{"list":"other","total":68,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"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":"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":"1710.09412","title":"mixup: Beyond Empirical Risk Minimization","created":"2017-10-25","cited_by_count":5183},{"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":"1905.04899","title":"CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features","created":"2019-05-13","cited_by_count":2884},{"id":"1903.12261","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","created":"2019-03-28","cited_by_count":2877},{"id":"1612.00837","title":"Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering","created":"2016-12-02","cited_by_count":2516},{"id":"2006.16241","title":"The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization","created":"2020-06-29","cited_by_count":1850},{"id":"2107.07651","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","created":"2021-07-16","cited_by_count":1619},{"id":"1907.07174","title":"Natural Adversarial Examples","created":"2019-07-16","cited_by_count":1408},{"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":"1707.07998","title":"Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering","created":"2017-07-25","cited_by_count":1312},{"id":"1409.1259","title":"On the Properties of Neural Machine Translation: Encoder-Decoder Approaches","created":"2014-09-03","cited_by_count":1304},{"id":"2205.01917","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","created":"2022-05-04","cited_by_count":1274},{"id":"2102.03334","title":"ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision","created":"2021-02-05","cited_by_count":1230},{"id":"2004.06165","title":"Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks","created":"2020-04-13","cited_by_count":1214},{"id":"1708.06733","title":"BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain","created":"2017-08-22","cited_by_count":1106},{"id":"1712.05526","title":"Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoning","created":"2017-12-15","cited_by_count":1055},{"id":"2103.17249","title":"StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery","created":"2021-03-31","cited_by_count":991},{"id":"1412.2306","title":"Deep Visual-Semantic Alignments for Generating Image Descriptions","created":"2014-12-07","cited_by_count":968},{"id":"1611.01236","title":"Adversarial Machine Learning at Scale","created":"2016-11-04","cited_by_count":936},{"id":"2109.12098","title":"CLIPort: What and Where Pathways for Robotic Manipulation","created":"2021-09-24","cited_by_count":622},{"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":"1705.07263","title":"Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methods","created":"2017-05-20","cited_by_count":546},{"id":"2004.09984","title":"BERT-ATTACK: Adversarial Attack Against BERT Using BERT","created":"2020-04-21","cited_by_count":491},{"id":"1804.07998","title":"Generating Natural Language Adversarial Examples","created":"2018-04-21","cited_by_count":424},{"id":"1803.08024","title":"Stacked Cross Attention for Image-Text Matching","created":"2018-03-21","cited_by_count":416},{"id":"2004.01970","title":"BAE: BERT-based Adversarial Examples for Text Classification","created":"2020-04-04","cited_by_count":316},{"id":"1711.02173","title":"Synthetic and Natural Noise Both Break Neural Machine Translation","created":"2017-11-06","cited_by_count":306},{"id":"1706.03691","title":"Certified Defenses for Data Poisoning Attacks","created":"2017-06-09","cited_by_count":303},{"id":"1804.06059","title":"Adversarial Example Generation with Syntactically Controlled Paraphrase Networks","created":"2018-04-17","cited_by_count":286},{"id":"1905.07121","title":"Simple Black-box Adversarial Attacks","created":"2019-05-17","cited_by_count":251},{"id":"1802.05300","title":"Using Trusted Data to Train Deep Networks on Labels Corrupted by Severe Noise","created":"2018-02-14","cited_by_count":216},{"id":"1909.02701","title":"Visual Semantic Reasoning for Image-Text Matching","created":"2019-09-06","cited_by_count":185},{"id":"1909.00986","title":"Certified Robustness to Adversarial Word Substitutions","created":"2019-09-03","cited_by_count":168},{"id":"2101.05068","title":"Probabilistic Embeddings for Cross-Modal Retrieval","created":"2021-01-13","cited_by_count":151},{"id":"2106.09667","title":"Poisoning and Backdooring Contrastive Learning","created":"2021-06-17","cited_by_count":151},{"id":"2011.04305","title":"Learning the Best Pooling Strategy for Visual Semantic Embedding","created":"2020-11-09","cited_by_count":137},{"id":"2009.07502","title":"Contextualized Perturbation for Textual Adversarial Attack","created":"2020-09-16","cited_by_count":136},{"id":"2101.01368","title":"Similarity Reasoning and Filtration for Image-Text Matching","created":"2021-01-05","cited_by_count":121},{"id":"1511.05099","title":"Yin and Yang: Balancing and Answering Binary Visual Questions","created":"2015-11-16","cited_by_count":109},{"id":"1902.05660","title":"Cycle-Consistency for Robust Visual Question Answering","created":"2019-02-15","cited_by_count":105},{"id":"1909.05040","title":"Sparse and Imperceivable Adversarial Attacks","created":"2019-09-11","cited_by_count":95},{"id":"1906.04402","title":"Polysemous Visual-Semantic Embedding for Cross-Modal Retrieval","created":"2019-06-11","cited_by_count":83},{"id":"2106.00245","title":"Adversarial VQA: A New Benchmark for Evaluating the Robustness of VQA Models","created":"2021-06-01","cited_by_count":75},{"id":"2106.09898","title":"Bad Characters: Imperceptible NLP Attacks","created":"2021-06-18","cited_by_count":71},{"id":"2107.13541","title":"Towards Robustness Against Natural Language Word Substitutions","created":"2021-07-28","cited_by_count":69},{"id":"2007.08883","title":"Consensus-Aware Visual-Semantic Embedding for Image-Text Matching","created":"2020-07-17","cited_by_count":59},{"id":"2102.01645","title":"Generating images from caption and vice versa via CLIP-Guided Generative Latent Space Search","created":"2021-02-02","cited_by_count":57},{"id":"2106.02280","title":"Human-Adversarial Visual Question Answering","created":"2021-06-04","cited_by_count":57},{"id":"2002.08325","title":"VQA-LOL: Visual Question Answering under the Lens of Logic","created":"2020-02-19","cited_by_count":48},{"id":"2004.15020","title":"Crisscrossed Captions: Extended Intramodal and Intermodal Semantic Similarity Judgments for MS-COCO","created":"2020-04-30","cited_by_count":46},{"id":"2012.08673","title":"A Closer Look at the Robustness of Vision-and-Language Pre-trained Models","created":"2020-12-15","cited_by_count":37},{"id":"2204.03359","title":"ECCV Caption: Correcting False Negatives by Collecting Machine-and-Human-verified Image-Caption Associations for MS-COCO","created":"2022-04-07","cited_by_count":37},{"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":"2211.16761","title":"Improving Cross-Modal Retrieval with Set of Diverse Embeddings","created":"2022-11-30","cited_by_count":33},{"id":"1812.00552","title":"Universal Perturbation Attack Against Image Retrieval","created":"2018-12-03","cited_by_count":32},{"id":"2203.16778","title":"ViSTA: Vision and Scene Text Aggregation for Cross-Modal Retrieval","created":"2022-03-31","cited_by_count":29},{"id":"2204.13653","title":"GRIT: General Robust Image Task Benchmark","created":"2022-04-28","cited_by_count":26},{"id":"2208.09843","title":"CODER: Coupled Diversity-Sensitive Momentum Contrastive Learning for Image-Text Retrieval","created":"2022-08-21","cited_by_count":13},{"id":"2208.04060","title":"GRIT-VLP: Grouped Mini-batch Sampling for Efficient Vision and Language Pre-training","created":"2022-08-08","cited_by_count":10}],"next_cursor":null}