{"list":"other","total":69,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"1609.02907","title":"Semi-Supervised Classification with Graph Convolutional Networks","created":"2016-09-09","cited_by_count":11361},{"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":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"id":"2004.11362","title":"Supervised Contrastive Learning","created":"2020-04-23","cited_by_count":2829},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"2303.12712","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","created":"2023-03-22","cited_by_count":2592},{"id":"2311.05232","title":"A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions","created":"2023-11-09","cited_by_count":1601},{"id":"1907.01341","title":"Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer","created":"2019-07-02","cited_by_count":1495},{"id":"1409.1259","title":"On the Properties of Neural Machine Translation: Encoder-Decoder Approaches","created":"2014-09-03","cited_by_count":1304},{"id":"2305.10403","title":"PaLM 2 Technical Report","created":"2023-05-17","cited_by_count":1162},{"id":"2311.03079","title":"CogVLM: Visual Expert for Pretrained Language Models","created":"2023-11-06","cited_by_count":708},{"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":"1701.02426","title":"Scene Graph Generation by Iterative Message Passing","created":"2017-01-10","cited_by_count":462},{"id":"1711.06640","title":"Neural Motifs: Scene Graph Parsing with Global Context","created":"2017-11-17","cited_by_count":414},{"id":"2002.11949","title":"Unbiased Scene Graph Generation from Biased Training","created":"2020-02-27","cited_by_count":356},{"id":"2304.09842","title":"Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models","created":"2023-04-19","cited_by_count":356},{"id":"1608.00187","title":"Visual Relationship Detection with Language Priors","created":"2016-07-31","cited_by_count":334},{"id":"1808.00191","title":"Graph R-CNN for Scene Graph Generation","created":"2018-08-01","cited_by_count":298},{"id":"1812.01880","title":"Learning to Compose Dynamic Tree Structures for Visual Contexts","created":"2018-12-05","cited_by_count":259},{"id":"2305.14078","title":"Large Language Models as Commonsense Knowledge for Large-Scale Task Planning","created":"2023-05-23","cited_by_count":231},{"id":"2003.12962","title":"GPS-Net: Graph Property Sensing Network for Scene Graph Generation","created":"2020-03-29","cited_by_count":166},{"id":"1903.03326","title":"Knowledge-Embedded Routing Network for Scene Graph Generation","created":"2019-03-08","cited_by_count":164},{"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":"2104.01111","title":"A Comprehensive Survey of Scene Graphs: Generation and Application","created":"2021-03-17","cited_by_count":125},{"id":"1702.08319","title":"Visual Translation Embedding Network for Visual Relation Detection","created":"2017-02-27","cited_by_count":112},{"id":"2103.02221","title":"Energy-Based Learning for Scene Graph Generation","created":"2021-03-03","cited_by_count":104},{"id":"2112.12970","title":"SGTR: End-to-end Scene Graph Generation with Transformer","created":"2021-12-24","cited_by_count":103},{"id":"1903.02728","title":"Graphical Contrastive Losses for Scene Graph Parsing","created":"2019-03-07","cited_by_count":100},{"id":"2201.11460","title":"RelTR: Relation Transformer for Scene Graph Generation","created":"2022-01-27","cited_by_count":96},{"id":"2201.00443","title":"Scene Graph Generation: A Comprehensive Survey","created":"2022-01-03","cited_by_count":73},{"id":"2109.02227","title":"Learning to Generate Scene Graph from Natural Language Supervision","created":"2021-09-06","cited_by_count":64},{"id":"2009.07526","title":"CogTree: Cognition Tree Loss for Unbiased Scene Graph Generation","created":"2020-09-16","cited_by_count":62},{"id":"2206.03014","title":"The Devil is in the Labels: Noisy Label Correction for Robust Scene Graph Generation","created":"2022-06-07","cited_by_count":60},{"id":"1706.07365","title":"Pixels to Graphs by Associative Embedding","created":"2017-06-22","cited_by_count":58},{"id":"2203.11654","title":"Fine-Grained Scene Graph Generation with Data Transfer","created":"2022-03-22","cited_by_count":57},{"id":"2208.08165","title":"Towards Open-vocabulary Scene Graph Generation with Prompt-based Finetuning","created":"2022-08-17","cited_by_count":54},{"id":"2106.10815","title":"Structured Sparse R-CNN for Direct Scene Graph Generation","created":"2021-06-21","cited_by_count":44},{"id":"1810.12813","title":"Contextual Hourglass Network for Semantic Segmentation of High Resolution Aerial Imagery","created":"2018-10-30","cited_by_count":43},{"id":"2303.13233","title":"Visually-Prompted Language Model for Fine-Grained Scene Graph Generation in an Open World","created":"2023-03-23","cited_by_count":35},{"id":"2310.10404","title":"LLM4SGG: Large Language Models for Weakly Supervised Scene Graph Generation","created":"2023-10-16","cited_by_count":30},{"id":"2105.13994","title":"Linguistic Structures as Weak Supervision for Visual Scene Graph Generation","created":"2021-05-28","cited_by_count":29},{"id":"2001.02359","title":"Weakly Supervised Visual Semantic Parsing","created":"2020-01-08","cited_by_count":28},{"id":"2305.12476","title":"Zero-shot Visual Relation Detection via Composite Visual Cues from Large Language Models","created":"2023-05-21","cited_by_count":27},{"id":"2103.15365","title":"Visual Distant Supervision for Scene Graph Generation","created":"2021-03-29","cited_by_count":25},{"id":"2202.10432","title":"Reasoning with Scene Graphs for Robot Planning under Partial Observability","created":"2022-02-21","cited_by_count":25},{"id":"2207.13440","title":"Iterative Scene Graph Generation","created":"2022-07-27","cited_by_count":24},{"id":"2111.13517","title":"Not All Relations are Equal: Mining Informative Labels for Scene Graph Generation","created":"2021-11-26","cited_by_count":21},{"id":"2004.06193","title":"Relation Transformer Network","created":"2020-04-13","cited_by_count":20},{"id":"2208.01834","title":"Integrating Object-aware and Interaction-aware Knowledge for Weakly Supervised Scene Graph Generation","created":"2022-08-03","cited_by_count":20},{"id":"2109.05346","title":"BGT-Net: Bidirectional GRU Transformer Network for Scene Graph Generation","created":"2021-09-11","cited_by_count":18},{"id":"2203.06907","title":"Hierarchical Memory Learning for Fine-Grained Scene Graph Generation","created":"2022-03-14","cited_by_count":15},{"id":"2202.10201","title":"OG-SGG: Ontology-Guided Scene Graph Generation. A Case Study in Transfer Learning for Telepresence Robotics","created":"2022-02-21","cited_by_count":9},{"id":"2309.02286","title":"Haystack: A Panoptic Scene Graph Dataset to Evaluate Rare Predicate Classes","created":"2023-09-05","cited_by_count":8},{"id":"2305.18668","title":"Fine-Grained is Too Coarse: A Novel Data-Centric Approach for Efficient Scene Graph Generation","created":"2023-05-30","cited_by_count":4},{"id":"2303.06842","title":"Hierarchical Relationships: A New Perspective to Enhance Scene Graph Generation","created":"2023-03-13","cited_by_count":3},{"id":"2310.07573","title":"Relational Prior Knowledge Graphs for Detection and Instance Segmentation","created":"2023-10-11","cited_by_count":1}],"next_cursor":null}