{"total":53,"rows":[{"id":"2312.17432","title":"Video Understanding with Large Language Models: A Survey","created":"2023-12-29","cited_by_count":206,"area":null},{"id":"2209.10767","title":"DRAMA: Joint Risk Localization and Captioning in Driving","created":"2022-09-22","cited_by_count":126,"area":null},{"id":"2401.01454","title":"A Survey on Autonomous Driving Datasets: Statistics, Annotation Quality, and a Future Outlook","created":"2024-01-02","cited_by_count":66,"area":null},{"id":"2108.08236","title":"LOKI: Long Term and Key Intentions for Trajectory Prediction","created":"2021-08-18","cited_by_count":57,"area":null},{"id":"2102.11585","title":"ROAD: The ROad event Awareness Dataset for Autonomous Driving","created":"2021-02-23","cited_by_count":54,"area":null},{"id":"2105.05226","title":"Home Action Genome: Cooperative Compositional Action Understanding","created":"2021-05-11","cited_by_count":53,"area":null},{"id":"2103.12474","title":"On Exposing the Challenging Long Tail in Future Prediction of Traffic Actors","created":"2021-03-23","cited_by_count":48,"area":null},{"id":"2211.00385","title":"Behavioral Intention Prediction in Driving Scenes: A Survey","created":"2022-11-01","cited_by_count":30,"area":null},{"id":"2210.07886","title":"PedFormer: Pedestrian Behavior Prediction via Cross-Modal Attention Modulation and Gated Multitask Learning","created":"2022-10-14","cited_by_count":23,"area":null},{"id":"2312.03408","title":"Open-sourced Data Ecosystem in Autonomous Driving: the Present and Future","created":"2023-12-06","cited_by_count":23,"area":null},{"id":"2407.12345","title":"VisionTrap: Vision-Augmented Trajectory Prediction Guided by Textual Descriptions","created":"2024-07-17","cited_by_count":19,"area":null},{"id":"2112.02604","title":"PSI: A Benchmark for Human Interpretation and Response in Traffic Interactions","created":"2021-12-05","cited_by_count":17,"area":null},{"id":"2106.12442","title":"Euro-PVI: Pedestrian Vehicle Interactions in Dense Urban Centers","created":"2021-06-22","cited_by_count":16,"area":null},{"id":"2207.08664","title":"Action-based Contrastive Learning for Trajectory Prediction","created":"2022-07-18","cited_by_count":15,"area":null},{"id":"2310.10424","title":"A Novel Benchmarking Paradigm and a Scale- and Motion-Aware Model for Egocentric Pedestrian Trajectory Prediction","created":"2023-10-16","cited_by_count":12,"area":null},{"id":"2311.17948","title":"Action-slot: Visual Action-centric Representations for Multi-label Atomic Activity Recognition in Traffic Scenes","created":"2023-11-29","cited_by_count":12,"area":null},{"id":"2312.01659","title":"RiskBench: A Scenario-based Benchmark for Risk Identification","created":"2023-12-04","cited_by_count":12,"area":null},{"id":"2308.07050","title":"Survey on video anomaly detection in dynamic scenes with moving cameras","created":"2023-08-14","cited_by_count":10,"area":null},{"id":"2106.13201","title":"DROID: Driver-centric Risk Object Identification","created":"2021-06-24","cited_by_count":9,"area":null},{"id":"2202.01478","title":"Trajectory Forecasting from Detection with Uncertainty-Aware Motion Encoding","created":"2022-02-03","cited_by_count":8,"area":null},{"id":"2302.10463","title":"Vision-based Multi-future Trajectory Prediction: A Survey","created":"2023-02-21","cited_by_count":8,"area":null},{"id":"2203.07098","title":"A Two-Block RNN-based Trajectory Prediction from Incomplete Trajectory","created":"2022-03-14","cited_by_count":6,"area":null},{"id":"2203.02489","title":"Pedestrian Stop and Go Forecasting with Hybrid Feature Fusion","created":"2022-03-04","cited_by_count":5,"area":null},{"id":"2210.11999","title":"On-Board Pedestrian Trajectory Prediction Using Behavioral Features","created":"2022-10-21","cited_by_count":5,"area":null},{"id":"2308.08764","title":"XVTP3D: Cross-view Trajectory Prediction Using Shared 3D Queries for Autonomous Driving","created":"2023-08-17","cited_by_count":4,"area":null},{"id":"2204.07157","title":"Joint Forecasting of Panoptic Segmentations with Difference Attention","created":"2022-04-14","cited_by_count":3,"area":null},{"id":"2208.07441","title":"WatchPed: Pedestrian Crossing Intention Prediction Using Embedded Sensors of Smartwatch","created":"2022-08-15","cited_by_count":3,"area":null},{"id":"2312.08558","title":"Leveraging Driver Field-of-View for Multimodal Ego-Trajectory Prediction","created":"2023-12-13","cited_by_count":3,"area":null},{"id":"2407.17162","title":"Context-aware Multi-task Learning for Pedestrian Intent and Trajectory Prediction","created":"2024-07-24","cited_by_count":3,"area":null},{"id":"2602.08962","title":"Modeling 3D Pedestrian-Vehicle Interactions for Vehicle-Conditioned Pose Forecasting","created":"2026-02-09","cited_by_count":3,"area":null},{"id":"2306.16784","title":"A Survey on Datasets for Decision-making of Autonomous Vehicle","created":"2023-06-29","cited_by_count":2,"area":null},{"id":"2407.00446","title":"Diving Deeper Into Pedestrian Behavior Understanding: Intention Estimation, Action Prediction, and Event Risk Assessment","created":"2024-06-29","cited_by_count":2,"area":null},{"id":"2407.20642","title":"Effectively Leveraging CLIP for Generating Situational Summaries of Images and Videos","created":"2024-07-30","cited_by_count":2,"area":null},{"id":"2409.15846","title":"Potential Field as Scene Affordance for Behavior Change-Based Visual Risk Object Identification","created":"2024-09-24","cited_by_count":2,"area":null},{"id":"2503.18553","title":"ATARS: An Aerial Traffic Atomic Activity Recognition and Temporal Segmentation Dataset","created":"2025-03-24","cited_by_count":2,"area":null},{"id":"2204.02688","title":"MM-SEAL: A Large-scale Video Dataset of Multi-person Multi-grained Spatio-temporally Action Localization","created":"2022-04-06","cited_by_count":1,"area":null},{"id":"2303.06935","title":"Importance Filtering with Risk Models for Complex Driving Situations","created":"2023-03-13","cited_by_count":1,"area":null},{"id":"2312.02872","title":"Experimental Insights Towards Explainable and Interpretable Pedestrian Crossing Prediction","created":"2023-12-05","cited_by_count":1,"area":null},{"id":"2408.15250","title":"Pedestrian Motion Prediction Using Transformer-based Behavior Clustering and Data-Driven Reachability Analysis","created":"2024-08-09","cited_by_count":1,"area":null},{"id":"2411.01683","title":"ROAD-Waymo: A Large-Scale Action Awareness Dataset for Autonomous Driving","created":"2024-11-03","cited_by_count":1,"area":null},{"id":"2412.13729","title":"TH\\\"OR-MAGNI Act: Actions for Human Motion Modeling in Robot-Shared Industrial Spaces","created":"2024-12-18","cited_by_count":1,"area":null},{"id":"2506.22111","title":"Pedestrian Intention and Trajectory Prediction in Unstructured Traffic Using IDD-PeD","created":"2025-06-27","cited_by_count":1,"area":null},{"id":"2603.05926","title":"Towards Driver Behavior Understanding: Weakly-Supervised Risk Perception in Driving Scenes","created":"2026-03-06","cited_by_count":1,"area":null},{"id":"2103.14113","title":"GPRAR: Graph Convolutional Network based Pose Reconstruction and Action Recognition for Human Trajectory Prediction","created":"2021-03-25","cited_by_count":0,"area":null},{"id":"2207.03870","title":"BlindSpotNet: Seeing Where We Cannot See","created":"2022-07-08","cited_by_count":0,"area":null},{"id":"2304.05345","title":"FIR-based Future Trajectory Prediction in Nighttime Autonomous Driving","created":"2023-03-31","cited_by_count":0,"area":null},{"id":"2305.15942","title":"Comparison of Pedestrian Prediction Models from Trajectory and Appearance Data for Autonomous Driving","created":"2023-05-25","cited_by_count":0,"area":null},{"id":"2409.09446","title":"MulCPred: Learning Multi-modal Concepts for Explainable Pedestrian Action Prediction","created":"2024-09-14","cited_by_count":0,"area":null},{"id":"2409.15224","title":"Enhancing Pedestrian Trajectory Prediction with Crowd Trip Information","created":"2024-09-23","cited_by_count":0,"area":null},{"id":"2410.12195","title":"Sparse Prototype Network for Explainable Pedestrian Behavior Prediction","created":"2024-10-16","cited_by_count":0,"area":null},{"id":"2603.23919","title":"Uncertainty-Aware Vision-based Risk Object Identification via Conformal Risk Tube Prediction","created":"2026-03-25","cited_by_count":0,"area":null},{"id":"2605.24950","title":"ARCANE-PedSynth: Synthetic Multi-Pedestrian Datasets with Behavioural Crossing Annotations","created":"2026-05-24","cited_by_count":0,"area":null},{"id":"2609.24127","title":"Action-Slot: Structured Action-Centric Representation Learning for Multi-Agent Atomic Activity Understanding","created":"2026-09-21","cited_by_count":0,"area":null}],"next_cursor":null}