{"list":"other","total":58,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"2203.03605","title":"DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection","created":"2022-03-07","cited_by_count":1319},{"id":"2211.15654","title":"OpenScene: 3D Scene Understanding with Open Vocabularies","created":"2022-11-28","cited_by_count":559},{"id":"2006.13256","title":"Rescaling Egocentric Vision","created":"2020-06-23","cited_by_count":540},{"id":"1701.02426","title":"Scene Graph Generation by Iterative Message Passing","created":"2017-01-10","cited_by_count":462},{"id":"1608.00187","title":"Visual Relationship Detection with Language Priors","created":"2016-07-31","cited_by_count":334},{"id":"2307.03601","title":"GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interest","created":"2023-07-07","cited_by_count":302},{"id":"2001.06303","title":"Detection and Tracking Meet Drones Challenge","created":"2020-01-16","cited_by_count":263},{"id":"2302.14115","title":"Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning","created":"2023-02-27","cited_by_count":263},{"id":"1912.06992","title":"Action Genome: Actions as Composition of Spatio-temporal Scene Graphs","created":"2019-12-15","cited_by_count":250},{"id":"1804.00518","title":"The Unmanned Aerial Vehicle Benchmark: Object Detection and Tracking","created":"2018-03-26","cited_by_count":208},{"id":"2207.14096","title":"Towards Large-Scale Small Object Detection: Survey and Benchmarks","created":"2022-07-28","cited_by_count":122},{"id":"2001.06891","title":"Where Does It Exist: Spatio-Temporal Video Grounding for Multi-Form Sentences","created":"2020-01-19","cited_by_count":118},{"id":"2207.11247","title":"Panoptic Scene Graph Generation","created":"2022-07-22","cited_by_count":114},{"id":"2110.01931","title":"Anchor-free Oriented Proposal Generator for Object Detection","created":"2021-10-05","cited_by_count":105},{"id":"2112.12970","title":"SGTR: End-to-end Scene Graph Generation with Transformer","created":"2021-12-24","cited_by_count":103},{"id":"2312.00093","title":"GraphDreamer: Compositional 3D Scene Synthesis from Scene Graphs","created":"2023-11-30","cited_by_count":97},{"id":"2107.12309","title":"Spatial-Temporal Transformer for Dynamic Scene Graph Generation","created":"2021-07-26","cited_by_count":96},{"id":"2106.12011","title":"P2T: Pyramid Pooling Transformer for Scene Understanding","created":"2021-06-22","cited_by_count":84},{"id":"2001.11737","title":"AU-AIR: A Multi-modal Unmanned Aerial Vehicle Dataset for Low Altitude Traffic Surveillance","created":"2020-01-31","cited_by_count":56},{"id":"2206.13996","title":"Detecting tiny objects in aerial images: A normalized Wasserstein distance and a new benchmark","created":"2022-06-28","cited_by_count":56},{"id":"2108.08121","title":"Target Adaptive Context Aggregation for Video Scene Graph Generation","created":"2021-08-18","cited_by_count":52},{"id":"2404.02072","title":"EGTR: Extracting Graph from Transformer for Scene Graph Generation","created":"2024-04-02","cited_by_count":47},{"id":"2311.17058","title":"Panoptic Video Scene Graph Generation","created":"2023-11-28","cited_by_count":46},{"id":"2304.08876","title":"Dynamic Coarse-to-Fine Learning for Oriented Tiny Object Detection","created":"2023-04-18","cited_by_count":43},{"id":"1903.10547","title":"Video Relationship Reasoning using Gated Spatio-Temporal Energy Graph","created":"2019-03-25","cited_by_count":41},{"id":"2304.08114","title":"ViPLO: Vision Transformer based Pose-Conditioned Self-Loop Graph for Human-Object Interaction Detection","created":"2023-04-17","cited_by_count":41},{"id":"2204.07718","title":"Interactiveness Field in Human-Object Interactions","created":"2022-04-16","cited_by_count":40},{"id":"2304.00733","title":"Unbiased Scene Graph Generation in Videos","created":"2023-04-03","cited_by_count":39},{"id":"2308.07893","title":"Memory-and-Anticipation Transformer for Online Action Understanding","created":"2023-08-15","cited_by_count":39},{"id":"1812.00155","title":"Learning RoI Transformer for Detecting Oriented Objects in Aerial Images","created":"2018-12-01","cited_by_count":37},{"id":"2111.12476","title":"Hierarchical Modular Network for Video Captioning","created":"2021-11-24","cited_by_count":32},{"id":"2106.06856","title":"DyGLIP: A Dynamic Graph Model with Link Prediction for Accurate Multi-Camera Multiple Object Tracking","created":"2021-06-12","cited_by_count":31},{"id":"2203.10233","title":"DirecFormer: A Directed Attention in Transformer Approach to Robust Action Recognition","created":"2022-03-19","cited_by_count":31},{"id":"2308.09534","title":"Small Object Detection via Coarse-to-fine Proposal Generation and Imitation Learning","created":"2023-08-18","cited_by_count":27},{"id":"2207.13440","title":"Iterative Scene Graph Generation","created":"2022-07-27","cited_by_count":24},{"id":"2305.13495","title":"Type-to-Track: Retrieve Any Object via Prompt-based Tracking","created":"2023-05-22","cited_by_count":24},{"id":"2211.16636","title":"Iterative Scene Graph Generation with Generative Transformers","created":"2022-11-30","cited_by_count":22},{"id":"2312.03050","title":"HIG: Hierarchical Interlacement Graph Approach to Scene Graph Generation in Video Understanding","created":"2023-12-05","cited_by_count":22},{"id":"2405.10305","title":"4D Panoptic Scene Graph Generation","created":"2024-05-16","cited_by_count":22},{"id":"2001.11394","title":"ERA: A Dataset and Deep Learning Benchmark for Event Recognition in Aerial Videos","created":"2020-01-30","cited_by_count":18},{"id":"2312.04548","title":"Multiview Aerial Visual Recognition (MAVREC): Can Multi-view Improve Aerial Visual Perception?","created":"2023-12-07","cited_by_count":18},{"id":"2008.01699","title":"MOR-UAV: A Benchmark Dataset and Baselines for Moving Object Recognition in UAV Videos","created":"2020-08-04","cited_by_count":15},{"id":"2404.04565","title":"SportsHHI: A Dataset for Human-Human Interaction Detection in Sports Videos","created":"2024-04-06","cited_by_count":15},{"id":"1811.11849","title":"Non-Volume Preserving-based Fusion to Group-Level Emotion Recognition on Crowd Videos","created":"2018-11-28","cited_by_count":13},{"id":"2403.14886","title":"DSGG: Dense Relation Transformer for an End-to-end Scene Graph Generation","created":"2024-03-21","cited_by_count":11},{"id":"2211.09663","title":"Multi-Camera Multi-Object Tracking on the Move via Single-Stage Global Association Approach","created":"2022-11-17","cited_by_count":7},{"id":"2304.05417","title":"The MONET dataset: Multimodal drone thermal dataset recorded in rural scenarios","created":"2023-04-11","cited_by_count":5},{"id":"2312.00188","title":"REACT: Recognize Every Action Everywhere All At Once","created":"2023-11-27","cited_by_count":5},{"id":"2208.14209","title":"A Circular Window-based Cascade Transformer for Online Action Detection","created":"2022-08-30","cited_by_count":4},{"id":"2312.07740","title":"HAtt-Flow: Hierarchical Attention-Flow Mechanism for Group Activity Scene Graph Generation in Videos","created":"2023-11-28","cited_by_count":4},{"id":"2310.01842","title":"SelfGraphVQA: A Self-Supervised Graph Neural Network for Scene-based Question Answering","created":"2023-10-03","cited_by_count":2}],"next_cursor":null}