{"total":55,"rows":[{"id":"2104.01111","title":"A Comprehensive Survey of Scene Graphs: Generation and Application","created":"2021-03-17","cited_by_count":125,"area":null},{"id":"2206.09541","title":"DualCoOp: Fast Adaptation to Multi-Label Recognition with Limited Annotations","created":"2022-06-20","cited_by_count":102,"area":null},{"id":"2110.06465","title":"Breaking the Dilemma of Medical Image-to-image Translation","created":"2021-10-13","cited_by_count":82,"area":null},{"id":"2104.14795","title":"Mitigating Political Bias in Language Models Through Reinforced Calibration","created":"2021-04-30","cited_by_count":73,"area":null},{"id":"2107.02112","title":"Recovering the Unbiased Scene Graphs from the Biased Ones","created":"2021-07-05","cited_by_count":71,"area":null},{"id":"2303.05892","title":"Object-Aware Distillation Pyramid for Open-Vocabulary Object Detection","created":"2023-03-10","cited_by_count":63,"area":null},{"id":"2210.12209","title":"Motion Policy Networks","created":"2022-10-21","cited_by_count":55,"area":null},{"id":"2109.13228","title":"PASS: An ImageNet replacement for self-supervised pretraining without humans","created":"2021-09-27","cited_by_count":51,"area":null},{"id":"2111.08940","title":"Transparent Human Evaluation for Image Captioning","created":"2021-11-17","cited_by_count":40,"area":null},{"id":"2205.01850","title":"Visual Commonsense in Pretrained Unimodal and Multimodal Models","created":"2022-05-04","cited_by_count":39,"area":null},{"id":"2110.08182","title":"The World of an Octopus: How Reporting Bias Influences a Language Model's Perception of Color","created":"2021-10-15","cited_by_count":32,"area":null},{"id":"2207.10888","title":"FairGRAPE: Fairness-aware GRAdient Pruning mEthod for Face Attribute Classification","created":"2022-07-22","cited_by_count":30,"area":null},{"id":"2210.05815","title":"Underspecification in Scene Description-to-Depiction Tasks","created":"2022-10-11","cited_by_count":30,"area":null},{"id":"2105.13994","title":"Linguistic Structures as Weak Supervision for Visual Scene Graph Generation","created":"2021-05-28","cited_by_count":29,"area":null},{"id":"2110.10955","title":"Multi-label Classification with Partial Annotations using Class-aware Selective Loss","created":"2021-10-21","cited_by_count":25,"area":null},{"id":"2302.07159","title":"A Friendly Face: Do Text-to-Image Systems Rely on Stereotypes when the Input is Under-Specified?","created":"2023-02-14","cited_by_count":25,"area":null},{"id":"2308.01890","title":"DualCoOp++: Fast and Effective Adaptation to Multi-Label Recognition with Limited Annotations","created":"2023-08-03","cited_by_count":22,"area":null},{"id":"2111.13517","title":"Not All Relations are Equal: Mining Informative Labels for Scene Graph Generation","created":"2021-11-26","cited_by_count":21,"area":null},{"id":"2207.13316","title":"NICEST: Noisy Label Correction and Training for Robust Scene Graph Generation","created":"2022-07-27","cited_by_count":19,"area":null},{"id":"2109.09150","title":"A Study of the Generalizability of Self-Supervised Representations","created":"2021-09-19","cited_by_count":18,"area":null},{"id":"2204.04421","title":"Unbiased Directed Object Attention Graph for Object Navigation","created":"2022-04-09","cited_by_count":18,"area":null},{"id":"2203.03762","title":"Defending Graph Convolutional Networks against Dynamic Graph Perturbations via Bayesian Self-supervision","created":"2022-03-07","cited_by_count":16,"area":null},{"id":"2203.06907","title":"Hierarchical Memory Learning for Fine-Grained Scene Graph Generation","created":"2022-03-14","cited_by_count":15,"area":null},{"id":"2407.08133","title":"Nonverbal Interaction Detection","created":"2024-07-11","cited_by_count":14,"area":null},{"id":"2408.02464","title":"Fairness and Bias Mitigation in Computer Vision: A Survey","created":"2024-08-05","cited_by_count":13,"area":null},{"id":"2210.03102","title":"Ambiguous Images With Human Judgments for Robust Visual Event Classification","created":"2022-10-06","cited_by_count":12,"area":null},{"id":"2308.08872","title":"Towards Semi-supervised Learning with Non-random Missing Labels","created":"2023-08-17","cited_by_count":12,"area":null},{"id":"2206.14923","title":"On Non-Random Missing Labels in Semi-Supervised Learning","created":"2022-06-29","cited_by_count":11,"area":null},{"id":"2503.13957","title":"DIFFVSGG: Diffusion-Driven Online Video Scene Graph Generation","created":"2025-03-18","cited_by_count":11,"area":null},{"id":"2304.07408","title":"Fairness in Visual Clustering: A Novel Transformer Clustering Approach","created":"2023-04-14","cited_by_count":10,"area":null},{"id":"2302.09595","title":"Latent Class-Conditional Noise Model","created":"2023-02-19","cited_by_count":9,"area":null},{"id":"2112.13165","title":"Semantic Clustering based Deduction Learning for Image Recognition and Classification","created":"2021-12-25","cited_by_count":8,"area":null},{"id":"2202.12382","title":"Fine-Grained Prediction of Political Leaning on Social Media with Unsupervised Deep Learning","created":"2022-02-23","cited_by_count":8,"area":null},{"id":"2105.11168","title":"Human-centric Relation Segmentation: Dataset and Solution","created":"2021-05-24","cited_by_count":7,"area":null},{"id":"2109.02688","title":"Rethinking Crowdsourcing Annotation: Partial Annotation with Salient Labels for Multi-Label Image Classification","created":"2021-09-06","cited_by_count":7,"area":null},{"id":"2110.00109","title":"DeepMCAT: Large-Scale Deep Clustering for Medical Image Categorization","created":"2021-09-30","cited_by_count":7,"area":null},{"id":"2407.03623","title":"Resampled Datasets Are Not Enough: Mitigating Societal Bias Beyond Single Attributes","created":"2024-07-04","cited_by_count":7,"area":null},{"id":"2404.16193","title":"Improving Multi-label Recognition using Class Co-Occurrence Probabilities","created":"2024-04-24","cited_by_count":6,"area":null},{"id":"2503.00548","title":"Unbiased Video Scene Graph Generation via Visual and Semantic Dual Debiasing","created":"2025-03-01","cited_by_count":6,"area":null},{"id":"2103.10869","title":"MetaLabelNet: Learning to Generate Soft-Labels from Noisy-Labels","created":"2021-03-19","cited_by_count":5,"area":null},{"id":"2301.00351","title":"Skew Class-balanced Re-weighting for Unbiased Scene Graph Generation","created":"2023-01-01","cited_by_count":5,"area":null},{"id":"2305.01888","title":"Fairness in AI Systems: Mitigating gender bias from language-vision models","created":"2023-05-03","cited_by_count":5,"area":null},{"id":"2405.01090","title":"Learning Multiple Object States from Actions via Large Language Models","created":"2024-05-02","cited_by_count":4,"area":null},{"id":"2303.13209","title":"Taking A Closer Look at Visual Relation: Unbiased Video Scene Graph Generation with Decoupled Label Learning","created":"2023-03-23","cited_by_count":3,"area":null},{"id":"2412.02373","title":"Active Negative Loss: A Robust Framework for Learning with Noisy Labels","created":"2024-12-03","cited_by_count":3,"area":null},{"id":"2503.16873","title":"Classifier-guided CLIP Distillation for Unsupervised Multi-label Classification","created":"2025-03-21","cited_by_count":2,"area":null},{"id":"2508.19791","title":"Color Bind: Exploring Color Perception in Text-to-Image Models","created":"2025-08-27","cited_by_count":2,"area":null},{"id":"2108.06810","title":"SCIDA: Self-Correction Integrated Domain Adaptation from Single- to Multi-label Aerial Images","created":"2021-08-15","cited_by_count":1,"area":null},{"id":"2207.08104","title":"A Multibias-mitigated and Sentiment Knowledge Enriched Transformer for Debiasing in Multimodal Conversational Emotion Recognition","created":"2022-07-17","cited_by_count":1,"area":null},{"id":"2307.16309","title":"Triple Correlations-Guided Label Supplementation for Unbiased Video Scene Graph Generation","created":"2023-07-30","cited_by_count":1,"area":null},{"id":"2401.13213","title":"Common-Sense Bias Modeling for Classification Tasks","created":"2024-01-24","cited_by_count":1,"area":null},{"id":"2405.18405","title":"WIDIn: Wording Image for Domain-Invariant Representation in Single-Source Domain Generalization","created":"2024-05-28","cited_by_count":1,"area":null},{"id":"2512.23024","title":"With Great Context Comes Great Prediction Power: Classifying Objects via Geo-Semantic Scene Graphs","created":"2025-12-28","cited_by_count":0,"area":null},{"id":"2603.16974","title":"Are a Thousand Words Better Than a Single Picture? Beyond Images -- A Framework for Multi-Modal Knowledge Graph Dataset Enrichment","created":"2026-03-17","cited_by_count":0,"area":null},{"id":"2604.17298","title":"Frequency-guided Multi-level Reasoning for Scene Graph Generation in Video","created":"2026-04-19","cited_by_count":0,"area":null}],"next_cursor":null}