{"list":"other","total":65,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"1505.04870","title":"Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models","created":"2015-05-19","cited_by_count":1362},{"id":"1906.00067","title":"OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge","created":"2019-05-31","cited_by_count":1121},{"id":"1608.00272","title":"Modeling Context in Referring Expressions","created":"2016-07-31","cited_by_count":1063},{"id":"1511.02283","title":"Generation and Comprehension of Unambiguous Object Descriptions","created":"2015-11-07","cited_by_count":904},{"id":"2104.12763","title":"MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding","created":"2021-04-26","cited_by_count":819},{"id":"2112.04482","title":"FLAVA: A Foundational Language And Vision Alignment Model","created":"2021-12-08","cited_by_count":649},{"id":"2210.01936","title":"When and why vision-language models behave like bags-of-words, and what to do about it?","created":"2022-10-04","cited_by_count":610},{"id":"2211.11559","title":"Visual Programming: Compositional visual reasoning without training","created":"2022-11-18","cited_by_count":516},{"id":"1701.02426","title":"Scene Graph Generation by Iterative Message Passing","created":"2017-01-10","cited_by_count":462},{"id":"1801.08186","title":"MAttNet: Modular Attention Network for Referring Expression Comprehension","created":"2018-01-24","cited_by_count":431},{"id":"1711.06640","title":"Neural Motifs: Scene Graph Parsing with Global Context","created":"2017-11-17","cited_by_count":414},{"id":"2303.03846","title":"Larger language models do in-context learning differently","created":"2023-03-07","cited_by_count":394},{"id":"1906.10770","title":"Deep Modular Co-Attention Networks for Visual Question Answering","created":"2019-06-25","cited_by_count":339},{"id":"2206.05836","title":"GLIPv2: Unifying Localization and Vision-Language Understanding","created":"2022-06-12","cited_by_count":275},{"id":"1812.01880","title":"Learning to Compose Dynamic Tree Structures for Visual Contexts","created":"2018-12-05","cited_by_count":259},{"id":"1810.10147","title":"FewRel: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluation","created":"2018-10-24","cited_by_count":254},{"id":"1810.04020","title":"A Comprehensive Survey of Deep Learning for Image Captioning","created":"2018-10-06","cited_by_count":214},{"id":"1910.11476","title":"A Unified MRC Framework for Named Entity Recognition","created":"2019-10-25","cited_by_count":199},{"id":"2101.05779","title":"Structured Prediction as Translation between Augmented Natural Languages","created":"2021-01-14","cited_by_count":183},{"id":"2104.13682","title":"HOTR: End-to-End Human-Object Interaction Detection with Transformers","created":"2021-04-28","cited_by_count":183},{"id":"2109.11797","title":"CPT: Colorful Prompt Tuning for Pre-trained Vision-Language Models","created":"2021-09-24","cited_by_count":183},{"id":"1707.09700","title":"Scene Graph Generation from Objects, Phrases and Region Captions","created":"2017-07-31","cited_by_count":154},{"id":"1904.05255","title":"Simple BERT Models for Relation Extraction and Semantic Role Labeling","created":"2019-04-10","cited_by_count":154},{"id":"1804.05392","title":"Higher-order Coreference Resolution with Coarse-to-fine Inference","created":"2018-04-15","cited_by_count":150},{"id":"2107.06912","title":"From Show to Tell: A Survey on Deep Learning-based Image Captioning","created":"2021-07-14","cited_by_count":138},{"id":"2203.13954","title":"GEN-VLKT: Simplify Association and Enhance Interaction Understanding for HOI Detection","created":"2022-03-26","cited_by_count":120},{"id":"2204.05991","title":"ReCLIP: A Strong Zero-Shot Baseline for Referring Expression Comprehension","created":"2022-04-12","cited_by_count":120},{"id":"2302.13996","title":"Aligning Bag of Regions for Open-Vocabulary Object Detection","created":"2023-02-27","cited_by_count":119},{"id":"2008.11714","title":"DRG: Dual Relation Graph for Human-Object Interaction Detection","created":"2020-08-26","cited_by_count":117},{"id":"2203.12667","title":"Vision-and-Language Navigation: A Survey of Tasks, Methods, and Future Directions","created":"2022-03-22","cited_by_count":117},{"id":"2207.11247","title":"Panoptic Scene Graph Generation","created":"2022-07-22","cited_by_count":114},{"id":"2108.05077","title":"Mining the Benefits of Two-stage and One-stage HOI Detection","created":"2021-08-11","cited_by_count":103},{"id":"2006.09920","title":"Contrastive Learning for Weakly Supervised Phrase Grounding","created":"2020-06-17","cited_by_count":102},{"id":"2012.06060","title":"Spatially Conditioned Graphs for Detecting Human-Object Interactions","created":"2020-12-11","cited_by_count":93},{"id":"1911.01746","title":"Coreference Resolution as Query-based Span Prediction","created":"2019-11-05","cited_by_count":91},{"id":"2112.01838","title":"Efficient Two-Stage Detection of Human-Object Interactions with a Novel Unary-Pairwise Transformer","created":"2021-12-03","cited_by_count":91},{"id":"2003.12058","title":"Grounded Situation Recognition","created":"2020-03-26","cited_by_count":78},{"id":"2305.19595","title":"Dense and Aligned Captions (DAC) Promote Compositional Reasoning in VL Models","created":"2023-05-31","cited_by_count":72},{"id":"2211.11733","title":"Teaching Structured Vision&Language Concepts to Vision&Language Models","created":"2022-11-21","cited_by_count":71},{"id":"2109.02227","title":"Learning to Generate Scene Graph from Natural Language Supervision","created":"2021-09-06","cited_by_count":64},{"id":"2303.17811","title":"Zero-shot Referring Image Segmentation with Global-Local Context Features","created":"2023-03-31","cited_by_count":61},{"id":"1511.06350","title":"Structured Prediction Energy Networks","created":"2015-11-19","cited_by_count":59},{"id":"2206.06291","title":"Exploring Structure-aware Transformer over Interaction Proposals for Human-Object Interaction Detection","created":"2022-06-13","cited_by_count":47},{"id":"2008.06254","title":"ConsNet: Learning Consistency Graph for Zero-Shot Human-Object Interaction Detection","created":"2020-08-14","cited_by_count":46},{"id":"2305.06343","title":"Incorporating Structured Representations into Pretrained Vision & Language Models Using Scene Graphs","created":"2023-05-10","cited_by_count":39},{"id":"2304.04997","title":"Relational Context Learning for Human-Object Interaction Detection","created":"2023-04-11","cited_by_count":36},{"id":"1909.02250","title":"Nested Named Entity Recognition via Second-best Sequence Learning and Decoding","created":"2019-09-05","cited_by_count":34},{"id":"2301.04019","title":"FGAHOI: Fine-Grained Anchors for Human-Object Interaction Detection","created":"2023-01-08","cited_by_count":30},{"id":"1803.10362","title":"Referring Relationships","created":"2018-03-28","cited_by_count":29},{"id":"2211.13854","title":"ComCLIP: Training-Free Compositional Image and Text Matching","created":"2022-11-25","cited_by_count":26},{"id":"2308.04030","title":"Gentopia: A Collaborative Platform for Tool-Augmented LLMs","created":"2023-08-08","cited_by_count":26},{"id":"1708.01956","title":"PPR-FCN: Weakly Supervised Visual Relation Detection via Parallel Pairwise R-FCN","created":"2017-08-07","cited_by_count":25},{"id":"2204.03647","title":"Adapting CLIP For Phrase Localization Without Further Training","created":"2022-04-07","cited_by_count":21},{"id":"2309.01141","title":"VGDiffZero: Text-to-image Diffusion Models Can Be Zero-shot Visual Grounders","created":"2023-09-03","cited_by_count":18},{"id":"2108.07253","title":"Who's Waldo? Linking People Across Text and Images","created":"2021-08-16","cited_by_count":16},{"id":"2304.13700","title":"UniNeXt: Exploring A Unified Architecture for Vision Recognition","created":"2023-04-26","cited_by_count":16},{"id":"2308.08529","title":"Diagnosing Human-object Interaction Detectors","created":"2023-08-16","cited_by_count":11},{"id":"2102.01156","title":"Improving Distantly-Supervised Relation Extraction through BERT-based Label & Instance Embeddings","created":"2021-02-01","cited_by_count":10},{"id":"2004.13833","title":"Data Annealing for Informal Language Understanding Tasks","created":"2020-04-24","cited_by_count":4}],"next_cursor":null}