{"total":71,"rows":[{"id":"2112.11561","title":"Explainable Artificial Intelligence for Autonomous Driving: A Comprehensive Overview and Field Guide for Future Research Directions","created":"2021-12-21","cited_by_count":73,"area":"driving"},{"id":"2108.08236","title":"LOKI: Long Term and Key Intentions for Trajectory Prediction","created":"2021-08-18","cited_by_count":57,"area":null},{"id":"2101.00443","title":"Semantics for Robotic Mapping, Perception and Interaction: A Survey","created":"2021-01-02","cited_by_count":56,"area":null},{"id":"2105.05226","title":"Home Action Genome: Cooperative Compositional Action Understanding","created":"2021-05-11","cited_by_count":53,"area":null},{"id":"2104.05485","title":"Predicting Pedestrian Crossing Intention with Feature Fusion and Spatio-Temporal Attention","created":"2021-04-12","cited_by_count":48,"area":null},{"id":"2107.13411","title":"Predicting the Future from First Person (Egocentric) Vision: A Survey","created":"2021-07-28","cited_by_count":36,"area":null},{"id":"2406.07471","title":"OphNet: A Large-Scale Video Benchmark for Ophthalmic Surgical Workflow Understanding","created":"2024-06-11","cited_by_count":32,"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":"2301.05223","title":"NOPA: Neurally-guided Online Probabilistic Assistance for Building Socially Intelligent Home Assistants","created":"2023-01-12","cited_by_count":23,"area":null},{"id":"2107.08031","title":"Is attention to bounding boxes all you need for pedestrian action prediction?","created":"2021-07-16","cited_by_count":21,"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":"2111.00993","title":"Egocentric Human Trajectory Forecasting with a Wearable Camera and Multi-Modal Fusion","created":"2021-11-01","cited_by_count":17,"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":"2206.03891","title":"PrivHAR: Recognizing Human Actions From Privacy-preserving Lens","created":"2022-06-08","cited_by_count":16,"area":null},{"id":"2407.17757","title":"CRASH: Crash Recognition and Anticipation System Harnessing with Context-Aware and Temporal Focus Attentions","created":"2024-07-25","cited_by_count":14,"area":null},{"id":"2503.03262","title":"Trajectory Prediction for Autonomous Driving: Progress, Limitations, and Future Directions","created":"2025-03-05","cited_by_count":14,"area":null},{"id":"2202.13402","title":"Concept Graph Neural Networks for Surgical Video Understanding","created":"2022-02-27","cited_by_count":13,"area":null},{"id":"2306.01075","title":"Pedestrian Crossing Action Recognition and Trajectory Prediction with 3D Human Keypoints","created":"2023-06-01","cited_by_count":12,"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":"2311.14786","title":"GPT-4V Takes the Wheel: Promises and Challenges for Pedestrian Behavior Prediction","created":"2023-11-24","cited_by_count":11,"area":null},{"id":"2402.12810","title":"PIP-Net: Pedestrian Intention Prediction in the Wild","created":"2024-02-20","cited_by_count":11,"area":null},{"id":"2106.13201","title":"DROID: Driver-centric Risk Object Identification","created":"2021-06-24","cited_by_count":9,"area":null},{"id":"2410.14045","title":"Human Action Anticipation: A Survey","created":"2024-10-17","cited_by_count":9,"area":null},{"id":"2211.05120","title":"Deep Learning based Computer Vision Methods for Complex Traffic Environments Perception: A Review","created":"2022-11-09","cited_by_count":7,"area":null},{"id":"2204.00942","title":"A-ACT: Action Anticipation through Cycle Transformations","created":"2022-04-02","cited_by_count":6,"area":null},{"id":"2409.18053","title":"DualAD: Dual-Layer Planning for Reasoning in Autonomous Driving","created":"2024-09-26","cited_by_count":6,"area":"lr"},{"id":"2103.00092","title":"The Age of Correlated Features in Supervised Learning based Forecasting","created":"2021-02-27","cited_by_count":5,"area":null},{"id":"2103.04019","title":"Indoor Future Person Localization from an Egocentric Wearable Camera","created":"2021-03-06","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":"2507.04141","title":"Pedestrian Intention Prediction via Vision-Language Foundation Models","created":"2025-07-05","cited_by_count":5,"area":"mllm"},{"id":"2305.13051","title":"Learning Pedestrian Actions to Ensure Safe Autonomous Driving","created":"2023-05-22","cited_by_count":4,"area":null},{"id":"2409.20223","title":"GTransPDM: A Graph-embedded Transformer with Positional Decoupling for Pedestrian Crossing Intention Prediction","created":"2024-09-30","cited_by_count":4,"area":null},{"id":"2512.02846","title":"Action Anticipation at a Glimpse: To What Extent Can Multimodal Cues Replace Video?","created":"2025-12-02","cited_by_count":4,"area":null},{"id":"2109.05226","title":"Evaluating Computer Vision Techniques for Urban Mobility on Large-Scale, Unconstrained Roads","created":"2021-09-11","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":"2305.01111","title":"Local and Global Contextual Features Fusion for Pedestrian Intention Prediction","created":"2023-05-01","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":"2308.15169","title":"Uncovering the Unseen: Discover Hidden Intentions by Micro-Behavior Graph Reasoning","created":"2023-08-29","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":"2411.13302","title":"Can Reasons Help Improve Pedestrian Intent Estimation? A Cross-Modal Approach","created":"2024-11-20","cited_by_count":2,"area":null},{"id":"2501.09878","title":"ASTRA: A Scene-aware TRAnsformer-based model for trajectory prediction","created":"2025-01-16","cited_by_count":2,"area":null},{"id":"2503.04952","title":"INTENT: Trajectory Prediction Framework with Intention-Guided Contrastive Clustering","created":"2025-03-06","cited_by_count":2,"area":null},{"id":"2503.08016","title":"SGNetPose+: Stepwise Goal-Driven Networks with Pose Information for Trajectory Prediction in Autonomous Driving","created":"2025-03-11","cited_by_count":2,"area":null},{"id":"2508.19866","title":"TrajFusionNet: Pedestrian Crossing Intention Prediction via Fusion of Sequential and Visual Trajectory Representations","created":"2025-08-27","cited_by_count":2,"area":null},{"id":"2601.22039","title":"Understanding Multimodal Complementarity for Single-Frame Action Anticipation","created":"2026-01-29","cited_by_count":2,"area":null},{"id":"2306.01623","title":"HomE: Homography-Equivariant Video Representation Learning","created":"2023-06-02","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":"2409.02508","title":"TLD: A Vehicle Tail Light signal Dataset and Benchmark","created":"2024-09-04","cited_by_count":1,"area":null},{"id":"2409.07645","title":"Feature Importance in Pedestrian Intention Prediction: A Context-Aware Review","created":"2024-09-11","cited_by_count":1,"area":null},{"id":"2501.04193","title":"GNN-based Decentralized Perception in Multirobot Systems for Predicting Worker Actions","created":"2025-01-08","cited_by_count":1,"area":null},{"id":"2506.14727","title":"Casper: Inferring Diverse Intents for Assistive Teleoperation with Vision Language Models","created":"2025-06-17","cited_by_count":1,"area":"mllm"},{"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":"2507.06513","title":"What Demands Attention in Urban Street Scenes? From Scene Understanding towards Road Safety: A Survey of Vision-driven Datasets and Studies","created":"2025-07-09","cited_by_count":1,"area":null},{"id":"2511.00858","title":"Occlusion-Aware Diffusion Model for Pedestrian Intention Prediction","created":"2025-11-02","cited_by_count":1,"area":"diffusion"},{"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":"2405.18945","title":"WTTFNet: A Weather-Time-Trajectory Fusion Network for Pedestrian Trajectory Prediction in Urban Complex","created":"2024-05-29","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":"2410.12195","title":"Sparse Prototype Network for Explainable Pedestrian Behavior Prediction","created":"2024-10-16","cited_by_count":0,"area":null},{"id":"2502.19260","title":"EMT: A Visual Multi-Task Benchmark Dataset for Autonomous Driving","created":"2025-02-26","cited_by_count":0,"area":null},{"id":"2507.11642","title":"Posture-Driven Action Intent Inference for Playing style and Fatigue Assessment","created":"2025-07-15","cited_by_count":0,"area":null},{"id":"2509.20715","title":"Beyond the Individual: Introducing Group Intention Forecasting with SHOT Dataset","created":"2025-09-25","cited_by_count":0,"area":null},{"id":"2510.03314","title":"From Camera-Based Sensing to Reasoning: A Comprehensive Review Toward Proactive Vulnerable Road User Safety","created":"2025-09-30","cited_by_count":0,"area":null},{"id":"2510.20189","title":"SPAN: Continuous Modeling of Suspicion Progression for Temporal Intention Localization","created":"2025-10-23","cited_by_count":0,"area":null},{"id":"2512.15386","title":"See It Before You Grab It: Deep Learning-based Action Anticipation in Basketball","created":"2025-12-17","cited_by_count":0,"area":null},{"id":"2604.09303","title":"Online Intention Prediction via Control-Informed Learning","created":"2026-04-10","cited_by_count":0,"area":null},{"id":"2605.24562","title":"PEDESTRIANQA: A Benchmark for Vision-Language Models on Pedestrian Intention and Trajectory Prediction","created":"2026-05-23","cited_by_count":0,"area":"mllm"},{"id":"2609.20178","title":"MTF-Net: Multi-Modal Temporal Feature Fusion Network for Pedestrian Intention Prediction","created":"2026-07-24","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}