Weakly Supervised Learning

Task Programming: Learning Data Efficient Behavior Representations CVPR 2021 Temporal Action Detection With Multi-Level Supervision ICCV 2021 Temporal Action Segmentation From Timestamp Supervision CVPR 2021 Temporal-aware Language Representation Learning From Crowdsourced Labels ACL 2021 Temporal Cue Guided Video Highlight Detection With Low-Rank Audio-Visual Fusion ICCV 2021 Testing Cross-Database Semantic Parsers With Canonical Utterances EMNLP 2021 Testing Using Privileged Information by Adapting Features With Statistical Dependence ICCV 2021 TexSmart: A System for Enhanced Natural Language Understanding ACL 2021 The Blessings of Unlabeled Background in Untrimmed Videos CVPR 2021 The Impact of Record Linkage on Learning from Feature Partitioned Data ICML 2021 The LIUM Human Active Correction Platform for Speaker Diarization Interspeech 2021 The Surprising Impact of Mask-Head Architecture on Novel Class Segmentation ICCV 2021 TIDOT: A Teacher Imitation Learning Approach for Domain Adaptation with Optimal Transport IJCAI 2021 Time to Transfer: Predicting and Evaluating Machine-Human Chatting Handoff AAAI 2021 Topic Scene Graph Generation by Attention Distillation From Caption ICCV 2021 Toward Joint Thing-and-Stuff Mining for Weakly Supervised Panoptic Segmentation CVPR 2021 Towards Benchmarking the Utility of Explanations for Model Debugging NAACL 2021 Towards Bridging Event Captioner and Sentence Localizer for Weakly Supervised Dense Event Captioning CVPR 2021 Towards Understanding Deep Learning from Noisy Labels with Small-Loss Criterion IJCAI 2021 Towers of Babel: Combining Images, Language, and 3D Geometry for Learning Multimodal Vision ICCV 2021 Training Dynamic based data filtering may not work for NLP datasets EMNLP 2021 Training Language Models under Resource Constraints for Adversarial Advertisement Detection NAACL 2021 Training Weakly Supervised Video Frame Interpolation With Events ICCV 2021 Transfer Learning with Adaptive Online TrAdaBoost for Data Streams ACML 2021 TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classification NeurIPS 2021