{"list":"other","total":78,"rows":[{"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"2104.08718","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","created":"2021-04-18","cited_by_count":2424},{"id":"2107.07651","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","created":"2021-07-16","cited_by_count":1619},{"id":"2111.02114","title":"LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs","created":"2021-11-03","cited_by_count":1555},{"id":"1612.06890","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","created":"2016-12-20","cited_by_count":1457},{"id":"2205.01917","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","created":"2022-05-04","cited_by_count":1274},{"id":"2102.08981","title":"Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts","created":"2021-02-17","cited_by_count":1216},{"id":"1905.05950","title":"BERT Rediscovers the Classical NLP Pipeline","created":"2019-05-15","cited_by_count":1059},{"id":"2103.17249","title":"StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery","created":"2021-03-31","cited_by_count":991},{"id":"2102.12452","title":"Probing Classifiers: Promises, Shortcomings, and Advances","created":"2021-02-24","cited_by_count":876},{"id":"2002.12327","title":"A Primer in BERTology: What we know about how BERT works","created":"2020-02-27","cited_by_count":815},{"id":"2201.03546","title":"Language-driven Semantic Segmentation","created":"2022-01-10","cited_by_count":717},{"id":"2112.04482","title":"FLAVA: A Foundational Language And Vision Alignment Model","created":"2021-12-08","cited_by_count":649},{"id":"1909.03368","title":"Designing and Interpreting Probes with Control Tasks","created":"2019-09-08","cited_by_count":640},{"id":"2109.12098","title":"CLIPort: What and Where Pathways for Robotic Manipulation","created":"2021-09-24","cited_by_count":622},{"id":"2109.14084","title":"VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding","created":"2021-09-28","cited_by_count":602},{"id":"2112.01518","title":"DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting","created":"2021-12-02","cited_by_count":532},{"id":"2204.03162","title":"Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality","created":"2022-04-07","cited_by_count":529},{"id":"2104.00677","title":"Putting NeRF on a Diet: Semantically Consistent Few-Shot View Synthesis","created":"2021-04-01","cited_by_count":464},{"id":"1811.00491","title":"A Corpus for Reasoning About Natural Language Grounded in Photographs","created":"2018-11-01","cited_by_count":459},{"id":"1511.02799","title":"Neural Module Networks","created":"2015-11-09","cited_by_count":376},{"id":"2109.01247","title":"Do Prompt-Based Models Really Understand the Meaning of their Prompts?","created":"2021-09-02","cited_by_count":326},{"id":"2107.06383","title":"How Much Can CLIP Benefit Vision-and-Language Tasks?","created":"2021-07-13","cited_by_count":321},{"id":"2109.08472","title":"ActionCLIP: A New Paradigm for Video Action Recognition","created":"2021-09-17","cited_by_count":320},{"id":"1912.09713","title":"Measuring Compositional Generalization: A Comprehensive Method on Realistic Data","created":"2019-12-20","cited_by_count":284},{"id":"1908.08351","title":"Compositionality decomposed: how do neural networks generalise?","created":"2019-08-22","cited_by_count":265},{"id":"1912.06992","title":"Action Genome: Actions as Composition of Spatio-temporal Scene Graphs","created":"2019-12-15","cited_by_count":250},{"id":"1503.01817","title":"YFCC100M: The New Data in Multimedia Research","created":"2015-03-05","cited_by_count":235},{"id":"2112.05744","title":"More Control for Free! Image Synthesis with Semantic Diffusion Guidance","created":"2021-12-10","cited_by_count":212},{"id":"2202.10401","title":"Vision-Language Pre-Training with Triple Contrastive Learning","created":"2022-02-21","cited_by_count":212},{"id":"1803.03067","title":"Compositional Attention Networks for Machine Reasoning","created":"2018-03-08","cited_by_count":183},{"id":"2109.02748","title":"Zero-Shot Out-of-Distribution Detection Based on the Pre-trained Model CLIP","created":"2021-09-06","cited_by_count":152},{"id":"2111.14447","title":"ZeroCap: Zero-Shot Image-to-Text Generation for Visual-Semantic Arithmetic","created":"2021-11-29","cited_by_count":150},{"id":"2112.09583","title":"Align and Prompt: Video-and-Language Pre-training with Entity Prompts","created":"2021-12-17","cited_by_count":149},{"id":"2112.07566","title":"VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena","created":"2021-12-14","cited_by_count":135},{"id":"2111.13792","title":"LAFITE: Towards Language-Free Training for Text-to-Image Generation","created":"2021-11-27","cited_by_count":128},{"id":"2205.14459","title":"CyCLIP: Cyclic Contrastive Language-Image Pretraining","created":"2022-05-28","cited_by_count":127},{"id":"2103.16002","title":"AGQA: A Benchmark for Compositional Spatio-Temporal Reasoning","created":"2021-03-30","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":"2106.09141","title":"Probing Image-Language Transformers for Verb Understanding","created":"2021-06-16","cited_by_count":109},{"id":"2003.05161","title":"A Benchmark for Systematic Generalization in Grounded Language Understanding","created":"2020-03-11","cited_by_count":108},{"id":"2107.00650","title":"CLIP-It! Language-Guided Video Summarization","created":"2021-07-01","cited_by_count":99},{"id":"1705.01359","title":"FOIL it! Find One mismatch between Image and Language caption","created":"2017-05-03","cited_by_count":95},{"id":"2012.15180","title":"Out of Order: How Important Is The Sequential Order of Words in a Sentence in Natural Language Understanding Tasks?","created":"2020-12-30","cited_by_count":73},{"id":"2109.04448","title":"Vision-and-Language or Vision-for-Language? On Cross-Modal Influence in Multimodal Transformers","created":"2021-09-09","cited_by_count":72},{"id":"2204.11134","title":"Can Foundation Models Perform Zero-Shot Task Specification For Robot Manipulation?","created":"2022-04-23","cited_by_count":70},{"id":"2104.03514","title":"Low-Complexity Probing via Finding Subnetworks","created":"2021-04-08","cited_by_count":64},{"id":"1912.05783","title":"CLOSURE: Assessing Systematic Generalization of CLEVR Models","created":"2019-12-12","cited_by_count":63},{"id":"2203.00048","title":"Multi-modal Alignment using Representation Codebook","created":"2022-02-28","cited_by_count":63},{"id":"2208.00005","title":"Testing Relational Understanding in Text-Guided Image Generation","created":"2022-07-29","cited_by_count":59},{"id":"2206.07835","title":"Disentangling visual and written concepts in CLIP","created":"2022-06-15","cited_by_count":58},{"id":"2003.00403","title":"Cops-Ref: A new Dataset and Task on Compositional Referring Expression Comprehension","created":"2020-03-01","cited_by_count":50},{"id":"2201.06696","title":"ProposalCLIP: Unsupervised Open-Category Object Proposal Generation via Exploiting CLIP Cues","created":"2022-01-18","cited_by_count":42},{"id":"2111.13333","title":"Predict, Prevent, and Evaluate: Disentangled Text-Driven Image Manipulation Empowered by Pre-Trained Vision-Language Model","created":"2021-11-26","cited_by_count":34},{"id":"2005.01655","title":"Words aren't enough, their order matters: On the Robustness of Grounding Visual Referring Expressions","created":"2020-05-04","cited_by_count":33},{"id":"2203.15799","title":"StyleT2I: Toward Compositional and High-Fidelity Text-to-Image Synthesis","created":"2022-03-29","cited_by_count":33},{"id":"2204.07441","title":"COTS: Collaborative Two-Stream Vision-Language Pre-Training Model for Cross-Modal Retrieval","created":"2022-04-15","cited_by_count":33},{"id":"2206.06930","title":"Comprehending and Ordering Semantics for Image Captioning","created":"2022-06-14","cited_by_count":33},{"id":"2202.08926","title":"On Guiding Visual Attention with Language Specification","created":"2022-02-17","cited_by_count":30},{"id":"2104.05904","title":"DirectProbe: Studying Representations without Classifiers","created":"2021-04-13","cited_by_count":25},{"id":"2109.10613","title":"COVR: A test-bed for Visually Grounded Compositional Generalization with real images","created":"2021-09-22","cited_by_count":25},{"id":"2203.09067","title":"UNIMO-2: End-to-End Unified Vision-Language Grounded Learning","created":"2022-03-17","cited_by_count":19},{"id":"2011.12073","title":"Picking BERT's Brain: Probing for Linguistic Dependencies in Contextualized Embeddings Using Representational Similarity Analysis","created":"2020-11-24","cited_by_count":18},{"id":"2204.07190","title":"Measuring Compositional Consistency for Video Question Answering","created":"2022-04-14","cited_by_count":15},{"id":"1901.06595","title":"Evaluating Text-to-Image Matching using Binary Image Selection (BISON)","created":"2019-01-19","cited_by_count":12},{"id":"2203.09306","title":"Finding Structural Knowledge in Multimodal-BERT","created":"2022-03-17","cited_by_count":7}],"next_cursor":null}