Description
Circular Smooth Label (CSL) is a classification-based rotation detection technique for arbitrary-oriented object detection. It is used for circularly distributed angle classification and addresses the periodicity of the angle and increases the error tolerance to adjacent angles.
Papers Using This Method
Moving Beyond Next-Token Prediction: Transformers are Context-Sensitive Language Generators2025-04-15Swin-MSTP: Swin transformer with multi-scale temporal perception for continuous sign language recognition2025-02-07A Chinese Continuous Sign Language Dataset Based on Complex Environments2024-09-18Simulation-based Benchmarking for Causal Structure Learning in Gene Perturbation Experiments2024-07-08Contextualized Sequence Likelihood: Enhanced Confidence Scores for Natural Language Generation2024-06-03Color Space Learning for Cross-Color Person Re-Identification2024-05-15Improving Continuous Sign Language Recognition with Adapted Image Models2024-04-12TimeCSL: Unsupervised Contrastive Learning of General Shapelets for Explorable Time Series Analysis2024-04-07TCNet: Continuous Sign Language Recognition from Trajectories and Correlated Regions2024-03-18Realigning Confidence with Temporal Saliency Information for Point-Level Weakly-Supervised Temporal Action Localization2024-01-01Shapley-PC: Constraint-based Causal Structure Learning with a Shapley Inspired Framework2023-12-18CSL: Class-Agnostic Structure-Constrained Learning for Segmentation Including the Unseen2023-12-09Causal Structure Learning Supervised by Large Language Model2023-11-20Real-Time Construction Algorithm of Co-Occurrence Network Based on Inverted Index2023-08-17AdaBrowse: Adaptive Video Browser for Efficient Continuous Sign Language Recognition2023-08-16Part-Aware Transformer for Generalizable Person Re-identification2023-08-07Machine learning reveals features of spinon Fermi surface2023-06-05Continuous Sign Language Recognition with Correlation Network2023-03-06Improving Continuous Sign Language Recognition with Consistency Constraints and Signer Removal2022-12-26Self-Emphasizing Network for Continuous Sign Language Recognition2022-11-30