Tagged articles
Weak Supervision
13 articles · Page 1 of 1
The CPL++ framework equips weakly supervised visual grounding models with confidence‑aware pseudo‑label learning, self‑supervised association correction, and dynamic validation, enabling the model to detect and amend erroneous region‑query links during training, which yields absolute performance gains of 1–6 % across five benchmark datasets.
Computer VisionSelf-CorrectionVisual Grounding
0 likes · 9 min read

This article presents an overview of weak supervision machine learning techniques applied to Ant Group’s business scenarios, covering an introduction to weak supervision, challenges of modeling with scarce or noisy labels, detailed methodologies for cross‑domain causal effect estimation, multi‑source noisy label denoising, and real‑world application examples.
Causal InferenceWeak Supervisioncross-domain
0 likes · 18 min read

This article presents a comprehensive technical overview of weak‑supervision machine learning at Ant Group, covering its fundamentals, cross‑domain causal effect estimation, strategies for scarce or noisy labels, novel framework components, experimental validation, and practical application scenarios.
AICausal InferenceWeak Supervision
0 likes · 18 min read

This article presents a comprehensive overview of weak supervision machine learning techniques applied to Ant Group's business problems, covering theoretical foundations, cross‑domain causal effect estimation, noisy‑label denoising frameworks, experimental results, and practical use cases such as risk modeling and marketing interventions.
Causal InferenceWeak Supervisioncross-domain learning
0 likes · 16 min read

The article reviews the CVPR 2021 MIST framework, explaining how a multiple‑instance pseudo‑label generator and a self‑guided attention encoder work together with sparse continuous sampling to improve context awareness and detection accuracy in weakly‑supervised video anomaly detection.
Attention EncoderComputer VisionSelf‑Training
0 likes · 9 min read

The paper introduces a graph‑based weakly supervised contrastive learning framework that uses heterogeneous user‑behavior graphs, e‑commerce‑specific augmentations, and a hybrid fine‑tuning/transfer learning strategy to improve semantic relevance matching between queries and product titles, achieving significant gains on a large‑scale Taobao dataset.
Contrastive LearningGraph Neural NetworksWeak Supervision
0 likes · 12 min read

This talk presents recent research on integrating dynamic analysis and graph machine learning to generate social relationship graphs from video, detailing hierarchical graph convolution networks, multimodal feature fusion, weakly supervised training, experimental results, and applications such as enhanced video retrieval and storyline understanding.
Graph Neural NetworkWeak Supervisionsocial relationship graph
0 likes · 11 min read

This article presents a multimodal approach that combines dynamic analysis and graph machine learning to generate and apply social relationship graphs in videos, detailing problem background, graph generation modules, applications such as video retrieval, experimental results, and future research directions.
AIGraph Neural NetworkWeak Supervision
0 likes · 11 min read

The article explains how Ctrip’s hotel customer‑service team uses the Snorkel weak‑supervision framework to generate large‑scale labeled data for training models that automatically produce structured event summaries, detailing the workflow, labeling functions, generative and discriminative model training, and performance improvements.
Data AnnotationLabeling FunctionsNLP
0 likes · 14 min read

This article presents a comprehensive overview of video excitement analysis, covering quality, aesthetics, and narrative factors, describing a multimodal framework with supervised, weakly supervised, and multi‑task models, and illustrating practical applications such as preview generation, clipping, and automatic cover creation.
Weak Supervisioncontent recommendationexcitement detection
0 likes · 14 min read

Meituan’s O2O search relies on a hybrid NER system that combines high‑precision domain dictionaries with BERT‑based models scored by a CRF, built from multi‑source offline mining, accelerated via operator fusion, batching and mixed‑precision, and further enhanced by lattice‑LSTM, knowledge‑infused stages and weak‑supervision, delivering millisecond‑level latency and over‑90% recall.
Dictionary MatchingKnowledge-EnhancedNER
0 likes · 30 min read

iQIYI’s video highlight analysis framework combines a large supervised dataset, deep label distribution learning, multi‑task training with a canonical‑correlated autoencoder, and a weakly supervised ranking model enhanced by confidence weighting and graph convolution, then fuses these signals to improve highlight detection accuracy.
Weak Supervisiongraph convolutional networksmulti-task learning
0 likes · 17 min read

This article introduces reinforcement learning fundamentals, contrasts it with supervised learning, and explores its challenges and advantages in natural language processing, including applications such as text classification, relation extraction from noisy data, and weakly supervised topic segmentation, while summarizing key insights and experimental results.
Weak Supervisionnatural language processingreinforcement learning
0 likes · 11 min read
