{"total":43,"rows":[{"id":"2311.11666","title":"OmniSeg3D: Omniversal 3D Segmentation via Hierarchical Contrastive Learning","created":"2023-11-20","cited_by_count":75,"area":null},{"id":"2412.20206","title":"Toward Visual Grounding: A Survey","created":"2024-12-28","cited_by_count":52,"area":null},{"id":"2109.11071","title":"Learning to Downsample for Segmentation of Ultra-High Resolution Images","created":"2021-09-22","cited_by_count":19,"area":null},{"id":"2308.15844","title":"Reconstructing Groups of People with Hypergraph Relational Reasoning","created":"2023-08-30","cited_by_count":18,"area":null},{"id":"2407.16424","title":"ESOD: Efficient Small Object Detection on High-Resolution Images","created":"2024-07-23","cited_by_count":15,"area":null},{"id":"2407.08133","title":"Nonverbal Interaction Detection","created":"2024-07-11","cited_by_count":14,"area":null},{"id":"2203.03806","title":"Panoramic Human Activity Recognition","created":"2022-03-08","cited_by_count":13,"area":null},{"id":"2404.04458","title":"JRDB-Social: A Multifaceted Robotic Dataset for Understanding of Context and Dynamics of Human Interactions Within Social Groups","created":"2024-04-06","cited_by_count":13,"area":null},{"id":"2301.09376","title":"Crowd3D: Towards Hundreds of People Reconstruction from a Single Image","created":"2023-01-23","cited_by_count":12,"area":null},{"id":"2207.13050","title":"Efficient High-Resolution Deep Learning: A Survey","created":"2022-07-26","cited_by_count":9,"area":null},{"id":"2507.05675","title":"MedGen: Unlocking Medical Video Generation by Scaling Granularly-annotated Medical Videos","created":"2025-07-08","cited_by_count":9,"area":null},{"id":"2302.10463","title":"Vision-based Multi-future Trajectory Prediction: A Survey","created":"2023-02-21","cited_by_count":8,"area":null},{"id":"2203.03843","title":"Self-supervised Social Relation Representation for Human Group Detection","created":"2022-03-08","cited_by_count":7,"area":null},{"id":"2502.07216","title":"SparseFormer: Detecting Objects in HRW Shots via Sparse Vision Transformer","created":"2025-02-11","cited_by_count":7,"area":null},{"id":"2403.19517","title":"XScale-NVS: Cross-Scale Novel View Synthesis with Hash Featurized Manifold","created":"2024-03-28","cited_by_count":6,"area":null},{"id":"2407.17956","title":"SaccadeDet: A Novel Dual-Stage Architecture for Rapid and Accurate Detection in Gigapixel Images","created":"2024-07-25","cited_by_count":5,"area":null},{"id":"2507.12841","title":"AnyCap Project: A Unified Framework, Dataset, and Benchmark for Controllable Omni-modal Captioning","created":"2025-07-17","cited_by_count":5,"area":null},{"id":"2510.18357","title":"Learning Human-Object Interaction as Groups","created":"2025-10-21","cited_by_count":5,"area":null},{"id":"2105.11578","title":"SHD360: A Benchmark Dataset for Salient Human Detection in 360{\\deg} Videos","created":"2021-05-24","cited_by_count":4,"area":null},{"id":"2509.04758","title":"Dynamic Group Detection using VLM-augmented Temporal Groupness Graph","created":"2025-09-05","cited_by_count":4,"area":null},{"id":"2110.01774","title":"HighlightMe: Detecting Highlights from Human-Centric Videos","created":"2021-10-05","cited_by_count":3,"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":"2308.13057","title":"Data-Side Efficiencies for Lightweight Convolutional Neural Networks","created":"2023-08-24","cited_by_count":3,"area":null},{"id":"2504.18406","title":"HRScene: How Far Are VLMs from Effective High-Resolution Image Understanding?","created":"2025-04-25","cited_by_count":3,"area":null},{"id":"2508.12644","title":"DyCrowd: Towards Dynamic Crowd Reconstruction from a Large-scene Video","created":"2025-08-18","cited_by_count":3,"area":null},{"id":"2202.00753","title":"ADG-Pose: Automated Dataset Generation for Real-World Human Pose Estimation","created":"2022-02-01","cited_by_count":2,"area":null},{"id":"2310.06332","title":"CrowdRec: 3D Crowd Reconstruction from Single Color Images","created":"2023-10-10","cited_by_count":2,"area":null},{"id":"2411.06232","title":"RCR: Robust Crowd Reconstruction with Upright Space from a Single Large-scene Image","created":"2024-11-09","cited_by_count":2,"area":null},{"id":"2204.04416","title":"E^2TAD: An Energy-Efficient Tracking-based Action Detector","created":"2022-04-09","cited_by_count":1,"area":null},{"id":"2209.01211","title":"Cross-Camera Deep Colorization","created":"2022-08-26","cited_by_count":1,"area":null},{"id":"2211.12424","title":"One Venue, Two Conferences: The Separation of Chinese and American Citation Networks","created":"2022-11-17","cited_by_count":1,"area":null},{"id":"2403.14113","title":"Spatio-Temporal Proximity-Aware Dual-Path Model for Panoramic Activity Recognition","created":"2024-03-21","cited_by_count":1,"area":null},{"id":"2208.12940","title":"Actor-identified Spatiotemporal Action Detection -- Detecting Who Is Doing What in Videos","created":"2022-08-27","cited_by_count":0,"area":null},{"id":"2305.09271","title":"Accurate Gigapixel Crowd Counting by Iterative Zooming and Refinement","created":"2023-05-16","cited_by_count":0,"area":null},{"id":"2407.18637","title":"DynamicTrack: Advancing Gigapixel Tracking in Crowded Scenes","created":"2024-07-26","cited_by_count":0,"area":null},{"id":"2408.00420","title":"MPT-PAR:Mix-Parameters Transformer for Panoramic Activity Recognition","created":"2024-08-01","cited_by_count":0,"area":null},{"id":"2501.06089","title":"Towards Developing Socially Compliant Automated Vehicles: Advances, Expert Insights, and A Conceptual Framework","created":"2025-01-10","cited_by_count":0,"area":null},{"id":"2603.22249","title":"EgoGroups: A Benchmark For Detecting Social Groups of People in the Wild","created":"2026-03-23","cited_by_count":0,"area":null},{"id":"2604.10619","title":"How to Design a Compact High-Throughput Video Camera?","created":"2026-04-12","cited_by_count":0,"area":null},{"id":"2604.21435","title":"UHR-DETR: Efficient End-to-End Small Object Detection for Ultra-High-Resolution Remote Sensing Imagery","created":"2026-04-23","cited_by_count":0,"area":null},{"id":"2606.02242","title":"Towards Resolving Optimization Conflicts Between Image- and Text-Based Person Re-Identification","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2607.19517","title":"Crowd4D: Scene-Aware Monocular 4D Crowd Reconstruction","created":"2026-07-21","cited_by_count":0,"area":null},{"id":"2609.18210","title":"Understanding Dynamic Scenes at Gigapixel Scale: Wide-Area Spatio-Temporal Perception from UAVs","created":"2026-09-16","cited_by_count":0,"area":null}],"next_cursor":null}