{"total":32,"rows":[{"id":"2108.13624","title":"Towards Out-Of-Distribution Generalization: A Survey","created":"2021-08-31","cited_by_count":436,"area":null},{"id":"2203.13049","title":"Compositional Temporal Grounding with Structured Variational Cross-Graph Correspondence Learning","created":"2022-03-24","cited_by_count":59,"area":null},{"id":"2404.10241","title":"Vision-and-Language Navigation via Causal Learning","created":"2024-04-16","cited_by_count":51,"area":null},{"id":"2110.12942","title":"DocTr: Document Image Transformer for Geometric Unwarping and Illumination Correction","created":"2021-10-25","cited_by_count":39,"area":null},{"id":"2111.06061","title":"Edge-Cloud Polarization and Collaboration: A Comprehensive Survey for AI","created":"2021-11-11","cited_by_count":39,"area":null},{"id":"2304.03391","title":"Exposing and Mitigating Spurious Correlations for Cross-Modal Retrieval","created":"2023-04-06","cited_by_count":36,"area":null},{"id":"2108.07073","title":"ROSITA: Enhancing Vision-and-Language Semantic Alignments via Cross- and Intra-modal Knowledge Integration","created":"2021-08-16","cited_by_count":31,"area":null},{"id":"2211.13854","title":"ComCLIP: Training-Free Compositional Image and Text Matching","created":"2022-11-25","cited_by_count":26,"area":null},{"id":"2302.07335","title":"Intelligent Model Update Strategy for Sequential Recommendation","created":"2023-02-14","cited_by_count":25,"area":null},{"id":"2210.14562","title":"FairCLIP: Social Bias Elimination based on Attribute Prototype Learning and Representation Neutralization","created":"2022-10-26","cited_by_count":20,"area":null},{"id":"2203.08013","title":"End-to-End Modeling via Information Tree for One-Shot Natural Language Spatial Video Grounding","created":"2022-03-15","cited_by_count":19,"area":null},{"id":"2107.12270","title":"Adaptive Hierarchical Graph Reasoning with Semantic Coherence for Video-and-Language Inference","created":"2021-07-26","cited_by_count":18,"area":null},{"id":"2110.00726","title":"Domain-Specific Bias Filtering for Single Labeled Domain Generalization","created":"2021-10-02","cited_by_count":18,"area":null},{"id":"2310.07379","title":"Causal Unsupervised Semantic Segmentation","created":"2023-10-11","cited_by_count":18,"area":null},{"id":"2308.07593","title":"AKVSR: Audio Knowledge Empowered Visual Speech Recognition by Compressing Audio Knowledge of a Pretrained Model","created":"2023-08-15","cited_by_count":16,"area":null},{"id":"2308.09311","title":"Lip Reading for Low-resource Languages by Learning and Combining General Speech Knowledge and Language-specific Knowledge","created":"2023-08-18","cited_by_count":16,"area":null},{"id":"2109.12651","title":"Why Do We Click: Visual Impression-aware News Recommendation","created":"2021-09-26","cited_by_count":10,"area":null},{"id":"2206.12296","title":"Intelligent Request Strategy Design in Recommender System","created":"2022-06-23","cited_by_count":10,"area":null},{"id":"2208.01954","title":"Dilated Context Integrated Network with Cross-Modal Consensus for Temporal Emotion Localization in Videos","created":"2022-08-03","cited_by_count":10,"area":null},{"id":"2109.13921","title":"Click-through Rate Prediction with Auto-Quantized Contrastive Learning","created":"2021-09-27","cited_by_count":7,"area":null},{"id":"2507.02645","title":"Fair Deepfake Detectors Can Generalize","created":"2025-07-03","cited_by_count":7,"area":null},{"id":"2408.12292","title":"Towards Deconfounded Image-Text Matching with Causal Inference","created":"2024-08-22","cited_by_count":6,"area":null},{"id":"2208.10912","title":"Learning Instrumental Variable from Data Fusion for Treatment Effect Estimation","created":"2022-08-23","cited_by_count":5,"area":null},{"id":"2412.18904","title":"FedCFA: Alleviating Simpson's Paradox in Model Aggregation with Counterfactual Federated Learning","created":"2024-12-25","cited_by_count":4,"area":null},{"id":"2210.02946","title":"VLSNR:Vision-Linguistics Coordination Time Sequence-aware News Recommendation","created":"2022-10-06","cited_by_count":3,"area":null},{"id":"2210.11933","title":"Fine-grained Semantic Alignment Network for Weakly Supervised Temporal Language Grounding","created":"2022-10-21","cited_by_count":3,"area":null},{"id":"2305.17652","title":"ConaCLIP: Exploring Distillation of Fully-Connected Knowledge Interaction Graph for Lightweight Text-Image Retrieval","created":"2023-05-28","cited_by_count":3,"area":null},{"id":"2501.02837","title":"Forward Once for All: Structural Parameterized Adaptation for Efficient Cloud-coordinated On-device Recommendation","created":"2025-01-06","cited_by_count":3,"area":null},{"id":"2404.13348","title":"Socialized Learning: A Survey of the Paradigm Shift for Edge Intelligence in Networked Systems","created":"2024-04-20","cited_by_count":2,"area":null},{"id":"2305.19664","title":"Unveiling Cross Modality Bias in Visual Question Answering: A Causal View with Possible Worlds VQA","created":"2023-05-31","cited_by_count":1,"area":null},{"id":"2512.24323","title":"Robust Egocentric Referring Video Object Segmentation via Dual-Modal Causal Intervention","created":"2025-12-30","cited_by_count":1,"area":null},{"id":"2504.14171","title":"Adaptation Method for Misinformation Identification","created":"2025-04-19","cited_by_count":0,"area":null}],"next_cursor":null}