Showing 1–19 of 19 results
/ Date/ Name
Jul 5, 2022Towards Realistic Semi-Supervised LearningJan 15, 2021In Defense of Pseudo-Labeling: An Uncertainty-Aware Pseudo-label Selection Framework for Semi-Supervised LearningMar 21, 2024VidLA: Video-Language Alignment at ScaleJul 5, 2022OpenLDN: Learning to Discover Novel Classes for Open-World Semi-Supervised LearningMar 1, 2021Exploring Complementary Strengths of Invariant and Equivariant Representations for Few-Shot LearningMar 28, 2023TimeBalance: Temporally-Invariant and Temporally-Distinctive Video Representations for Semi-Supervised Action RecognitionSep 2, 2024FinePseudo: Improving Pseudo-Labelling through Temporal-Alignablity for Semi-Supervised Fine-Grained Action RecognitionJan 20, 2021TCLR: Temporal Contrastive Learning for Video RepresentationAug 5, 2024GAReT: Cross-view Video Geolocalization with Adapters and Auto-Regressive TransformersDec 3, 2025Rethinking Prompt Design for Inference-time Scaling in Text-to-Visual GenerationSep 7, 2023CDFSL-V: Cross-Domain Few-Shot Learning for VideosJul 18, 2024X-Former: Unifying Contrastive and Reconstruction Learning for MLLMsJul 12, 2024Open Vocabulary Multi-Label Video ClassificationAug 24, 2023Preserving Modality Structure Improves Multi-Modal LearningApr 23, 2020Gabriella: An Online System for Real-Time Activity Detection in Untrimmed Security VideosMar 28, 2022UNICON: Combating Label Noise Through Uniform Selection and Contrastive LearningOct 12, 2023Is ImageNet worth 1 video? Learning strong image encoders from 1 long unlabelled videoAug 31, 2025CompSlider: Compositional Slider for Disentangled Multiple-Attribute Image GenerationMay 27, 2025Unified Alignment Protocol: Making Sense of the Unlabeled Data in New Domains