{"list":"other","total":80,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175},{"id":"1612.03975","title":"ConceptNet 5.5: An Open Multilingual Graph of General Knowledge","created":"2016-12-12","cited_by_count":1067},{"id":"2401.14159","title":"Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks","created":"2024-01-25","cited_by_count":929},{"id":"1607.08822","title":"SPICE: Semantic Propositional Image Caption Evaluation","created":"2016-07-29","cited_by_count":824},{"id":"1804.02748","title":"Scaling Egocentric Vision: The EPIC-KITCHENS Dataset","created":"2018-04-08","cited_by_count":795},{"id":"2111.14819","title":"Point-BERT: Pre-training 3D Point Cloud Transformers with Masked Point Modeling","created":"2021-11-29","cited_by_count":653},{"id":"2309.05519","title":"NExT-GPT: Any-to-Any Multimodal LLM","created":"2023-09-11","cited_by_count":615},{"id":"1811.00982","title":"The Open Images Dataset V4: Unified image classification, object detection, and visual relationship detection at scale","created":"2018-11-02","cited_by_count":544},{"id":"1604.01753","title":"Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding","created":"2016-04-06","cited_by_count":537},{"id":"1701.02426","title":"Scene Graph Generation by Iterative Message Passing","created":"2017-01-10","cited_by_count":462},{"id":"1912.08830","title":"ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language","created":"2019-12-18","cited_by_count":452},{"id":"1711.06640","title":"Neural Motifs: Scene Graph Parsing with Global Context","created":"2017-11-17","cited_by_count":414},{"id":"2310.01852","title":"LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment","created":"2023-10-03","cited_by_count":370},{"id":"2309.16650","title":"ConceptGraphs: Open-Vocabulary 3D Scene Graphs for Perception and Planning","created":"2023-09-28","cited_by_count":365},{"id":"2112.10482","title":"ScanQA: 3D Question Answering for Spatial Scene Understanding","created":"2021-12-20","cited_by_count":346},{"id":"1608.00187","title":"Visual Relationship Detection with Language Priors","created":"2016-07-31","cited_by_count":334},{"id":"1812.01880","title":"Learning to Compose Dynamic Tree Structures for Visual Contexts","created":"2018-12-05","cited_by_count":259},{"id":"1912.06992","title":"Action Genome: Actions as Composition of Spatio-temporal Scene Graphs","created":"2019-12-15","cited_by_count":250},{"id":"1907.12412","title":"ERNIE 2.0: A Continual Pre-training Framework for Language Understanding","created":"2019-07-29","cited_by_count":231},{"id":"2004.03967","title":"Learning 3D Semantic Scene Graphs from 3D Indoor Reconstructions","created":"2020-04-08","cited_by_count":208},{"id":"2403.17846","title":"Hierarchical Open-Vocabulary 3D Scene Graphs for Language-Grounded Robot Navigation","created":"2024-03-26","cited_by_count":196},{"id":"2309.11436","title":"You Only Look at Screens: Multimodal Chain-of-Action Agents","created":"2023-09-20","cited_by_count":185},{"id":"2003.12962","title":"GPS-Net: Graph Property Sensing Network for Scene Graph Generation","created":"2020-03-29","cited_by_count":166},{"id":"2103.14898","title":"SceneGraphFusion: Incremental 3D Scene Graph Prediction from RGB-D Sequences","created":"2021-03-27","cited_by_count":163},{"id":"2501.03230","title":"Video-of-Thought: Step-by-Step Video Reasoning from Perception to Cognition","created":"2024-05-07","cited_by_count":153},{"id":"2104.00308","title":"Bipartite Graph Network with Adaptive Message Passing for Unbiased Scene Graph Generation","created":"2021-04-01","cited_by_count":137},{"id":"2207.11247","title":"Panoptic Scene Graph Generation","created":"2022-07-22","cited_by_count":114},{"id":"2112.12970","title":"SGTR: End-to-end Scene Graph Generation with Transformer","created":"2021-12-24","cited_by_count":103},{"id":"2107.12309","title":"Spatial-Temporal Transformer for Dynamic Scene Graph Generation","created":"2021-07-26","cited_by_count":96},{"id":"2201.11460","title":"RelTR: Relation Transformer for Scene Graph Generation","created":"2022-01-27","cited_by_count":96},{"id":"2401.10229","title":"OMG-Seg: Is One Model Good Enough For All Segmentation?","created":"2024-01-18","cited_by_count":75},{"id":"2009.07526","title":"CogTree: Cognition Tree Loss for Unbiased Scene Graph Generation","created":"2020-09-16","cited_by_count":62},{"id":"1707.09423","title":"Visual Relationship Detection with Internal and External Linguistic Knowledge Distillation","created":"2017-07-28","cited_by_count":61},{"id":"1706.07365","title":"Pixels to Graphs by Associative Embedding","created":"2017-06-22","cited_by_count":58},{"id":"2103.16083","title":"Fully Convolutional Scene Graph Generation","created":"2021-03-30","cited_by_count":57},{"id":"2108.08121","title":"Target Adaptive Context Aggregation for Video Scene Graph Generation","created":"2021-08-18","cited_by_count":52},{"id":"2312.03391","title":"Action Scene Graphs for Long-Form Understanding of Egocentric Videos","created":"2023-12-06","cited_by_count":51},{"id":"2305.17497","title":"FACTUAL: A Benchmark for Faithful and Consistent Textual Scene Graph Parsing","created":"2023-05-27","cited_by_count":50},{"id":"2103.05558","title":"Exploiting Edge-Oriented Reasoning for 3D Point-based Scene Graph Analysis","created":"2021-03-09","cited_by_count":49},{"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":"2303.14408","title":"VL-SAT: Visual-Linguistic Semantics Assisted Training for 3D Semantic Scene Graph Prediction in Point Cloud","created":"2023-03-25","cited_by_count":43},{"id":"2304.00733","title":"Unbiased Scene Graph Generation in Videos","created":"2023-04-03","cited_by_count":39},{"id":"2103.15662","title":"Unified Graph Structured Models for Video Understanding","created":"2021-03-29","cited_by_count":38},{"id":"2308.13812","title":"Dysen-VDM: Empowering Dynamics-aware Text-to-Video Diffusion with LLMs","created":"2023-08-26","cited_by_count":35},{"id":"2309.06635","title":"Collaborative Dynamic 3D Scene Graphs for Automated Driving","created":"2023-09-12","cited_by_count":34},{"id":"2406.19255","title":"Enhancing Video-Language Representations with Structural Spatio-Temporal Alignment","created":"2024-06-27","cited_by_count":32},{"id":"2112.09828","title":"Exploiting Long-Term Dependencies for Generating Dynamic Scene Graphs","created":"2021-12-18","cited_by_count":31},{"id":"2310.10404","title":"LLM4SGG: Large Language Models for Weakly Supervised Scene Graph Generation","created":"2023-10-16","cited_by_count":30},{"id":"2403.19098","title":"GraphAD: Interaction Scene Graph for End-to-end Autonomous Driving","created":"2024-03-28","cited_by_count":25},{"id":"2405.16925","title":"OED: Towards One-stage End-to-End Dynamic Scene Graph Generation","created":"2024-05-27","cited_by_count":23},{"id":"2405.10305","title":"4D Panoptic Scene Graph Generation","created":"2024-05-16","cited_by_count":22},{"id":"2405.15321","title":"SG-Adapter: Enhancing Text-to-Image Generation with Scene Graph Guidance","created":"2024-05-24","cited_by_count":20},{"id":"2008.07817","title":"Retargetable AR: Context-aware Augmented Reality in Indoor Scenes based on 3D Scene Graph","created":"2020-08-18","cited_by_count":19},{"id":"2303.15994","title":"HiLo: Exploiting High Low Frequency Relations for Unbiased Panoptic Scene Graph Generation","created":"2023-03-28","cited_by_count":19},{"id":"2308.09472","title":"Vision Relation Transformer for Unbiased Scene Graph Generation","created":"2023-08-18","cited_by_count":18},{"id":"2304.08600","title":"RS2G: Data-Driven Scene-Graph Extraction and Embedding for Robust Autonomous Perception and Scenario Understanding","created":"2023-04-17","cited_by_count":17},{"id":"2307.08699","title":"Pair then Relation: Pair-Net for Panoptic Scene Graph Generation","created":"2023-07-17","cited_by_count":17},{"id":"2305.11719","title":"Information Screening whilst Exploiting! Multimodal Relation Extraction with Feature Denoising and Multimodal Topic Modeling","created":"2023-05-19","cited_by_count":16},{"id":"2308.06712","title":"Compositional Feature Augmentation for Unbiased Scene Graph Generation","created":"2023-08-13","cited_by_count":15},{"id":"2403.12033","title":"HiKER-SGG: Hierarchical Knowledge Enhanced Robust Scene Graph Generation","created":"2024-03-18","cited_by_count":14},{"id":"2408.06926","title":"SceneGPT: A Language Model for 3D Scene Understanding","created":"2024-08-13","cited_by_count":12},{"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":"2406.11820","title":"Composing Object Relations and Attributes for Image-Text Matching","created":"2024-06-17","cited_by_count":11},{"id":"2102.04760","title":"Improving Scene Graph Classification by Exploiting Knowledge from Texts","created":"2021-02-09","cited_by_count":10},{"id":"2206.11653","title":"Learning To Generate Scene Graph from Head to Tail","created":"2022-06-23","cited_by_count":7},{"id":"2311.12889","title":"Enhancing Scene Graph Generation with Hierarchical Relationships and Commonsense Knowledge","created":"2023-11-21","cited_by_count":7},{"id":"2407.18715","title":"BCTR: Bidirectional Conditioning Transformer for Scene Graph Generation","created":"2024-07-26","cited_by_count":3},{"id":"2309.03240","title":"RepSGG: Novel Representations of Entities and Relationships for Scene Graph Generation","created":"2023-09-06","cited_by_count":2}],"next_cursor":null}