{"total":20,"rows":[{"id":"2404.05231","title":"PromptAD: Learning Prompts with only Normal Samples for Few-Shot Anomaly Detection","created":"2024-04-08","cited_by_count":98,"area":null},{"id":"2208.12526","title":"Cross-Lingual Cross-Modal Retrieval with Noise-Robust Learning","created":"2022-08-26","cited_by_count":22,"area":null},{"id":"2303.08475","title":"Mutual Information-Based Temporal Difference Learning for Human Pose Estimation in Video","created":"2023-03-15","cited_by_count":17,"area":null},{"id":"2208.10211","title":"PoseBERT: A Generic Transformer Module for Temporal 3D Human Modeling","created":"2022-08-22","cited_by_count":15,"area":null},{"id":"2311.01066","title":"Dynamic Multimodal Information Bottleneck for Multimodality Classification","created":"2023-11-02","cited_by_count":14,"area":null},{"id":"2205.01373","title":"Copy Motion From One to Another: Fake Motion Video Generation","created":"2022-05-03","cited_by_count":13,"area":null},{"id":"2403.19926","title":"Video-Based Human Pose Regression via Decoupled Space-Time Aggregation","created":"2024-03-29","cited_by_count":10,"area":null},{"id":"2306.07576","title":"Action Recognition with Multi-stream Motion Modeling and Mutual Information Maximization","created":"2023-06-13","cited_by_count":7,"area":null},{"id":"2209.00475","title":"REMOT: A Region-to-Whole Framework for Realistic Human Motion Transfer","created":"2022-09-01","cited_by_count":4,"area":null},{"id":"2303.02575","title":"MITFAS: Mutual Information based Temporal Feature Alignment and Sampling for Aerial Video Action Recognition","created":"2023-03-05","cited_by_count":4,"area":null},{"id":"2407.00574","title":"Humans as Checkerboards: Calibrating Camera Motion Scale for World-Coordinate Human Mesh Recovery","created":"2024-06-30","cited_by_count":4,"area":null},{"id":"2207.10971","title":"Kinematics Modeling Network for Video-based Human Pose Estimation","created":"2022-07-22","cited_by_count":2,"area":null},{"id":"2307.16074","title":"Iterative Graph Filtering Network for 3D Human Pose Estimation","created":"2023-07-29","cited_by_count":1,"area":null},{"id":"2412.20002","title":"Learning an Adaptive and View-Invariant Vision Transformer for Real-Time UAV Tracking","created":"2024-12-28","cited_by_count":1,"area":null},{"id":"2511.13208","title":"End-to-End Multi-Person Pose Estimation with Pose-Aware Video Transformer","created":"2025-11-17","cited_by_count":1,"area":null},{"id":"2309.06877","title":"Video Infringement Detection via Feature Disentanglement and Mutual Information Maximization","created":"2023-09-13","cited_by_count":0,"area":null},{"id":"2503.05365","title":"Multi-Grained Feature Pruning for Video-Based Human Pose Estimation","created":"2025-03-07","cited_by_count":0,"area":null},{"id":"2509.01095","title":"An End-to-End Framework for Video Multi-Person Pose Estimation","created":"2025-09-01","cited_by_count":0,"area":null},{"id":"2603.05929","title":"Beyond Static Frames: Temporal Aggregate-and-Restore Vision Transformer for Human Pose Estimation","created":"2026-03-06","cited_by_count":0,"area":null},{"id":"2603.20323","title":"NCSTR: Node-Centric Decoupled Spatio-Temporal Reasoning for Video-based Human Pose Estimation","created":"2026-03-20","cited_by_count":0,"area":null}],"next_cursor":null}