{"list":"other","total":65,"rows":[{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2409.12191","title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","created":"2024-09-18","cited_by_count":4234},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"1912.04838","title":"Scalability in Perception for Autonomous Driving: Waymo Open Dataset","created":"2019-12-10","cited_by_count":2451},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"2503.19786","title":"Gemma 3 Technical Report","created":"2025-03-25","cited_by_count":1824},{"id":"1904.05866","title":"Expressive Body Capture: 3D Hands, Face, and Body from a Single Image","created":"2019-04-11","cited_by_count":1612},{"id":"2412.05271","title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","created":"2024-12-06","cited_by_count":1599},{"id":"2403.13372","title":"LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models","created":"2024-03-20","cited_by_count":1464},{"id":"1904.03278","title":"AMASS: Archive of Motion Capture as Surface Shapes","created":"2019-04-05","cited_by_count":1236},{"id":"2209.14916","title":"Human Motion Diffusion Model","created":"2022-09-29","cited_by_count":1080},{"id":"2408.01800","title":"MiniCPM-V: A GPT-4V Level MLLM on Your Phone","created":"2024-08-03","cited_by_count":1079},{"id":"2208.15001","title":"MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model","created":"2022-08-31","cited_by_count":780},{"id":"2412.10302","title":"DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding","created":"2024-12-13","cited_by_count":572},{"id":"2312.14150","title":"DriveLM: Driving with Graph Visual Question Answering","created":"2023-12-21","cited_by_count":536},{"id":"2306.14795","title":"MotionGPT: Human Motion as a Foreign Language","created":"2023-06-26","cited_by_count":527},{"id":"2503.01743","title":"Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs","created":"2025-03-03","cited_by_count":521},{"id":"1708.07819","title":"Semantic Foggy Scene Understanding with Synthetic Data","created":"2017-08-25","cited_by_count":403},{"id":"2504.07491","title":"Kimi-VL Technical Report","created":"2025-04-10","cited_by_count":388},{"id":"2312.07488","title":"LMDrive: Closed-Loop End-to-End Driving with Large Language Models","created":"2023-12-12","cited_by_count":305},{"id":"2106.09696","title":"BABEL: Bodies, Action and Behavior with English Labels","created":"2021-06-17","cited_by_count":265},{"id":"2305.14836","title":"NuScenes-QA: A Multi-modal Visual Question Answering Benchmark for Autonomous Driving Scenario","created":"2023-05-24","cited_by_count":262},{"id":"2310.01957","title":"Driving with LLMs: Fusing Object-Level Vector Modality for Explainable Autonomous Driving","created":"2023-10-03","cited_by_count":232},{"id":"2307.00818","title":"Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset","created":"2023-07-03","cited_by_count":227},{"id":"2405.01483","title":"MANTIS: Interleaved Multi-Image Instruction Tuning","created":"2024-05-02","cited_by_count":216},{"id":"2312.07531","title":"WHAM: Reconstructing World-grounded Humans with Accurate 3D Motion","created":"2023-12-12","cited_by_count":206},{"id":"2007.11858","title":"Whole-Body Human Pose Estimation in the Wild","created":"2020-07-23","cited_by_count":178},{"id":"2007.11755","title":"History Repeats Itself: Human Motion Prediction via Motion Attention","created":"2020-07-23","cited_by_count":165},{"id":"2112.01524","title":"GLAMR: Global Occlusion-Aware Human Mesh Recovery with Dynamic Cameras","created":"2021-12-02","cited_by_count":153},{"id":"2312.14115","title":"LingoQA: Visual Question Answering for Autonomous Driving","created":"2023-12-21","cited_by_count":145},{"id":"2302.12827","title":"Decoupling Human and Camera Motion from Videos in the Wild","created":"2023-02-24","cited_by_count":142},{"id":"2209.10767","title":"DRAMA: Joint Risk Localization and Captioning in Driving","created":"2022-09-22","cited_by_count":126},{"id":"2312.00438","title":"Dolphins: Multimodal Language Model for Driving","created":"2023-12-01","cited_by_count":124},{"id":"2312.03661","title":"Reason2Drive: Towards Interpretable and Chain-based Reasoning for Autonomous Driving","created":"2023-12-06","cited_by_count":123},{"id":"2104.03516","title":"TokenPose: Learning Keypoint Tokens for Human Pose Estimation","created":"2021-04-08","cited_by_count":107},{"id":"2207.01567","title":"Back to MLP: A Simple Baseline for Human Motion Prediction","created":"2022-07-04","cited_by_count":100},{"id":"2402.10828","title":"RAG-Driver: Generalisable Driving Explanations with Retrieval-Augmented In-Context Learning in Multi-Modal Large Language Model","created":"2024-02-16","cited_by_count":92},{"id":"2408.10845","title":"CoVLA: Comprehensive Vision-Language-Action Dataset for Autonomous Driving","created":"2024-08-19","cited_by_count":77},{"id":"1912.12148","title":"DADA: Driver Attention Prediction in Driving Accident Scenarios","created":"2019-12-18","cited_by_count":70},{"id":"2012.15175","title":"Rethinking the Heatmap Regression for Bottom-up Human Pose Estimation","created":"2020-12-30","cited_by_count":69},{"id":"2203.13694","title":"Implicit Neural Representations for Variable Length Human Motion Generation","created":"2022-03-25","cited_by_count":61},{"id":"2105.05226","title":"Home Action Genome: Cooperative Compositional Action Understanding","created":"2021-05-11","cited_by_count":53},{"id":"2104.05485","title":"Predicting Pedestrian Crossing Intention with Feature Fusion and Spatio-Temporal Attention","created":"2021-04-12","cited_by_count":48},{"id":"2209.08790","title":"D&D: Learning Human Dynamics from Dynamic Camera","created":"2022-09-19","cited_by_count":41},{"id":"1609.04741","title":"Joint Attention in Autonomous Driving (JAAD)","created":"2016-09-15","cited_by_count":36},{"id":"2008.07931","title":"Motion Capture from Internet Videos","created":"2020-08-18","cited_by_count":33},{"id":"2312.06352","title":"NuScenes-MQA: Integrated Evaluation of Captions and QA for Autonomous Driving Datasets using Markup Annotations","created":"2023-12-11","cited_by_count":31},{"id":"2211.00385","title":"Behavioral Intention Prediction in Driving Scenes: A Survey","created":"2022-11-01","cited_by_count":30},{"id":"1605.02914","title":"Recurrent Human Pose Estimation","created":"2016-05-10","cited_by_count":27},{"id":"2110.10355","title":"Dynamic Multi-Person Mesh Recovery From Uncalibrated Multi-View Cameras","created":"2021-10-20","cited_by_count":26},{"id":"1702.03555","title":"Agreeing to Cross: How Drivers and Pedestrians Communicate","created":"2017-02-12","cited_by_count":23},{"id":"2308.08414","title":"Tem-adapter: Adapting Image-Text Pretraining for Video Question Answer","created":"2023-08-16","cited_by_count":22},{"id":"2308.08942","title":"Auxiliary Tasks Benefit 3D Skeleton-based Human Motion Prediction","created":"2023-08-17","cited_by_count":20},{"id":"2301.05175","title":"Scene-Aware 3D Multi-Human Motion Capture from a Single Camera","created":"2023-01-12","cited_by_count":19},{"id":"2106.12442","title":"Euro-PVI: Pedestrian Vehicle Interactions in Dense Urban Centers","created":"2021-06-22","cited_by_count":16},{"id":"2410.13790","title":"MotionBank: A Large-scale Video Motion Benchmark with Disentangled Rule-based Annotations","created":"2024-10-17","cited_by_count":14},{"id":"2312.11850","title":"GCNext: Towards the Unity of Graph Convolutions for Human Motion Prediction","created":"2023-12-19","cited_by_count":12},{"id":"2210.14714","title":"TAMFormer: Multi-Modal Transformer with Learned Attention Mask for Early Intent Prediction","created":"2022-10-26","cited_by_count":9},{"id":"2402.19237","title":"Context-based Interpretable Spatio-Temporal Graph Convolutional Network for Human Motion Forecasting","created":"2024-02-21","cited_by_count":6},{"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},{"id":"2410.07500","title":"Learning to Generate Diverse Pedestrian Movements from Web Videos with Noisy Labels","created":"2024-10-10","cited_by_count":4},{"id":"2412.05277","title":"Text to Blind Motion","created":"2024-12-06","cited_by_count":3}],"next_cursor":null}