{"list":"other","total":52,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2202.05262","title":"Locating and Editing Factual Associations in GPT","created":"2022-02-10","cited_by_count":2691},{"id":"1512.04150","title":"Learning Deep Features for Discriminative Localization","created":"2015-12-14","cited_by_count":2436},{"id":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"2102.03334","title":"ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision","created":"2021-02-05","cited_by_count":1230},{"id":"2007.04612","title":"Concept Bottleneck Models","created":"2020-07-09","cited_by_count":1032},{"id":"2106.04560","title":"Scaling Vision Transformers","created":"2021-06-08","cited_by_count":999},{"id":"2309.16588","title":"Vision Transformers Need Registers","created":"2023-09-28","cited_by_count":871},{"id":"2103.14899","title":"CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification","created":"2021-03-27","cited_by_count":806},{"id":"2005.00928","title":"Quantifying Attention Flow in Transformers","created":"2020-05-02","cited_by_count":775},{"id":"2109.07161","title":"Resolution-robust Large Mask Inpainting with Fourier Convolutions","created":"2021-09-15","cited_by_count":738},{"id":"2401.06209","title":"Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs","created":"2024-01-11","cited_by_count":735},{"id":"1704.03296","title":"Interpretable Explanations of Black Boxes by Meaningful Perturbation","created":"2017-04-11","cited_by_count":612},{"id":"2206.06520","title":"Memory-Based Model Editing at Scale","created":"2022-06-13","cited_by_count":447},{"id":"2202.07800","title":"Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations","created":"2022-02-16","cited_by_count":363},{"id":"1608.00507","title":"Top-down Neural Attention by Excitation Backprop","created":"2016-08-01","cited_by_count":321},{"id":"2103.15679","title":"Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers","created":"2021-03-29","cited_by_count":320},{"id":"2009.05041","title":"Understanding the Role of Individual Units in a Deep Neural Network","created":"2020-09-10","cited_by_count":255},{"id":"2002.01650","title":"Concept Whitening for Interpretable Image Recognition","created":"2020-02-05","cited_by_count":225},{"id":"2304.04370","title":"OpenAGI: When LLM Meets Domain Experts","created":"2023-04-10","cited_by_count":197},{"id":"2011.05429","title":"Debugging Tests for Model Explanations","created":"2020-11-10","cited_by_count":147},{"id":"2204.05991","title":"ReCLIP: A Strong Zero-Shot Baseline for Referring Expression Comprehension","created":"2022-04-12","cited_by_count":120},{"id":"2303.10323","title":"Dynamic Graph Enhanced Contrastive Learning for Chest X-ray Report Generation","created":"2023-03-18","cited_by_count":118},{"id":"1808.10584","title":"Learning to Describe Differences Between Pairs of Similar Images","created":"2018-08-31","cited_by_count":114},{"id":"2007.15646","title":"Rewriting a Deep Generative Model","created":"2020-07-30","cited_by_count":107},{"id":"2205.01580","title":"Better plain ViT baselines for ImageNet-1k","created":"2022-05-03","cited_by_count":98},{"id":"2105.14944","title":"The effectiveness of feature attribution methods and its correlation with automatic evaluation scores","created":"2021-05-31","cited_by_count":88},{"id":"2308.04657","title":"Which Tokens to Use? Investigating Token Reduction in Vision Transformers","created":"2023-08-09","cited_by_count":60},{"id":"2010.13233","title":"Now You See Me (CME): Concept-based Model Extraction","created":"2020-10-25","cited_by_count":51},{"id":"1906.07689","title":"Expressing Visual Relationships via Language","created":"2019-06-18","cited_by_count":49},{"id":"1907.10882","title":"Interpretability Beyond Classification Output: Semantic Bottleneck Networks","created":"2019-07-25","cited_by_count":49},{"id":"2304.10131","title":"Learning Bottleneck Concepts in Image Classification","created":"2023-04-20","cited_by_count":49},{"id":"2103.14146","title":"Describing and Localizing Multiple Changes with Transformers","created":"2021-03-25","cited_by_count":47},{"id":"2307.11986","title":"Expert Knowledge-Aware Image Difference Graph Representation Learning for Difference-Aware Medical Visual Question Answering","created":"2023-07-22","cited_by_count":41},{"id":"2202.04298","title":"Image Difference Captioning with Pre-training and Contrastive Learning","created":"2022-02-09","cited_by_count":39},{"id":"2206.00629","title":"CLIP4IDC: CLIP for Image Difference Captioning","created":"2022-06-01","cited_by_count":25},{"id":"2112.04016","title":"DeepFace-EMD: Re-ranking Using Patch-wise Earth Mover's Distance Improves Out-Of-Distribution Face Identification","created":"2021-12-07","cited_by_count":20},{"id":"2408.04594","title":"Img-Diff: Contrastive Data Synthesis for Multimodal Large Language Models","created":"2024-08-08","cited_by_count":17},{"id":"2407.05645","title":"OneDiff: A Generalist Model for Image Difference Captioning","created":"2024-07-08","cited_by_count":15},{"id":"2402.19119","title":"VIXEN: Visual Text Comparison Network for Image Difference Captioning","created":"2024-02-29","cited_by_count":12},{"id":"2205.13042","title":"How explainable are adversarially-robust CNNs?","created":"2022-05-25","cited_by_count":9},{"id":"2102.01860","title":"L2C: Describing Visual Differences Needs Semantic Understanding of Individuals","created":"2021-02-03","cited_by_count":8},{"id":"2403.05297","title":"PEEB: Part-based Image Classifiers with an Explainable and Editable Language Bottleneck","created":"2024-03-08","cited_by_count":7},{"id":"2406.13424","title":"Towards a multimodal framework for remote sensing image change retrieval and captioning","created":"2024-06-19","cited_by_count":5},{"id":"2311.02803","title":"Fast and Interpretable Face Identification for Out-Of-Distribution Data Using Vision Transformers","created":"2023-11-06","cited_by_count":4}],"next_cursor":null}