{"list":"other","total":97,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"2405.21060","title":"Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality","created":"2024-05-31","cited_by_count":1336},{"id":"1805.04687","title":"BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning","created":"2018-05-12","cited_by_count":1288},{"id":"2212.10156","title":"Planning-oriented Autonomous Driving","created":"2022-12-20","cited_by_count":1087},{"id":"1703.07402","title":"Simple Online and Realtime Tracking with a Deep Association Metric","created":"2017-03-21","cited_by_count":910},{"id":"1602.00763","title":"Simple Online and Realtime Tracking","created":"2016-02-02","cited_by_count":868},{"id":"2401.06066","title":"DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models","created":"2024-01-11","cited_by_count":867},{"id":"2110.06864","title":"ByteTrack: Multi-Object Tracking by Associating Every Detection Box","created":"2021-10-13","cited_by_count":823},{"id":"1609.01775","title":"Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking","created":"2016-09-06","cited_by_count":692},{"id":"2009.07736","title":"HOTA: A Higher Order Metric for Evaluating Multi-Object Tracking","created":"2020-09-16","cited_by_count":552},{"id":"2304.08069","title":"DETRs Beat YOLOs on Real-time Object Detection","created":"2023-04-17","cited_by_count":533},{"id":"1603.00831","title":"MOT16: A Benchmark for Multi-Object Tracking","created":"2016-03-02","cited_by_count":532},{"id":"2101.02702","title":"TrackFormer: Multi-Object Tracking with Transformers","created":"2021-01-07","cited_by_count":518},{"id":"2105.03247","title":"MOTR: End-to-End Multiple-Object Tracking with Transformer","created":"2021-05-07","cited_by_count":381},{"id":"2012.15460","title":"TransTrack: Multiple Object Tracking with Transformer","created":"2020-12-31","cited_by_count":371},{"id":"2003.09003","title":"MOT20: A benchmark for multi object tracking in crowded scenes","created":"2020-03-19","cited_by_count":357},{"id":"2203.14360","title":"Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Tracking","created":"2022-03-27","cited_by_count":346},{"id":"2206.14651","title":"BoT-SORT: Robust Associations Multi-Pedestrian Tracking","created":"2022-06-29","cited_by_count":320},{"id":"2111.14690","title":"DanceTrack: Multi-Object Tracking in Uniform Appearance and Diverse Motion","created":"2021-11-29","cited_by_count":217},{"id":"2202.13514","title":"StrongSORT: Make DeepSORT Great Again","created":"2022-02-28","cited_by_count":213},{"id":"2311.16813","title":"Panacea: Panoramic and Controllable Video Generation for Autonomous Driving","created":"2023-11-28","cited_by_count":168},{"id":"2211.09791","title":"MOTRv2: Bootstrapping End-to-End Multi-Object Tracking by Pretrained Object Detectors","created":"2022-11-17","cited_by_count":148},{"id":"2304.05170","title":"SportsMOT: A Large Multi-Object Tracking Dataset in Multiple Sports Scenes","created":"2023-04-11","cited_by_count":131},{"id":"2203.09283","title":"PanoFormer: Panorama Transformer for Indoor 360 Depth Estimation","created":"2022-03-17","cited_by_count":95},{"id":"2102.03550","title":"UniFuse: Unidirectional Fusion for 360$^{\\circ}$ Panorama Depth Estimation","created":"2021-02-06","cited_by_count":92},{"id":"2307.15700","title":"MeMOTR: Long-Term Memory-Augmented Transformer for Multi-Object Tracking","created":"2023-07-28","cited_by_count":88},{"id":"2404.06903","title":"DreamScene360: Unconstrained Text-to-3D Scene Generation with Panoramic Gaussian Splatting","created":"2024-04-10","cited_by_count":82},{"id":"2305.19195","title":"PanoGen: Text-Conditioned Panoramic Environment Generation for Vision-and-Language Navigation","created":"2023-05-30","cited_by_count":77},{"id":"2308.00783","title":"Hybrid-SORT: Weak Cues Matter for Online Multi-Object Tracking","created":"2023-08-01","cited_by_count":67},{"id":"2303.10404","title":"MotionTrack: Learning Robust Short-term and Long-term Motions for Multi-Object Tracking","created":"2023-03-18","cited_by_count":64},{"id":"2403.16848","title":"Multiple Object Tracking as ID Prediction","created":"2024-03-25","cited_by_count":60},{"id":"2403.02075","title":"DiffMOT: A Real-time Diffusion-based Multiple Object Tracker with Non-linear Prediction","created":"2024-03-04","cited_by_count":59},{"id":"2206.07704","title":"Waymo Open Dataset: Panoramic Video Panoptic Segmentation","created":"2022-06-15","cited_by_count":58},{"id":"2401.06578","title":"360DVD: Controllable Panorama Video Generation with 360-Degree Video Diffusion Model","created":"2024-01-12","cited_by_count":58},{"id":"2304.08408","title":"OVTrack: Open-Vocabulary Multiple Object Tracking","created":"2023-04-17","cited_by_count":53},{"id":"2207.11860","title":"Behind Every Domain There is a Shift: Adapting Distortion-aware Vision Transformers for Panoramic Semantic Segmentation","created":"2022-07-25","cited_by_count":46},{"id":"2310.16831","title":"PERF: Panoramic Neural Radiance Field from a Single Panorama","created":"2023-10-25","cited_by_count":45},{"id":"2312.08952","title":"UCMCTrack: Multi-Object Tracking with Uniform Camera Motion Compensation","created":"2023-12-14","cited_by_count":44},{"id":"2304.07803","title":"EGformer: Equirectangular Geometry-biased Transformer for 360 Depth Estimation","created":"2023-04-16","cited_by_count":43},{"id":"2106.08827","title":"JRDB-Act: A Large-scale Dataset for Spatio-temporal Action, Social Group and Activity Detection","created":"2021-06-16","cited_by_count":39},{"id":"2410.24203","title":"DiffPano: Scalable and Consistent Text to Panorama Generation with Spherical Epipolar-Aware Diffusion","created":"2024-10-31","cited_by_count":38},{"id":"2209.02952","title":"BiFuse++: Self-supervised and Efficient Bi-projection Fusion for 360 Depth Estimation","created":"2022-09-07","cited_by_count":35},{"id":"2404.00989","title":"360+x: A Panoptic Multi-modal Scene Understanding Dataset","created":"2024-04-01","cited_by_count":35},{"id":"2405.08909","title":"ADA-Track++: End-to-End Multi-Camera 3D Multi-Object Tracking with Alternating Detection and Association","created":"2024-05-14","cited_by_count":33},{"id":"2312.16245","title":"iKUN: Speak to Trackers without Retraining","created":"2023-12-25","cited_by_count":32},{"id":"2403.16376","title":"Elite360D: Towards Efficient 360 Depth Estimation via Semantic- and Distance-Aware Bi-Projection Fusion","created":"2024-03-25","cited_by_count":31},{"id":"2311.17389","title":"360Loc: A Dataset and Benchmark for Omnidirectional Visual Localization with Cross-device Queries","created":"2023-11-29","cited_by_count":30},{"id":"2403.16370","title":"GoodSAM: Bridging Domain and Capacity Gaps via Segment Anything Model for Distortion-aware Panoramic Semantic Segmentation","created":"2024-03-25","cited_by_count":28},{"id":"2404.16501","title":"360SFUDA++: Towards Source-free UDA for Panoramic Segmentation by Learning Reliable Category Prototypes","created":"2024-04-25","cited_by_count":28},{"id":"2503.07098","title":"OmniSAM: Omnidirectional Segment Anything Model for UDA in Panoramic Semantic Segmentation","created":"2025-03-10","cited_by_count":28},{"id":"2202.13388","title":"PanoFlow: Learning 360{\\deg} Optical Flow for Surrounding Temporal Understanding","created":"2022-02-27","cited_by_count":26},{"id":"2306.03403","title":"SGAT4PASS: Spherical Geometry-Aware Transformer for PAnoramic Semantic Segmentation","created":"2023-06-06","cited_by_count":26},{"id":"2509.04444","title":"One Flight Over the Gap: A Survey from Perspective to Panoramic Vision","created":"2025-09-04","cited_by_count":25},{"id":"2502.10444","title":"A Survey of Representation Learning, Optimization Strategies, and Applications for Omnidirectional Vision","created":"2025-02-11","cited_by_count":24},{"id":"2402.02968","title":"Delving into Multi-modal Multi-task Foundation Models for Road Scene Understanding: From Learning Paradigm Perspectives","created":"2024-02-05","cited_by_count":23},{"id":"2406.00429","title":"Towards Generalizable Multi-Object Tracking","created":"2024-06-01","cited_by_count":23},{"id":"2308.11157","title":"TOPIC: A Parallel Association Paradigm for Multi-Object Tracking under Complex Motions and Diverse Scenes","created":"2023-08-22","cited_by_count":21},{"id":"2307.07313","title":"HEAL-SWIN: A Vision Transformer On The Sphere","created":"2023-07-14","cited_by_count":20},{"id":"2308.14726","title":"PanoSwin: a Pano-style Swin Transformer for Panorama Understanding","created":"2023-08-28","cited_by_count":20},{"id":"2305.09078","title":"PanelNet: Understanding 360 Indoor Environment via Panel Representation","created":"2023-05-16","cited_by_count":19},{"id":"2305.12497","title":"PanoContext-Former: Panoramic Total Scene Understanding with a Transformer","created":"2023-05-21","cited_by_count":19},{"id":"2309.12303","title":"PanoVOS: Bridging Non-panoramic and Panoramic Views with Transformer for Video Segmentation","created":"2023-09-21","cited_by_count":18},{"id":"2403.04700","title":"Delving into the Trajectory Long-tail Distribution for Muti-object Tracking","created":"2024-03-07","cited_by_count":18},{"id":"2202.02796","title":"GLPanoDepth: Global-to-Local Panoramic Depth Estimation","created":"2022-02-06","cited_by_count":16},{"id":"2303.00971","title":"Disentangling Orthogonal Planes for Indoor Panoramic Room Layout Estimation with Cross-Scale Distortion Awareness","created":"2023-03-02","cited_by_count":14},{"id":"2203.03806","title":"Panoramic Human Activity Recognition","created":"2022-03-08","cited_by_count":13},{"id":"2306.12992","title":"Minimalist and High-Quality Panoramic Imaging with PSF-aware Transformers","created":"2023-06-22","cited_by_count":13},{"id":"2412.06968","title":"SphereUFormer: A U-Shaped Transformer for Spherical 360 Perception","created":"2024-12-09","cited_by_count":13},{"id":"2503.04565","title":"Omnidirectional Multi-Object Tracking","created":"2025-03-06","cited_by_count":13},{"id":"2503.09010","title":"HumanoidPano: Hybrid Spherical Panoramic-LiDAR Cross-Modal Perception for Humanoid Robots","created":"2025-03-12","cited_by_count":13},{"id":"2403.05021","title":"Beyond MOT: Semantic Multi-Object Tracking","created":"2024-03-08","cited_by_count":12},{"id":"2307.14630","title":"360VOT: A New Benchmark Dataset for Omnidirectional Visual Object Tracking","created":"2023-07-27","cited_by_count":11},{"id":"2403.19904","title":"Fully Geometric Panoramic Localization","created":"2024-03-29","cited_by_count":11},{"id":"2309.10815","title":"PanopticNeRF-360: Panoramic 3D-to-2D Label Transfer in Urban Scenes","created":"2023-09-19","cited_by_count":10},{"id":"2403.02767","title":"DeconfuseTrack:Dealing with Confusion for Multi-Object Tracking","created":"2024-03-05","cited_by_count":9},{"id":"2403.15712","title":"PNAS-MOT: Multi-Modal Object Tracking with Pareto Neural Architecture Search","created":"2024-03-23","cited_by_count":9},{"id":"2105.14683","title":"Know Your Surroundings: Panoramic Multi-Object Tracking by Multimodality Collaboration","created":"2021-05-31","cited_by_count":8},{"id":"2208.00776","title":"Deep 360$^\\circ$ Optical Flow Estimation Based on Multi-Projection Fusion","created":"2022-07-27","cited_by_count":8},{"id":"2404.13953","title":"360VOTS: Visual Object Tracking and Segmentation in Omnidirectional Videos","created":"2024-04-22","cited_by_count":8},{"id":"2408.16469","title":"Multi-source Domain Adaptation for Panoramic Semantic Segmentation","created":"2024-08-29","cited_by_count":8},{"id":"2409.13912","title":"OneBEV: Using One Panoramic Image for Bird's-Eye-View Semantic Mapping","created":"2024-09-20","cited_by_count":8},{"id":"2506.14271","title":"Leader360V: The Large-scale, Real-world 360 Video Dataset for Multi-task Learning in Diverse Environment","created":"2025-06-17","cited_by_count":8},{"id":"2507.21960","title":"PanoSplatt3R: Leveraging Perspective Pretraining for Generalized Unposed Wide-Baseline Panorama Reconstruction","created":"2025-07-29","cited_by_count":8},{"id":"2508.02512","title":"QuaDreamer: Controllable Panoramic Video Generation for Quadruped Robots","created":"2025-08-04","cited_by_count":8},{"id":"2407.02182","title":"Occlusion-Aware Seamless Segmentation","created":"2024-07-02","cited_by_count":7},{"id":"2312.16268","title":"360 Layout Estimation via Orthogonal Planes Disentanglement and Multi-view Geometric Consistency Perception","created":"2023-12-26","cited_by_count":5},{"id":"2507.20217","title":"Humanoid Occupancy: Enabling A Generalized Multimodal Occupancy Perception System on Humanoid Robots","created":"2025-07-27","cited_by_count":5},{"id":"2505.07446","title":"TPT-Bench: A Large-Scale, Long-Term and Robot-Egocentric Dataset for Benchmarking Target Person Tracking","created":"2025-05-12","cited_by_count":4},{"id":"2506.23897","title":"PriOr-Flow: Enhancing Primitive Panoramic Optical Flow with Orthogonal View","created":"2025-06-30","cited_by_count":4},{"id":"2404.00252","title":"Learned Scanpaths Aid Blind Panoramic Video Quality Assessment","created":"2024-03-30","cited_by_count":3},{"id":"2508.20221","title":"Spherical Vision Transformers for Audio-Visual Saliency Prediction in 360-Degree Videos","created":"2025-08-27","cited_by_count":3},{"id":"2502.12655","title":"LiMo-Calib: On-Site Fast LiDAR-Motor Calibration for Quadruped Robot-Based Panoramic 3D Sensing System","created":"2025-02-18","cited_by_count":2},{"id":"2506.13133","title":"EmbodiedPlace: Learning Mixture-of-Features with Embodied Constraints for Visual Place Recognition","created":"2025-06-16","cited_by_count":2},{"id":"2507.12832","title":"MVA 2025 Small Multi-Object Tracking for Spotting Birds Challenge: Dataset, Methods, and Results","created":"2025-07-17","cited_by_count":2},{"id":"2403.14113","title":"Spatio-Temporal Proximity-Aware Dual-Path Model for Panoramic Activity Recognition","created":"2024-03-21","cited_by_count":1}],"next_cursor":null}