{"total":24,"rows":[{"id":"2407.06886","title":"Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AI","created":"2024-07-09","cited_by_count":179,"area":null},{"id":"2207.08132","title":"E-NeRV: Expedite Neural Video Representation with Disentangled Spatial-Temporal Context","created":"2022-07-17","cited_by_count":76,"area":null},{"id":"2307.08476","title":"SkeletonMAE: Graph-based Masked Autoencoder for Skeleton Sequence Pre-training","created":"2023-07-17","cited_by_count":41,"area":null},{"id":"2401.03717","title":"Universal Time-Series Representation Learning: A Survey","created":"2024-01-08","cited_by_count":30,"area":null},{"id":"2305.04224","title":"Visual Causal Scene Refinement for Video Question Answering","created":"2023-05-07","cited_by_count":16,"area":null},{"id":"2211.10412","title":"Video Unsupervised Domain Adaptation with Deep Learning: A Comprehensive Survey","created":"2022-11-17","cited_by_count":12,"area":null},{"id":"2303.09789","title":"Urban Regional Function Guided Traffic Flow Prediction","created":"2023-03-17","cited_by_count":12,"area":null},{"id":"2209.05653","title":"Semantic2Graph: Graph-based Multi-modal Feature Fusion for Action Segmentation in Videos","created":"2022-09-13","cited_by_count":9,"area":null},{"id":"2202.06503","title":"Adaptive Graph Convolutional Networks for Weakly Supervised Anomaly Detection in Videos","created":"2022-02-14","cited_by_count":7,"area":null},{"id":"2306.07553","title":"DenseLight: Efficient Control for Large-scale Traffic Signals with Dense Feedback","created":"2023-06-13","cited_by_count":7,"area":null},{"id":"2402.00290","title":"MEIA: Multimodal Embodied Perception and Interaction in Unknown Environments","created":"2024-02-01","cited_by_count":5,"area":null},{"id":"2204.13386","title":"Self-supervised Contrastive Learning for Audio-Visual Action Recognition","created":"2022-04-28","cited_by_count":4,"area":null},{"id":"2304.08083","title":"VCD: Visual Causality Discovery for Cross-Modal Question Reasoning","created":"2023-04-17","cited_by_count":2,"area":null},{"id":"2305.02324","title":"Cross-Stream Contrastive Learning for Self-Supervised Skeleton-Based Action Recognition","created":"2023-05-03","cited_by_count":2,"area":null},{"id":"2312.03327","title":"Building Category Graphs Representation with Spatial and Temporal Attention for Visual Navigation","created":"2023-12-06","cited_by_count":2,"area":null},{"id":"2401.10805","title":"Learning to Visually Connect Actions and their Effects","created":"2024-01-19","cited_by_count":2,"area":null},{"id":"2207.10158","title":"GOCA: Guided Online Cluster Assignment for Self-Supervised Video Representation Learning","created":"2022-07-20","cited_by_count":1,"area":null},{"id":"2304.10335","title":"A baseline on continual learning methods for video action recognition","created":"2023-04-20","cited_by_count":1,"area":null},{"id":"2401.07584","title":"Collaboratively Self-supervised Video Representation Learning for Action Recognition","created":"2024-01-15","cited_by_count":0,"area":null},{"id":"2503.02284","title":"Semi-Supervised Audio-Visual Video Action Recognition with Audio Source Localization Guided Mixup","created":"2025-03-04","cited_by_count":0,"area":null},{"id":"2511.21202","title":"Towards an Effective Action-Region Tracking Framework for Fine-grained Video Action Recognition","created":"2025-11-26","cited_by_count":0,"area":null},{"id":"2512.16504","title":"Skeleton-Snippet Contrastive Learning with Multiscale Feature Fusion for Action Localization","created":"2025-12-18","cited_by_count":0,"area":null},{"id":"2602.15330","title":"A Scalable Curiosity-Driven Game-Theoretic Framework for Long-Tail Multi-Label Learning in Data Mining","created":"2026-02-17","cited_by_count":0,"area":null},{"id":"2602.22791","title":"Robust Human Trajectory Prediction via Self-Supervised Skeleton Representation Learning","created":"2026-02-26","cited_by_count":0,"area":null}],"next_cursor":null}