Showing 1–20 of 69 results
/ Date/ Name
Mar 3, 2020Towards Noise-resistant Object Detection with Noisy AnnotationsFeb 9, 2020GradMix: Multi-source Transfer across Domains and TasksJul 25, 2018Video Storytelling: Textual Summaries for EventsSep 17, 2020MoPro: Webly Supervised Learning with Momentum PrototypesJan 30, 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language ModelsDec 13, 2018Visual Social Relationship RecognitionAug 23, 2024Identification and validation of the dynamic model of a tendon-driven anthropomorphic fingerJan 28, 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and GenerationDec 13, 2018Learning to Learn from Noisy Labeled DataAug 3, 2017Attention Transfer from Web Images for Video RecognitionSep 6, 2018Unsupervised Learning of View-invariant Action RepresentationsJun 7, 2022Masked Unsupervised Self-training for Label-free Image ClassificationMay 11, 2020Prototypical Contrastive Learning of Unsupervised RepresentationsNov 23, 2020CoMatch: Semi-supervised Learning with Contrastive Graph RegularizationFeb 18, 2020DivideMix: Learning with Noisy Labels as Semi-supervised LearningFeb 9, 2020Weakly-Supervised Multi-Person Action Recognition in 360$^{\circ}$ VideosJul 16, 2021Align before Fuse: Vision and Language Representation Learning with Momentum DistillationAug 2, 2017Dual-Glance Model for Deciphering Social RelationshipsMar 30, 2020Improving out-of-distribution generalization via multi-task self-supervised pretrainingJul 23, 2020The Devil is in Classification: A Simple Framework for Long-tail Object Detection and Instance Segmentation