{"list":"other","total":59,"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"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":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2010.04159","title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","created":"2020-10-08","cited_by_count":3422},{"id":"1505.07818","title":"Domain-Adversarial Training of Neural Networks","created":"2015-05-28","cited_by_count":3044},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"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":"2006.10739","title":"Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains","created":"2020-06-18","cited_by_count":2200},{"id":"1409.7495","title":"Unsupervised Domain Adaptation by Backpropagation","created":"2014-09-26","cited_by_count":1917},{"id":"2306.02858","title":"Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding","created":"2023-06-05","cited_by_count":1471},{"id":"1504.00325","title":"Microsoft COCO Captions: Data Collection and Evaluation Server","created":"2015-04-01","cited_by_count":1462},{"id":"2105.01601","title":"MLP-Mixer: An all-MLP Architecture for Vision","created":"2021-05-04","cited_by_count":1446},{"id":"2205.01917","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","created":"2022-05-04","cited_by_count":1274},{"id":"1906.00067","title":"OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge","created":"2019-05-31","cited_by_count":1121},{"id":"2306.15195","title":"Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic","created":"2023-06-27","cited_by_count":906},{"id":"1607.08822","title":"SPICE: Semantic Propositional Image Caption Evaluation","created":"2016-07-29","cited_by_count":824},{"id":"2406.07476","title":"VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs","created":"2024-06-11","cited_by_count":771},{"id":"2206.01718","title":"A-OKVQA: A Benchmark for Visual Question Answering using World Knowledge","created":"2022-06-03","cited_by_count":710},{"id":"2311.03079","title":"CogVLM: Visual Expert for Pretrained Language Models","created":"2023-11-06","cited_by_count":708},{"id":"2205.14100","title":"GIT: A Generative Image-to-text Transformer for Vision and Language","created":"2022-05-27","cited_by_count":537},{"id":"2312.14125","title":"VideoPoet: A Large Language Model for Zero-Shot Video Generation","created":"2023-12-21","cited_by_count":492},{"id":"2308.16911","title":"PointLLM: Empowering Large Language Models to Understand Point Clouds","created":"2023-08-31","cited_by_count":333},{"id":"1905.13648","title":"Scene Text Visual Question Answering","created":"2019-05-31","cited_by_count":331},{"id":"2309.15112","title":"InternLM-XComposer: A Vision-Language Large Model for Advanced Text-image Comprehension and Composition","created":"2023-09-26","cited_by_count":297},{"id":"2205.00363","title":"Visual Spatial Reasoning","created":"2022-04-30","cited_by_count":293},{"id":"2312.03700","title":"OneLLM: One Framework to Align All Modalities with Language","created":"2023-12-06","cited_by_count":187},{"id":"2305.18274","title":"Reconstructing the Mind's Eye: fMRI-to-Image with Contrastive Learning and Diffusion Priors","created":"2023-05-29","cited_by_count":160},{"id":"1810.12440","title":"TallyQA: Answering Complex Counting Questions","created":"2018-10-29","cited_by_count":153},{"id":"2211.06956","title":"Seeing Beyond the Brain: Conditional Diffusion Model with Sparse Masked Modeling for Vision Decoding","created":"2022-11-13","cited_by_count":144},{"id":"2311.07574","title":"To See is to Believe: Prompting GPT-4V for Better Visual Instruction Tuning","created":"2023-11-13","cited_by_count":144},{"id":"1505.02074","title":"Exploring Models and Data for Image Question Answering","created":"2015-05-08","cited_by_count":139},{"id":"2402.17766","title":"ShapeLLM: Universal 3D Object Understanding for Embodied Interaction","created":"2024-02-27","cited_by_count":137},{"id":"1905.11833","title":"Interpreting and improving natural-language processing (in machines) with natural language-processing (in the brain)","created":"2019-05-28","cited_by_count":128},{"id":"2403.11207","title":"MindEye2: Shared-Subject Models Enable fMRI-To-Image With 1 Hour of Data","created":"2024-03-17","cited_by_count":109},{"id":"1611.06607","title":"A Hierarchical Approach for Generating Descriptive Image Paragraphs","created":"2016-11-20","cited_by_count":104},{"id":"2210.06681","title":"Brain Network Transformer","created":"2022-10-13","cited_by_count":94},{"id":"1703.09684","title":"An Analysis of Visual Question Answering Algorithms","created":"2017-03-28","cited_by_count":90},{"id":"2404.07850","title":"MindBridge: A Cross-Subject Brain Decoding Framework","created":"2024-04-11","cited_by_count":66},{"id":"1803.07464","title":"VQA-E: Explaining, Elaborating, and Enhancing Your Answers for Visual Questions","created":"2018-03-20","cited_by_count":50},{"id":"2308.07428","title":"UniBrain: Unify Image Reconstruction and Captioning All in One Diffusion Model from Human Brain Activity","created":"2023-08-14","cited_by_count":42},{"id":"2305.11560","title":"Brain Captioning: Decoding human brain activity into images and text","created":"2023-05-19","cited_by_count":34},{"id":"2310.17594","title":"SPA: A Graph Spectral Alignment Perspective for Domain Adaptation","created":"2023-10-26","cited_by_count":22},{"id":"1909.10470","title":"Improving Generative Visual Dialog by Answering Diverse Questions","created":"2019-09-23","cited_by_count":21},{"id":"2310.04420","title":"BrainSCUBA: Fine-Grained Natural Language Captions of Visual Cortex Selectivity","created":"2023-10-06","cited_by_count":19},{"id":"2412.19487","title":"UniBrain: A Unified Model for Cross-Subject Brain Decoding","created":"2024-12-27","cited_by_count":11},{"id":"2312.02203","title":"Learning High-Order Relationships of Brain Regions","created":"2023-12-02","cited_by_count":10},{"id":"2402.01590","title":"NeuroCine: Decoding Vivid Video Sequences from Human Brain Activties","created":"2024-02-02","cited_by_count":10},{"id":"2405.07840","title":"Open-vocabulary Auditory Neural Decoding Using fMRI-prompted LLM","created":"2024-05-13","cited_by_count":9},{"id":"1609.06657","title":"The Color of the Cat is Gray: 1 Million Full-Sentences Visual Question Answering (FSVQA)","created":"2016-09-21","cited_by_count":7},{"id":"2309.15729","title":"MindGPT: Interpreting What You See with Non-invasive Brain Recordings","created":"2023-09-27","cited_by_count":6},{"id":"2401.08968","title":"COCO is \"ALL'' You Need for Visual Instruction Fine-tuning","created":"2024-01-17","cited_by_count":3},{"id":"2406.07584","title":"BrainChat: Decoding Semantic Information from fMRI using Vision-language Pretrained Models","created":"2024-06-10","cited_by_count":3},{"id":"2212.03169","title":"When Brain-Computer Interfaces Meet the Metaverse: Landscape, Demonstrator, Trends, Challenges, and Concerns","created":"2022-12-06","cited_by_count":2},{"id":"2409.19710","title":"A multimodal LLM for the non-invasive decoding of spoken text from brain recordings","created":"2024-09-29","cited_by_count":1}],"next_cursor":null}