{"list":"other","total":52,"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":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"id":"1905.07830","title":"HellaSwag: Can a Machine Really Finish Your Sentence?","created":"2019-05-19","cited_by_count":4100},{"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":"1911.11641","title":"PIQA: Reasoning about Physical Commonsense in Natural Language","created":"2019-11-26","cited_by_count":2883},{"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":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"id":"2209.09513","title":"Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering","created":"2022-09-20","cited_by_count":1919},{"id":"2002.05202","title":"GLU Variants Improve Transformer","created":"2020-02-12","cited_by_count":1804},{"id":"2305.10355","title":"Evaluating Object Hallucination in Large Vision-Language Models","created":"2023-05-17","cited_by_count":1729},{"id":"1904.08920","title":"Towards VQA Models That Can Read","created":"2019-04-18","cited_by_count":1718},{"id":"2102.03334","title":"ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision","created":"2021-02-05","cited_by_count":1230},{"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":"2101.11986","title":"Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet","created":"2021-01-28","cited_by_count":1101},{"id":"1608.05442","title":"Semantic Understanding of Scenes through the ADE20K Dataset","created":"2016-08-18","cited_by_count":1069},{"id":"1704.00675","title":"The 2017 DAVIS Challenge on Video Object Segmentation","created":"2017-04-03","cited_by_count":957},{"id":"2112.04482","title":"FLAVA: A Foundational Language And Vision Alignment Model","created":"2021-12-08","cited_by_count":649},{"id":"2112.09133","title":"Masked Feature Prediction for Self-Supervised Visual Pre-Training","created":"2021-12-16","cited_by_count":576},{"id":"2005.04790","title":"The Hateful Memes Challenge: Detecting Hate Speech in Multimodal Memes","created":"2020-05-10","cited_by_count":490},{"id":"2403.18814","title":"Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models","created":"2024-03-27","cited_by_count":365},{"id":"2102.06171","title":"High-Performance Large-Scale Image Recognition Without Normalization","created":"2021-02-11","cited_by_count":360},{"id":"2006.06666","title":"VirTex: Learning Visual Representations from Textual Annotations","created":"2020-06-11","cited_by_count":339},{"id":"2107.06383","title":"How Much Can CLIP Benefit Vision-and-Language Tasks?","created":"2021-07-13","cited_by_count":321},{"id":"2110.13214","title":"IconQA: A New Benchmark for Abstract Diagram Understanding and Visual Language Reasoning","created":"2021-10-25","cited_by_count":267},{"id":"2403.09338","title":"LocalMamba: Visual State Space Model with Windowed Selective Scan","created":"2024-03-14","cited_by_count":236},{"id":"2304.06939","title":"Multimodal C4: An Open, Billion-scale Corpus of Images Interleaved with Text","created":"2023-04-14","cited_by_count":208},{"id":"2406.07522","title":"Samba: Simple Hybrid State Space Models for Efficient Unlimited Context Language Modeling","created":"2024-06-11","cited_by_count":174},{"id":"2501.03895","title":"LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision Token","created":"2025-01-07","cited_by_count":166},{"id":"2405.16712","title":"Zamba: A Compact 7B SSM Hybrid Model","created":"2024-05-26","cited_by_count":124},{"id":"1807.05713","title":"Land-Cover Classification with High-Resolution Remote Sensing Images Using Transferable Deep Models","created":"2018-07-16","cited_by_count":119},{"id":"2105.09996","title":"VLM: Task-agnostic Video-Language Model Pre-training for Video Understanding","created":"2021-05-20","cited_by_count":102},{"id":"2301.06267","title":"Multimodality Helps Unimodality: Cross-Modal Few-Shot Learning with Multimodal Models","created":"2023-01-16","cited_by_count":91},{"id":"2105.06220","title":"VSR: A Unified Framework for Document Layout Analysis combining Vision, Semantics and Relations","created":"2021-05-13","cited_by_count":40},{"id":"2412.00678","title":"2DMamba: Efficient State Space Model for Image Representation with Applications on Giga-Pixel Whole Slide Image Classification","created":"2024-12-01","cited_by_count":35},{"id":"2312.05328","title":"Bad Students Make Great Teachers: Active Learning Accelerates Large-Scale Visual Understanding","created":"2023-12-08","cited_by_count":28},{"id":"2311.00308","title":"From Image to Language: A Critical Analysis of Visual Question Answering (VQA) Approaches, Challenges, and Opportunities","created":"2023-11-01","cited_by_count":25},{"id":"2310.04414","title":"CIFAR-10-Warehouse: Broad and More Realistic Testbeds in Model Generalization Analysis","created":"2023-10-06","cited_by_count":12},{"id":"2411.17773","title":"Efficient Multi-modal Large Language Models via Visual Token Grouping","created":"2024-11-26","cited_by_count":9},{"id":"2409.19937","title":"MaskMamba: A Hybrid Mamba-Transformer Model for Masked Image Generation","created":"2024-09-30","cited_by_count":8},{"id":"2106.03640","title":"Making EfficientNet More Efficient: Exploring Batch-Independent Normalization, Group Convolutions and Reduced Resolution Training","created":"2021-06-07","cited_by_count":6},{"id":"2311.02709","title":"Benchmarking a Benchmark: How Reliable is MS-COCO?","created":"2023-11-05","cited_by_count":6},{"id":"2407.08558","title":"ST-Mamba: Spatial-Temporal Mamba for Traffic Flow Estimation Recovery using Limited Data","created":"2024-07-11","cited_by_count":4},{"id":"2309.16141","title":"Align before Search: Aligning Ads Image to Text for Accurate Cross-Modal Sponsored Search","created":"2023-09-28","cited_by_count":3},{"id":"2412.18409","title":"The Impact of the Single-Label Assumption in Image Recognition Benchmarking","created":"2024-12-24","cited_by_count":1}],"next_cursor":null}