{"list":"other","total":55,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"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":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"1706.06083","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","created":"2017-06-19","cited_by_count":6415},{"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":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"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":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"2107.07651","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","created":"2021-07-16","cited_by_count":1619},{"id":"1908.07490","title":"LXMERT: Learning Cross-Modality Encoder Representations from Transformers","created":"2019-08-20","cited_by_count":1553},{"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":"2004.06165","title":"Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks","created":"2020-04-13","cited_by_count":1214},{"id":"2101.11986","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet","created":"2021-01-28","cited_by_count":1101},{"id":"1608.00272","title":"Modeling Context in Referring Expressions","created":"2016-07-31","cited_by_count":1063},{"id":"1607.08822","title":"SPICE: Semantic Propositional Image Caption Evaluation","created":"2016-07-29","cited_by_count":824},{"id":"2203.02053","title":"Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning","created":"2022-03-03","cited_by_count":561},{"id":"2004.09984","title":"BERT-ATTACK: Adversarial Attack Against BERT Using BERT","created":"2020-04-21","cited_by_count":491},{"id":"2105.10497","title":"Intriguing Properties of Vision Transformers","created":"2021-05-21","cited_by_count":446},{"id":"1904.02884","title":"Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attacks","created":"2019-04-05","cited_by_count":442},{"id":"2111.02387","title":"An Empirical Study of Training End-to-End Vision-and-Language Transformers","created":"2021-11-03","cited_by_count":271},{"id":"2202.10401","title":"Vision-Language Pre-Training with Triple Contrastive Learning","created":"2022-02-21","cited_by_count":212},{"id":"2111.12233","title":"Scaling Up Vision-Language Pre-training for Image Captioning","created":"2021-11-24","cited_by_count":196},{"id":"2102.00436","title":"Admix: Enhancing the Transferability of Adversarial Attacks","created":"2021-01-31","cited_by_count":156},{"id":"2003.03772","title":"IMRAM: Iterative Matching with Recurrent Attention Memory for Cross-Modal Image-Text Retrieval","created":"2020-03-08","cited_by_count":115},{"id":"1909.05506","title":"CAMP: Cross-Modal Adaptive Message Passing for Text-Image Retrieval","created":"2019-09-12","cited_by_count":110},{"id":"2010.04055","title":"A Unified Approach to Interpreting and Boosting Adversarial Transferability","created":"2020-10-08","cited_by_count":71},{"id":"2008.01919","title":"Adv-watermark: A Novel Watermark Perturbation for Adversarial Examples","created":"2020-08-05","cited_by_count":56},{"id":"2206.08919","title":"VLMixer: Unpaired Vision-Language Pre-training via Cross-Modal CutMix","created":"2022-06-17","cited_by_count":45},{"id":"2310.17626","title":"A Survey on Transferability of Adversarial Examples across Deep Neural Networks","created":"2023-10-26","cited_by_count":44},{"id":"2108.01682","title":"Exploiting BERT For Multimodal Target Sentiment Classification Through Input Space Translation","created":"2021-08-03","cited_by_count":41},{"id":"2307.16634","title":"CDUL: CLIP-Driven Unsupervised Learning for Multi-Label Image Classification","created":"2023-07-31","cited_by_count":39},{"id":"2303.15735","title":"Improving the Transferability of Adversarial Samples by Path-Augmented Method","created":"2023-03-28","cited_by_count":36},{"id":"2304.00202","title":"Improving Fast Adversarial Training with Prior-Guided Knowledge","created":"2023-04-01","cited_by_count":35},{"id":"2308.03793","title":"ReCLIP: Refine Contrastive Language Image Pre-Training with Source Free Domain Adaptation","created":"2023-08-04","cited_by_count":35},{"id":"2009.11508","title":"Improving Query Efficiency of Black-box Adversarial Attack","created":"2020-09-24","cited_by_count":34},{"id":"2307.07873","title":"Why Does Little Robustness Help? A Further Step Towards Understanding Adversarial Transferability","created":"2023-07-15","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":"2304.13410","title":"Improving Adversarial Transferability via Intermediate-level Perturbation Decay","created":"2023-04-26","cited_by_count":29},{"id":"2104.09411","title":"Understanding Chinese Video and Language via Contrastive Multimodal Pre-Training","created":"2021-04-19","cited_by_count":23},{"id":"2405.14077","title":"Learning to Transform Dynamically for Better Adversarial Transferability","created":"2024-05-23","cited_by_count":23},{"id":"2006.14512","title":"Uncovering the Connections Between Adversarial Transferability and Knowledge Transferability","created":"2020-06-25","cited_by_count":22},{"id":"2210.03919","title":"CLIP-PAE: Projection-Augmentation Embedding to Extract Relevant Features for a Disentangled, Interpretable, and Controllable Text-Guided Face Manipulation","created":"2022-10-08","cited_by_count":19},{"id":"2405.14169","title":"Towards Transferable Attacks Against Vision-LLMs in Autonomous Driving with Typography","created":"2024-05-23","cited_by_count":18},{"id":"2107.12085","title":"Learning to Adversarially Blur Visual Object Tracking","created":"2021-07-26","cited_by_count":14},{"id":"2306.08565","title":"Reliable Evaluation of Adversarial Transferability","created":"2023-06-14","cited_by_count":13},{"id":"2201.06070","title":"ALA: Naturalness-aware Adversarial Lightness Attack","created":"2022-01-16","cited_by_count":11},{"id":"2403.06014","title":"Hard-label based Small Query Black-box Adversarial Attack","created":"2024-03-09","cited_by_count":10},{"id":"2303.14038","title":"Accelerating Vision-Language Pretraining with Free Language Modeling","created":"2023-03-24","cited_by_count":9},{"id":"2111.13841","title":"Adaptive Perturbation for Adversarial Attack","created":"2021-11-27","cited_by_count":7},{"id":"2109.11778","title":"Dense Contrastive Visual-Linguistic Pretraining","created":"2021-09-24","cited_by_count":5}],"next_cursor":null}