{"total":37,"rows":[{"id":"2207.14096","title":"Towards Large-Scale Small Object Detection: Survey and Benchmarks","created":"2022-07-28","cited_by_count":122,"area":null},{"id":"2303.02936","title":"UniHCP: A Unified Model for Human-Centric Perceptions","created":"2023-03-06","cited_by_count":59,"area":null},{"id":"2303.05675","title":"HumanBench: Towards General Human-centric Perception with Projector Assisted Pretraining","created":"2023-03-10","cited_by_count":38,"area":null},{"id":"2204.01026","title":"STCrowd: A Multimodal Dataset for Pedestrian Perception in Crowded Scenes","created":"2022-04-03","cited_by_count":35,"area":null},{"id":"2406.14482","title":"Visible-Thermal Tiny Object Detection: A Benchmark Dataset and Baselines","created":"2024-06-20","cited_by_count":27,"area":null},{"id":"2301.10931","title":"Towards Continual Egocentric Activity Recognition: A Multi-modal Egocentric Activity Dataset for Continual Learning","created":"2023-01-26","cited_by_count":26,"area":null},{"id":"2312.01697","title":"Hulk: A Universal Knowledge Translator for Human-Centric Tasks","created":"2023-12-04","cited_by_count":22,"area":null},{"id":"2304.03135","title":"VLPD: Context-Aware Pedestrian Detection via Vision-Language Semantic Self-Supervision","created":"2023-04-06","cited_by_count":19,"area":null},{"id":"2207.11169","title":"Rethinking Few-Shot Object Detection on a Multi-Domain Benchmark","created":"2022-07-22","cited_by_count":17,"area":null},{"id":"2509.25182","title":"DC-VideoGen: Efficient Video Generation with Deep Compression Video Autoencoder","created":"2025-09-29","cited_by_count":16,"area":null},{"id":"2306.02744","title":"Towards Better Explanations for Object Detection","created":"2023-06-05","cited_by_count":14,"area":null},{"id":"2201.03176","title":"Pedestrian Detection: Domain Generalization, CNNs, Transformers and Beyond","created":"2022-01-10","cited_by_count":8,"area":null},{"id":"2307.09143","title":"MVA2023 Small Object Detection Challenge for Spotting Birds: Dataset, Methods, and Results","created":"2023-07-18","cited_by_count":8,"area":null},{"id":"2203.07662","title":"What's in the Black Box? The False Negative Mechanisms Inside Object Detectors","created":"2022-03-15","cited_by_count":7,"area":null},{"id":"2206.02424","title":"Slim-neck by GSConv: A lightweight-design for real-time detector architectures","created":"2022-06-06","cited_by_count":7,"area":null},{"id":"2607.06560","title":"Vision as Unified Multimodal Generation","created":"2026-07-07","cited_by_count":7,"area":null},{"id":"2208.02580","title":"SOMPT22: A Surveillance Oriented Multi-Pedestrian Tracking Dataset","created":"2022-08-04","cited_by_count":3,"area":null},{"id":"2407.18137","title":"XS-VID: A Large-Scale Benchmark for Small Object Detection and Tracking in Videos","created":"2024-07-25","cited_by_count":3,"area":null},{"id":"2206.08172","title":"RefCrowd: Grounding the Target in Crowd with Referring Expressions","created":"2022-06-16","cited_by_count":2,"area":null},{"id":"2404.16609","title":"SFMViT: SlowFast Meet ViT in Chaotic World","created":"2024-04-25","cited_by_count":2,"area":null},{"id":"2107.10050","title":"You Better Look Twice: a new perspective for designing accurate detectors with reduced computations","created":"2021-07-21","cited_by_count":1,"area":null},{"id":"2305.15697","title":"Privacy Protectability: An Information-theoretical Approach","created":"2023-05-25","cited_by_count":1,"area":null},{"id":"2505.21868","title":"Cross-DINO: Cross the Deep MLP and Transformer for Small Object Detection","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2507.19807","title":"DS-Det: Single-Query Paradigm and Attention Disentangled Learning for Flexible Object Detection","created":"2025-07-26","cited_by_count":1,"area":null},{"id":"2104.13763","title":"LGA-RCNN: Loss-Guided Attention for Object Detection","created":"2021-04-28","cited_by_count":0,"area":null},{"id":"2309.06313","title":"Semantic and Articulated Pedestrian Sensing Onboard a Moving Vehicle","created":"2023-09-12","cited_by_count":0,"area":null},{"id":"2309.11002","title":"PPD: A New Valet Parking Pedestrian Fisheye Dataset for Autonomous Driving","created":"2023-09-20","cited_by_count":0,"area":null},{"id":"2402.12968","title":"MapTrack: Tracking in the Map","created":"2024-02-20","cited_by_count":0,"area":null},{"id":"2407.13392","title":"Lightweight Uncertainty Quantification with Simplex Semantic Segmentation for Terrain Traversability","created":"2024-07-18","cited_by_count":0,"area":null},{"id":"2507.02513","title":"Automatic Labelling for Low-Light Pedestrian Detection","created":"2025-07-03","cited_by_count":0,"area":null},{"id":"2509.10503","title":"FEDEXCHANGE: Bridging the Domain Gap in Federated Object Detection for Free","created":"2025-09-01","cited_by_count":0,"area":null},{"id":"2601.16617","title":"Boundary and Position Information Mining for Aerial Small Object Detection","created":"2026-01-23","cited_by_count":0,"area":null},{"id":"2604.02032","title":"IndoorCrowd: A Multi-Scene Dataset for Human Detection, Segmentation, and Tracking with an Automated Annotation Pipeline","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2606.21568","title":"A Smart Classroom Behavior Analysis Framework with a New Highly Congested Classroom Dataset","created":"2026-06-19","cited_by_count":0,"area":null},{"id":"2609.04196","title":"Puffin-World: Scaling a Unified Multimodal Model with Native 3D World States","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.08265","title":"Tracking-by-detection in Multi-object Tracking: Survey and Experiments","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.14383","title":"Contour-Guided Spectral Routing for Robust Real-Time Pedestrian Detection","created":"2026-09-13","cited_by_count":0,"area":null}],"next_cursor":null}