{"list":"other","total":98,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"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":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332},{"id":"1608.00272","title":"Modeling Context in Referring Expressions","created":"2016-07-31","cited_by_count":1063},{"id":"1904.08405","title":"Event-based Vision: A Survey","created":"2019-04-17","cited_by_count":1016},{"id":"2104.12763","title":"MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding","created":"2021-04-26","cited_by_count":819},{"id":"2401.17270","title":"YOLO-World: Real-Time Open-Vocabulary Object Detection","created":"2024-01-30","cited_by_count":503},{"id":"1912.08830","title":"ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language","created":"2019-12-18","cited_by_count":452},{"id":"1906.07165","title":"High Speed and High Dynamic Range Video with an Event Camera","created":"2019-06-15","cited_by_count":345},{"id":"2306.09683","title":"Scaling Open-Vocabulary Object Detection","created":"2023-06-16","cited_by_count":343},{"id":"2311.15826","title":"GeoChat: Grounded Large Vision-Language Model for Remote Sensing","created":"2023-11-24","cited_by_count":328},{"id":"1812.08156","title":"Unsupervised Event-based Learning of Optical Flow, Depth, and Egomotion","created":"2018-12-19","cited_by_count":307},{"id":"2205.06230","title":"Simple Open-Vocabulary Object Detection with Vision Transformers","created":"2022-05-12","cited_by_count":305},{"id":"2103.06011","title":"DSEC: A Stereo Event Camera Dataset for Driving Scenarios","created":"2021-03-10","cited_by_count":303},{"id":"1801.10202","title":"The Multi Vehicle Stereo Event Camera Dataset: An Event Camera Dataset for 3D Perception","created":"2018-01-30","cited_by_count":254},{"id":"1802.06898","title":"EV-FlowNet: Self-Supervised Optical Flow Estimation for Event-based Cameras","created":"2018-02-19","cited_by_count":224},{"id":"1904.08245","title":"End-to-End Learning of Representations for Asynchronous Event-Based Data","created":"2019-04-17","cited_by_count":217},{"id":"1804.01310","title":"Event-based Vision meets Deep Learning on Steering Prediction for Self-driving Cars","created":"2018-04-04","cited_by_count":200},{"id":"1908.06354","title":"A Fast and Accurate One-Stage Approach to Visual Grounding","created":"2019-08-18","cited_by_count":195},{"id":"2009.13436","title":"Learning to Detect Objects with a 1 Megapixel Event Camera","created":"2020-09-28","cited_by_count":186},{"id":"2306.15880","title":"Towards Open Vocabulary Learning: A Survey","created":"2023-06-28","cited_by_count":166},{"id":"1912.03095","title":"Video to Events: Recycling Video Datasets for Event Cameras","created":"2019-12-06","cited_by_count":165},{"id":"2212.05598","title":"Recurrent Vision Transformers for Object Detection with Event Cameras","created":"2022-12-11","cited_by_count":159},{"id":"2108.10552","title":"E-RAFT: Dense Optical Flow from Event Cameras","created":"2021-08-24","cited_by_count":152},{"id":"2106.03089","title":"Referring Transformer: A One-step Approach to Multi-task Visual Grounding","created":"2021-06-06","cited_by_count":143},{"id":"2103.01128","title":"InstanceRefer: Cooperative Holistic Understanding for Visual Grounding on Point Clouds through Instance Multi-level Contextual Referring","created":"2021-03-01","cited_by_count":141},{"id":"2112.08879","title":"Bottom Up Top Down Detection Transformers for Language Grounding in Images and Point Clouds","created":"2021-12-16","cited_by_count":128},{"id":"2105.11450","title":"SAT: 2D Semantics Assisted Training for 3D Visual Grounding","created":"2021-05-24","cited_by_count":124},{"id":"2210.12634","title":"RSVG: Exploring Data and Models for Visual Grounding on Remote Sensing Data","created":"2022-10-23","cited_by_count":123},{"id":"2501.04003","title":"Are VLMs Ready for Autonomous Driving? An Empirical Study from the Reliability, Data, and Metric Perspectives","created":"2025-01-07","cited_by_count":122},{"id":"1704.03470","title":"Learning Two-Branch Neural Networks for Image-Text Matching Tasks","created":"2017-04-11","cited_by_count":119},{"id":"2204.06272","title":"3D-SPS: Single-Stage 3D Visual Grounding via Referred Point Progressive Selection","created":"2022-04-13","cited_by_count":110},{"id":"2103.11555","title":"Context-aware Biaffine Localizing Network for Temporal Sentence Grounding","created":"2021-03-22","cited_by_count":107},{"id":"1812.04794","title":"Neighbourhood Watch: Referring Expression Comprehension via Language-guided Graph Attention Networks","created":"2018-12-12","cited_by_count":102},{"id":"2203.16434","title":"TubeDETR: Spatio-Temporal Video Grounding with Transformers","created":"2022-03-30","cited_by_count":98},{"id":"1811.12039","title":"EV-SegNet: Semantic Segmentation for Event-based Cameras","created":"2018-11-29","cited_by_count":93},{"id":"2303.03366","title":"Referring Multi-Object Tracking","created":"2023-03-06","cited_by_count":93},{"id":"2112.01041","title":"N-ImageNet: Towards Robust, Fine-Grained Object Recognition with Event Cameras","created":"2021-12-02","cited_by_count":92},{"id":"2204.07640","title":"Event-aided Direct Sparse Odometry","created":"2022-04-15","cited_by_count":92},{"id":"2302.08890","title":"Deep Learning for Event-based Vision: A Comprehensive Survey and Benchmarks","created":"2023-02-17","cited_by_count":90},{"id":"2108.02388","title":"TransRefer3D: Entity-and-Relation Aware Transformer for Fine-Grained 3D Visual Grounding","created":"2021-08-05","cited_by_count":86},{"id":"2010.08350","title":"Learning Monocular Dense Depth from Events","created":"2020-10-16","cited_by_count":85},{"id":"1711.01458","title":"DDD17: End-To-End DAVIS Driving Dataset","created":"2017-11-04","cited_by_count":84},{"id":"2203.10016","title":"ESS: Learning Event-based Semantic Segmentation from Still Images","created":"2022-03-18","cited_by_count":82},{"id":"2103.16381","title":"Free-form Description Guided 3D Visual Graph Network for Object Grounding in Point Cloud","created":"2021-03-30","cited_by_count":81},{"id":"1908.07129","title":"Zero-Shot Grounding of Objects from Natural Language Queries","created":"2019-08-20","cited_by_count":79},{"id":"2402.15584","title":"State Space Models for Event Cameras","created":"2024-02-23","cited_by_count":75},{"id":"2309.14611","title":"Event Stream-based Visual Object Tracking: A High-Resolution Benchmark Dataset and A Novel Baseline","created":"2023-09-26","cited_by_count":73},{"id":"2401.17868","title":"Convolution Meets LoRA: Parameter Efficient Finetuning for Segment Anything Model","created":"2024-01-31","cited_by_count":69},{"id":"2408.13627","title":"Recent Event Camera Innovations: A Survey","created":"2024-08-24","cited_by_count":68},{"id":"2412.04383","title":"SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Grounding","created":"2024-12-05","cited_by_count":67},{"id":"2311.15383","title":"Visual Programming for Zero-shot Open-Vocabulary 3D Visual Grounding","created":"2023-11-26","cited_by_count":64},{"id":"1702.07389","title":"Continuous-Time Visual-Inertial Odometry for Event Cameras","created":"2017-02-23","cited_by_count":57},{"id":"2405.05258","title":"Multi-Modal Data-Efficient 3D Scene Understanding for Autonomous Driving","created":"2024-05-08","cited_by_count":54},{"id":"2304.13455","title":"From Chaos Comes Order: Ordering Event Representations for Object Recognition and Detection","created":"2023-04-26","cited_by_count":52},{"id":"2412.20206","title":"Toward Visual Grounding: A Survey","created":"2024-12-28","cited_by_count":52},{"id":"2301.01928","title":"Event Camera Data Pre-training","created":"2023-01-05","cited_by_count":50},{"id":"2111.12341","title":"EvDistill: Asynchronous Events to End-task Learning via Bidirectional Reconstruction-guided Cross-modal Knowledge Distillation","created":"2021-11-24","cited_by_count":47},{"id":"2305.17852","title":"Hierarchical Neural Memory Network for Low Latency Event Processing","created":"2023-05-29","cited_by_count":47},{"id":"2411.11904","title":"GeoGround: A Unified Large Vision-Language Model for Remote Sensing Visual Grounding","created":"2024-11-16","cited_by_count":47},{"id":"2203.15125","title":"Text2Pos: Text-to-Point-Cloud Cross-Modal Localization","created":"2022-03-28","cited_by_count":40},{"id":"2209.08323","title":"RGB-Event Fusion for Moving Object Detection in Autonomous Driving","created":"2022-09-17","cited_by_count":40},{"id":"2308.04047","title":"SODFormer: Streaming Object Detection with Transformer Using Events and Frames","created":"2023-08-08","cited_by_count":39},{"id":"2404.01882","title":"Scene Adaptive Sparse Transformer for Event-based Object Detection","created":"2024-04-02","cited_by_count":39},{"id":"2405.05259","title":"OpenESS: Event-based Semantic Scene Understanding with Open Vocabularies","created":"2024-05-08","cited_by_count":38},{"id":"2203.02966","title":"Exploring Optical-Flow-Guided Motion and Detection-Based Appearance for Temporal Sentence Grounding","created":"2022-03-06","cited_by_count":35},{"id":"2103.07894","title":"Refer-it-in-RGBD: A Bottom-up Approach for 3D Visual Grounding in RGBD Images","created":"2021-03-14","cited_by_count":33},{"id":"2403.12534","title":"ExACT: Language-guided Conceptual Reasoning and Uncertainty Estimation for Event-based Action Recognition and More","created":"2024-03-19","cited_by_count":33},{"id":"2109.01801","title":"Dual Transfer Learning for Event-based End-task Prediction via Pluggable Event to Image Translation","created":"2021-09-04","cited_by_count":32},{"id":"2211.12324","title":"Pushing the Limits of Asynchronous Graph-based Object Detection with Event Cameras","created":"2022-11-22","cited_by_count":32},{"id":"2401.12761","title":"MUSES: The Multi-Sensor Semantic Perception Dataset for Driving under Uncertainty","created":"2024-01-23","cited_by_count":32},{"id":"2308.09383","title":"Label-Free Event-based Object Recognition via Joint Learning with Image Reconstruction from Events","created":"2023-08-18","cited_by_count":28},{"id":"2407.12582","title":"Embracing Events and Frames with Hierarchical Feature Refinement Network for Object Detection","created":"2024-07-17","cited_by_count":28},{"id":"2412.00832","title":"EventGPT: Event Stream Understanding with Multimodal Large Language Models","created":"2024-12-01","cited_by_count":28},{"id":"2211.10754","title":"HALSIE: Hybrid Approach to Learning Segmentation by Simultaneously Exploiting Image and Event Modalities","created":"2022-11-19","cited_by_count":25},{"id":"2406.05785","title":"A Survey on Text-guided 3D Visual Grounding: Elements, Recent Advances, and Future Directions","created":"2024-06-09","cited_by_count":25},{"id":"2305.00434","title":"EVREAL: Towards a Comprehensive Benchmark and Analysis Suite for Event-based Video Reconstruction","created":"2023-04-30","cited_by_count":24},{"id":"2311.17286","title":"LEOD: Label-Efficient Object Detection for Event Cameras","created":"2023-11-29","cited_by_count":24},{"id":"2312.08022","title":"Mono3DVG: 3D Visual Grounding in Monocular Images","created":"2023-12-13","cited_by_count":22},{"id":"2310.18773","title":"CityRefer: Geography-aware 3D Visual Grounding Dataset on City-scale Point Cloud Data","created":"2023-10-28","cited_by_count":18},{"id":"2307.11558","title":"Advancing Visual Grounding with Scene Knowledge: Benchmark and Method","created":"2023-07-21","cited_by_count":17},{"id":"2501.13707","title":"EventVL: Understand Event Streams via Multimodal Large Language Model","created":"2025-01-23","cited_by_count":13},{"id":"2311.02327","title":"ECMD: An Event-Centric Multisensory Driving Dataset for SLAM","created":"2023-11-04","cited_by_count":11},{"id":"2412.06708","title":"FlexEvent: Towards Flexible Event-Frame Object Detection at Varying Operational Frequencies","created":"2024-12-09","cited_by_count":10},{"id":"2503.19916","title":"EventFly: Event Camera Perception from Ground to the Sky","created":"2025-03-25","cited_by_count":10},{"id":"2403.16788","title":"HPL-ESS: Hybrid Pseudo-Labeling for Unsupervised Event-based Semantic Segmentation","created":"2024-03-25","cited_by_count":9},{"id":"2407.10703","title":"Towards Robust Event-based Networks for Nighttime via Unpaired Day-to-Night Event Translation","created":"2024-07-15","cited_by_count":9},{"id":"2412.02890","title":"EvRT-DETR: Latent Space Adaptation of Image Detectors for Event-based Vision","created":"2024-12-03","cited_by_count":9},{"id":"2304.05645","title":"WildRefer: 3D Object Localization in Large-scale Dynamic Scenes with Multi-modal Visual Data and Natural Language","created":"2023-04-12","cited_by_count":8},{"id":"2404.04698","title":"CEAR: Comprehensive Event Camera Dataset for Rapid Perception of Agile Quadruped Robots","created":"2024-04-06","cited_by_count":7},{"id":"2406.14178","title":"EvSegSNN: Neuromorphic Semantic Segmentation for Event Data","created":"2024-06-20","cited_by_count":7},{"id":"2410.19164","title":"HUE Dataset: High-Resolution Event and Frame Sequences for Low-Light Vision","created":"2024-10-24","cited_by_count":5},{"id":"2307.15829","title":"Seeing Behind Dynamic Occlusions with Event Cameras","created":"2023-07-28","cited_by_count":3},{"id":"2404.01801","title":"EventSleep: Sleep Activity Recognition with Event Cameras","created":"2024-04-02","cited_by_count":3},{"id":"2410.15615","title":"Joint Top-Down and Bottom-Up Frameworks for 3D Visual Grounding","created":"2024-10-21","cited_by_count":3}],"next_cursor":null}