{"list":"other","total":48,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"1912.04838","title":"Scalability in Perception for Autonomous Driving: Waymo Open Dataset","created":"2019-12-10","cited_by_count":2451},{"id":"1909.10351","title":"TinyBERT: Distilling BERT for Natural Language Understanding","created":"2019-09-23","cited_by_count":1167},{"id":"2402.12289","title":"DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models","created":"2024-02-19","cited_by_count":490},{"id":"2404.16994","title":"PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning","created":"2024-04-25","cited_by_count":322},{"id":"2203.13777","title":"Stochastic Trajectory Prediction via Motion Indeterminacy Diffusion","created":"2022-03-25","cited_by_count":185},{"id":"2408.12637","title":"Building and better understanding vision-language models: insights and future directions","created":"2024-08-22","cited_by_count":173},{"id":"2112.08274","title":"Putting People in their Place: Monocular Regression of 3D People in Depth","created":"2021-12-15","cited_by_count":142},{"id":"2303.10895","title":"Leapfrog Diffusion Model for Stochastic Trajectory Prediction","created":"2023-03-20","cited_by_count":132},{"id":"2401.05577","title":"VLP: Vision Language Planning for Autonomous Driving","created":"2024-01-10","cited_by_count":126},{"id":"2309.10228","title":"Drive as You Speak: Enabling Human-Like Interaction with Large Language Models in Autonomous Vehicles","created":"2023-09-19","cited_by_count":100},{"id":"2303.10876","title":"EqMotion: Equivariant Multi-agent Motion Prediction with Invariant Interaction Reasoning","created":"2023-03-20","cited_by_count":97},{"id":"2308.09882","title":"Forecast-MAE: Self-supervised Pre-training for Motion Forecasting with Masked Autoencoders","created":"2023-08-19","cited_by_count":73},{"id":"2310.08034","title":"Receive, Reason, and React: Drive as You Say with Large Language Models in Autonomous Vehicles","created":"2023-10-12","cited_by_count":72},{"id":"2203.08207","title":"SocialVAE: Human Trajectory Prediction using Timewise Latents","created":"2022-03-15","cited_by_count":67},{"id":"2302.13933","title":"LAformer: Trajectory Prediction for Autonomous Driving with Lane-Aware Scene Constraints","created":"2023-02-27","cited_by_count":53},{"id":"2305.14715","title":"Leveraging Future Relationship Reasoning for Vehicle Trajectory Prediction","created":"2023-05-24","cited_by_count":48},{"id":"2312.04372","title":"LaMPilot: An Open Benchmark Dataset for Autonomous Driving with Language Model Programs","created":"2023-12-07","cited_by_count":45},{"id":"2303.15083","title":"UniDistill: A Universal Cross-Modality Knowledge Distillation Framework for 3D Object Detection in Bird's-Eye View","created":"2023-03-27","cited_by_count":43},{"id":"2406.14556","title":"Asynchronous Large Language Model Enhanced Planner for Autonomous Driving","created":"2024-06-20","cited_by_count":38},{"id":"2312.16168","title":"Social-Transmotion: Promptable Human Trajectory Prediction","created":"2023-12-26","cited_by_count":33},{"id":"2403.16439","title":"Producing and Leveraging Online Map Uncertainty in Trajectory Prediction","created":"2024-03-25","cited_by_count":33},{"id":"2301.02217","title":"EgoDistill: Egocentric Head Motion Distillation for Efficient Video Understanding","created":"2023-01-05","cited_by_count":32},{"id":"2403.18447","title":"Can Language Beat Numerical Regression? Language-Based Multimodal Trajectory Prediction","created":"2024-03-27","cited_by_count":31},{"id":"2404.05218","title":"Multi-agent Long-term 3D Human Pose Forecasting via Interaction-aware Trajectory Conditioning","created":"2024-04-08","cited_by_count":30},{"id":"2303.02203","title":"X$^3$KD: Knowledge Distillation Across Modalities, Tasks and Stages for Multi-Camera 3D Object Detection","created":"2023-03-03","cited_by_count":28},{"id":"2309.15289","title":"SEPT: Towards Efficient Scene Representation Learning for Motion Prediction","created":"2023-09-26","cited_by_count":27},{"id":"2409.18031","title":"Reasoning Multi-Agent Behavioral Topology for Interactive Autonomous Driving","created":"2024-09-26","cited_by_count":27},{"id":"2407.14177","title":"EVLM: An Efficient Vision-Language Model for Visual Understanding","created":"2024-07-19","cited_by_count":25},{"id":"2309.17209","title":"Robots That Can See: Leveraging Human Pose for Trajectory Prediction","created":"2023-09-29","cited_by_count":23},{"id":"2404.00742","title":"Adapting to Length Shift: FlexiLength Network for Trajectory Prediction","created":"2024-03-31","cited_by_count":22},{"id":"2407.21635","title":"MART: MultiscAle Relational Transformer Networks for Multi-agent Trajectory Prediction","created":"2024-07-31","cited_by_count":21},{"id":"2411.02673","title":"Multi-Transmotion: Pre-trained Model for Human Motion Prediction","created":"2024-11-04","cited_by_count":21},{"id":"2403.10052","title":"T4P: Test-Time Training of Trajectory Prediction via Masked Autoencoder and Actor-specific Token Memory","created":"2024-03-15","cited_by_count":20},{"id":"2407.12345","title":"VisionTrap: Vision-Augmented Trajectory Prediction Guided by Textual Descriptions","created":"2024-07-17","cited_by_count":19},{"id":"2402.19298","title":"Suppress and Rebalance: Towards Generalized Multi-Modal Face Anti-Spoofing","created":"2024-02-29","cited_by_count":16},{"id":"2407.11588","title":"Progressive Pretext Task Learning for Human Trajectory Prediction","created":"2024-07-16","cited_by_count":16},{"id":"2407.11494","title":"Learning Semantic Latent Directions for Accurate and Controllable Human Motion Prediction","created":"2024-07-16","cited_by_count":14},{"id":"2404.02227","title":"OOSTraj: Out-of-Sight Trajectory Prediction With Vision-Positioning Denoising","created":"2024-04-02","cited_by_count":13},{"id":"2404.04458","title":"JRDB-Social: A Multifaceted Robotic Dataset for Understanding of Context and Dynamics of Human Interactions Within Social Groups","created":"2024-04-06","cited_by_count":13},{"id":"2311.06623","title":"VT-Former: An Exploratory Study on Vehicle Trajectory Prediction for Highway Surveillance through Graph Isomorphism and Transformer","created":"2023-11-11","cited_by_count":10},{"id":"2407.10164","title":"LabelDistill: Label-guided Cross-modal Knowledge Distillation for Camera-based 3D Object Detection","created":"2024-07-14","cited_by_count":9},{"id":"2411.00174","title":"Pedestrian Trajectory Prediction with Missing Data: Datasets, Imputation, and Benchmarking","created":"2024-10-31","cited_by_count":8},{"id":"2412.07369","title":"ITPNet: Towards Instantaneous Trajectory Prediction for Autonomous Driving","created":"2024-12-10","cited_by_count":2}],"next_cursor":null}