from Gradient-based Signatures.- Multifaceted Anchor Nodes Attack on Graph Neural Networks: A Budget-efficient Approach.- Causal Attentive Group Recommendation.- E2DAS: An Efficient Equivariant Dynamic Aggregation Saliency Model for Omnidirectional Images.- FewConv: Efficient variant convolution for few-shot image generation.- FixPix: Fixing Bad Pixels using Deep Learning.- Real-world Coarse to Fine-Grained Source-Free Multidomain Adaptation.