{"list":"other","total":55,"rows":[{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"2511.21631","title":"Qwen3-VL Technical Report","created":"2025-11-26","cited_by_count":2793},{"id":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"id":"2504.10479","title":"InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models","created":"2025-04-14","cited_by_count":1834},{"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":"2508.18265","title":"InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency","created":"2025-08-25","cited_by_count":1510},{"id":"2403.13372","title":"LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models","created":"2024-03-20","cited_by_count":1464},{"id":"2511.16719","title":"SAM 3: Segment Anything with Concepts","created":"2025-11-20","cited_by_count":906},{"id":"2401.12168","title":"SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities","created":"2024-01-22","cited_by_count":706},{"id":"2511.10647","title":"Depth Anything 3: Recovering the Visual Space from Any Views","created":"2025-11-13","cited_by_count":692},{"id":"2412.14171","title":"Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces","created":"2024-12-18","cited_by_count":611},{"id":"2312.16256","title":"DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Vision","created":"2023-12-26","cited_by_count":537},{"id":"2504.07491","title":"Kimi-VL Technical Report","created":"2025-04-10","cited_by_count":388},{"id":"2406.01584","title":"SpatialRGPT: Grounded Spatial Reasoning in Vision Language Models","created":"2024-06-03","cited_by_count":311},{"id":"2509.23661","title":"LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Training","created":"2025-09-28","cited_by_count":244},{"id":"2505.23747","title":"Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence","created":"2025-05-29","cited_by_count":217},{"id":"2505.23764","title":"MMSI-Bench: A Benchmark for Multi-Image Spatial Intelligence","created":"2025-05-29","cited_by_count":183},{"id":"2504.01805","title":"SpaceR: Reinforcing MLLMs in Video Spatial Reasoning","created":"2025-04-02","cited_by_count":159},{"id":"1804.04527","title":"SoccerNet: A Scalable Dataset for Action Spotting in Soccer Videos","created":"2018-04-12","cited_by_count":150},{"id":"2503.22976","title":"From Flatland to Space: Teaching Vision-Language Models to Perceive and Reason in 3D","created":"2025-03-29","cited_by_count":138},{"id":"2411.16537","title":"RoboSpatial: Teaching Spatial Understanding to 2D and 3D Vision-Language Models for Robotics","created":"2024-11-25","cited_by_count":136},{"id":"2511.04670","title":"Cambrian-S: Towards Spatial Supersensing in Video","created":"2025-11-06","cited_by_count":134},{"id":"2505.24625","title":"Learning from Videos for 3D World: Enhancing MLLMs with 3D Vision Geometry Priors","created":"2025-05-30","cited_by_count":120},{"id":"2505.21500","title":"ViewSpatial-Bench: Evaluating Multi-perspective Spatial Localization in Vision-Language Models","created":"2025-05-27","cited_by_count":118},{"id":"2506.21458","title":"MindCube: Spatial Mental Modeling from Limited Views","created":"2025-06-26","cited_by_count":95},{"id":"2510.08531","title":"SpatialLadder: Progressive Training for Spatial Reasoning in Vision-Language Models","created":"2025-10-09","cited_by_count":90},{"id":"1607.02643","title":"Hierarchical Deep Temporal Models for Group Activity Recognition","created":"2016-07-09","cited_by_count":89},{"id":"2511.05491","title":"Visual Spatial Tuning","created":"2025-11-07","cited_by_count":89},{"id":"2511.13719","title":"Scaling Spatial Intelligence with Multimodal Foundation Models","created":"2025-11-17","cited_by_count":82},{"id":"2504.06397","title":"PromptHMR: Promptable Human Mesh Recovery","created":"2025-04-08","cited_by_count":76},{"id":"2503.13111","title":"MM-Spatial: Exploring 3D Spatial Understanding in Multimodal LLMs","created":"2025-03-17","cited_by_count":73},{"id":"2304.04565","title":"SoccerNet-Caption: Dense Video Captioning for Soccer Broadcasts Commentaries","created":"2023-04-10","cited_by_count":57},{"id":"2310.10553","title":"TacticAI: an AI assistant for football tactics","created":"2023-10-16","cited_by_count":44},{"id":"2512.10863","title":"MMSI-Video-Bench: A Holistic Benchmark for Video-Based Spatial Intelligence","created":"2025-12-11","cited_by_count":38},{"id":"2306.10988","title":"Tame a Wild Camera: In-the-Wild Monocular Camera Calibration","created":"2023-06-19","cited_by_count":34},{"id":"2509.25413","title":"DepthLM: Metric Depth From Vision Language Models","created":"2025-09-29","cited_by_count":30},{"id":"2505.05456","title":"SITE: towards Spatial Intelligence Thorough Evaluation","created":"2025-05-08","cited_by_count":29},{"id":"2506.18385","title":"InternSpatial: A Comprehensive Dataset for Spatial Reasoning in Vision-Language Models","created":"2025-06-23","cited_by_count":28},{"id":"2410.08474","title":"SPORTU: A Comprehensive Sports Understanding Benchmark for Multimodal Large Language Models","created":"2024-10-11","cited_by_count":24},{"id":"2412.01820","title":"Towards Universal Soccer Video Understanding","created":"2024-12-02","cited_by_count":21},{"id":"2510.09606","title":"SpaceVista: All-Scale Visual Spatial Reasoning from mm to km","created":"2025-10-10","cited_by_count":19},{"id":"2505.03735","title":"Multi-Agent System for Comprehensive Soccer Understanding","created":"2025-05-06","cited_by_count":18},{"id":"2204.00003","title":"Ball 3D Localization From A Single Calibrated Image","created":"2022-03-30","cited_by_count":17},{"id":"2511.06499","title":"SportR: A Benchmark for Multimodal Large Language Model Reasoning in Sports","created":"2025-11-09","cited_by_count":17},{"id":"2402.15862","title":"SportQA: A Benchmark for Sports Understanding in Large Language Models","created":"2024-02-24","cited_by_count":15},{"id":"2508.07554","title":"FineBadminton: A Multi-Level Dataset for Fine-Grained Badminton Video Understanding","created":"2025-08-11","cited_by_count":10},{"id":"2507.20163","title":"Player-Centric Multimodal Prompt Generation for Large Language Model Based Identity-Aware Basketball Video Captioning","created":"2025-07-27","cited_by_count":7},{"id":"2603.06704","title":"On the Generalization Capacities of MLLMs for Spatial Intelligence","created":"2026-03-05","cited_by_count":7},{"id":"2504.19514","title":"FSBench: A Figure Skating Benchmark for Advancing Artistic Sports Understanding","created":"2025-04-28","cited_by_count":6},{"id":"2603.07660","title":"Holi-Spatial: Evolving Video Streams into Holistic 3D Spatial Intelligence","created":"2026-03-08","cited_by_count":6},{"id":"2511.12908","title":"DeepSport: A Multimodal Large Language Model for Comprehensive Sports Video Reasoning via Agentic Reinforcement Learning","created":"2025-11-17","cited_by_count":5},{"id":"2503.06522","title":"SGA-INTERACT: A 3D Skeleton-based Benchmark for Group Activity Understanding in Modern Basketball Tactic","created":"2025-03-09","cited_by_count":4},{"id":"2511.20250","title":"Uplifting Table Tennis: A Robust, Real-World Application for 3D Trajectory and Spin Estimation","created":"2025-11-25","cited_by_count":3},{"id":"2511.17045","title":"RacketVision: A Multiple Racket Sports Benchmark for Unified Ball and Racket Analysis","created":"2025-11-21","cited_by_count":2}],"next_cursor":null}