{"list":"other","total":99,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1611.07004","title":"Image-to-Image Translation with Conditional Adversarial Networks","created":"2016-11-21","cited_by_count":4527},{"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":"1912.04958","title":"Analyzing and Improving the Image Quality of StyleGAN","created":"2019-12-03","cited_by_count":3588},{"id":"2006.09882","title":"Unsupervised Learning of Visual Features by Contrasting Cluster Assignments","created":"2020-06-17","cited_by_count":2857},{"id":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"1602.07261","title":"Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning","created":"2016-02-23","cited_by_count":1512},{"id":"1908.03557","title":"VisualBERT: A Simple and Performant Baseline for Vision and Language","created":"2019-08-09","cited_by_count":1296},{"id":"2102.03334","title":"ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision","created":"2021-02-05","cited_by_count":1230},{"id":"1606.05328","title":"Conditional Image Generation with PixelCNN Decoders","created":"2016-06-16","cited_by_count":862},{"id":"2004.14368","title":"VGGSound: A Large-scale Audio-Visual Dataset","created":"2020-04-29","cited_by_count":648},{"id":"2107.09044","title":"Just Train Twice: Improving Group Robustness without Training Group Information","created":"2021-07-19","cited_by_count":523},{"id":"2301.11325","title":"MusicLM: Generating Music From Text","created":"2023-01-26","cited_by_count":448},{"id":"1703.09039","title":"Efficient Processing of Deep Neural Networks: A Tutorial and Survey","created":"2017-03-27","cited_by_count":434},{"id":"1606.05908","title":"Tutorial on Variational Autoencoders","created":"2016-06-19","cited_by_count":409},{"id":"2012.09740","title":"Understanding the Behaviour of Contrastive Loss","created":"2020-12-15","cited_by_count":398},{"id":"1512.07108","title":"Recent Advances in Convolutional Neural Networks","created":"2015-12-22","cited_by_count":360},{"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":"2009.07888","title":"Transfer Learning in Deep Reinforcement Learning: A Survey","created":"2020-09-16","cited_by_count":265},{"id":"1812.01784","title":"Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoders","created":"2018-12-05","cited_by_count":206},{"id":"2211.08332","title":"Versatile Diffusion: Text, Images and Variations All in One Diffusion Model","created":"2022-11-15","cited_by_count":199},{"id":"1406.4773","title":"Deep Learning Face Representation by Joint Identification-Verification","created":"2014-06-18","cited_by_count":162},{"id":"1601.06733","title":"Long Short-Term Memory-Networks for Machine Reading","created":"2016-01-25","cited_by_count":161},{"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":"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":"1712.09763","title":"PixelSNAIL: An Improved Autoregressive Generative Model","created":"2017-12-28","cited_by_count":137},{"id":"2106.06847","title":"Video Super-Resolution Transformer","created":"2021-06-12","cited_by_count":121},{"id":"1510.06479","title":"Generic decoding of seen and imagined objects using hierarchical visual features","created":"2015-10-22","cited_by_count":120},{"id":"2404.00282","title":"Survey on Large Language Model-Enhanced Reinforcement Learning: Concept, Taxonomy, and Methods","created":"2024-03-30","cited_by_count":116},{"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":"2303.05334","title":"Natural scene reconstruction from fMRI signals using generative latent diffusion","created":"2023-03-09","cited_by_count":97},{"id":"2106.01804","title":"E2E-VLP: End-to-End Vision-Language Pre-training Enhanced by Visual Learning","created":"2021-06-03","cited_by_count":85},{"id":"2210.01769","title":"Mind Reader: Reconstructing complex images from brain activities","created":"2022-09-30","cited_by_count":85},{"id":"2007.10595","title":"Video Super-resolution with Temporal Group Attention","created":"2020-07-21","cited_by_count":81},{"id":"1609.00344","title":"Deep Learning Human Mind for Automated Visual Classification","created":"2016-09-01","cited_by_count":77},{"id":"2211.05994","title":"A Survey of Knowledge Enhanced Pre-trained Language Models","created":"2022-11-11","cited_by_count":76},{"id":"2411.17558","title":"Natural Language Understanding and Inference with MLLM in Visual Question Answering: A Survey","created":"2024-11-26","cited_by_count":76},{"id":"2305.11675","title":"Cinematic Mindscapes: High-quality Video Reconstruction from Brain Activity","created":"2023-05-19","cited_by_count":71},{"id":"1907.02431","title":"From voxels to pixels and back: Self-supervision in natural-image reconstruction from fMRI","created":"2019-07-03","cited_by_count":67},{"id":"2404.07850","title":"MindBridge: A Cross-Subject Brain Decoding Framework","created":"2024-04-11","cited_by_count":66},{"id":"2307.04722","title":"Advances and Challenges in Meta-Learning: A Technical Review","created":"2023-07-10","cited_by_count":65},{"id":"1809.01281","title":"BOLD5000: A public fMRI dataset of 5000 images","created":"2018-09-05","cited_by_count":63},{"id":"1608.03425","title":"Neural Encoding and Decoding with Deep Learning for Dynamic Natural Vision","created":"2016-08-11","cited_by_count":60},{"id":"2202.12692","title":"Reconstruction of Perceived Images from fMRI Patterns and Semantic Brain Exploration using Instance-Conditioned GANs","created":"2022-02-25","cited_by_count":55},{"id":"1810.10974","title":"Decoding Brain Representations by Multimodal Learning of Neural Activity and Visual Features","created":"2018-10-25","cited_by_count":52},{"id":"2212.02409","title":"Decoding natural image stimuli from fMRI data with a surface-based convolutional network","created":"2022-12-05","cited_by_count":49},{"id":"2403.05234","title":"Benchmarking Micro-action Recognition: Dataset, Methods, and Applications","created":"2024-03-08","cited_by_count":48},{"id":"2308.04249","title":"MindDiffuser: Controlled Image Reconstruction from Human Brain Activity with Semantic and Structural Diffusion","created":"2023-08-08","cited_by_count":47},{"id":"2001.11761","title":"Reconstructing Natural Scenes from fMRI Patterns using BigBiGAN","created":"2020-01-31","cited_by_count":44},{"id":"2310.02265","title":"DREAM: Visual Decoding from Reversing Human Visual System","created":"2023-10-03","cited_by_count":44},{"id":"1810.03856","title":"Reconstructing Faces from fMRI Patterns using Deep Generative Neural Networks","created":"2018-10-09","cited_by_count":43},{"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":"2307.01003","title":"Visual Instruction Tuning with Polite Flamingo","created":"2023-07-03","cited_by_count":38},{"id":"2305.17214","title":"Contrast, Attend and Diffuse to Decode High-Resolution Images from Brain Activities","created":"2023-05-26","cited_by_count":36},{"id":"2305.11560","title":"Brain Captioning: Decoding human brain activity into images and text","created":"2023-05-19","cited_by_count":34},{"id":"2403.18211","title":"NeuroPictor: Refining fMRI-to-Image Reconstruction via Multi-individual Pretraining and Multi-level Modulation","created":"2024-03-27","cited_by_count":34},{"id":"2101.12083","title":"Reconstructing Perceptive Images from Brain Activity by Shape-Semantic GAN","created":"2021-01-28","cited_by_count":32},{"id":"2404.07202","title":"UMBRAE: Unified Multimodal Brain Decoding","created":"2024-04-10","cited_by_count":32},{"id":"2407.02235","title":"Towards a Holistic Framework for Multimodal Large Language Models in Three-dimensional Brain CT Report Generation","created":"2024-07-02","cited_by_count":31},{"id":"2305.10135","title":"Controllable Mind Visual Diffusion Model","created":"2023-05-17","cited_by_count":30},{"id":"2211.05617","title":"Debiasing Methods for Fairer Neural Models in Vision and Language Research: A Survey","created":"2022-11-10","cited_by_count":22},{"id":"2307.05355","title":"UniCoRN: Unified Cognitive Signal ReconstructioN bridging cognitive signals and human language","created":"2023-07-06","cited_by_count":22},{"id":"2403.20022","title":"Psychometry: An Omnifit Model for Image Reconstruction from Human Brain Activity","created":"2024-03-29","cited_by_count":22},{"id":"2412.14719","title":"Prototypical Calibrating Ambiguous Samples for Micro-Action Recognition","created":"2024-12-19","cited_by_count":22},{"id":"2307.10246","title":"Deep Neural Networks and Brain Alignment: Brain Encoding and Decoding (Survey)","created":"2023-07-17","cited_by_count":21},{"id":"2309.00627","title":"Through their eyes: multi-subject Brain Decoding with simple alignment techniques","created":"2023-08-01","cited_by_count":21},{"id":"2206.03544","title":"A Penny for Your (visual) Thoughts: Self-Supervised Reconstruction of Natural Movies from Brain Activity","created":"2022-06-07","cited_by_count":20},{"id":"2407.04490","title":"Micro-gesture Online Recognition using Learnable Query Points","created":"2024-07-05","cited_by_count":18},{"id":"2409.02413","title":"Abstractive Text Summarization: State of the Art, Challenges, and Improvements","created":"2024-09-04","cited_by_count":17},{"id":"2401.00430","title":"Brain-Conditional Multimodal Synthesis: A Survey and Taxonomy","created":"2023-12-31","cited_by_count":15},{"id":"1912.07358","title":"Blind Denoising Autoencoder","created":"2019-12-11","cited_by_count":13},{"id":"2407.14020","title":"NeuroBind: Towards Unified Multimodal Representations for Neural Signals","created":"2024-07-19","cited_by_count":13},{"id":"2212.06726","title":"Semantic Brain Decoding: from fMRI to conceptually similar image reconstruction of visual stimuli","created":"2022-12-13","cited_by_count":12},{"id":"2503.06940","title":"CineBrain: A Large-Scale Multi-Modal Brain Dataset During Naturalistic Audiovisual Narrative Processing","created":"2025-03-10","cited_by_count":11},{"id":"2307.11078","title":"Brain2Music: Reconstructing Music from Human Brain Activity","created":"2023-07-20","cited_by_count":10},{"id":"2402.13809","title":"NeuralDiffuser: Neuroscience-inspired Diffusion Guidance for fMRI Visual Reconstruction","created":"2024-02-21","cited_by_count":10},{"id":"2501.14309","title":"BrainGuard: Privacy-Preserving Multisubject Image Reconstructions from Brain Activities","created":"2025-01-24","cited_by_count":10},{"id":"2303.14730","title":"Joint fMRI Decoding and Encoding with Latent Embedding Alignment","created":"2023-03-26","cited_by_count":8},{"id":"2306.00927","title":"Second Sight: Using brain-optimized encoding models to align image distributions with human brain activity","created":"2023-06-01","cited_by_count":7},{"id":"2110.06634","title":"End-to-end translation of human neural activity to speech with a dual-dual generative adversarial network","created":"2021-10-13","cited_by_count":6},{"id":"2308.12058","title":"DR-Tune: Improving Fine-tuning of Pretrained Visual Models by Distribution Regularization with Semantic Calibration","created":"2023-08-23","cited_by_count":6},{"id":"2106.05113","title":"More Than Meets the Eye: Self-Supervised Depth Reconstruction From Brain Activity","created":"2021-06-09","cited_by_count":5},{"id":"2306.11629","title":"Sound reconstruction from human brain activity via a generative model with brain-like auditory features","created":"2023-06-20","cited_by_count":5},{"id":"2502.06552","title":"Diffusion Models for Computational Neuroimaging: A Survey","created":"2025-02-10","cited_by_count":5},{"id":"2306.10082","title":"DreamCatcher: Revealing the Language of the Brain with fMRI using GPT Embedding","created":"2023-06-16","cited_by_count":3},{"id":"2405.18812","title":"MindSemantix: Deciphering Brain Visual Experiences with a Brain-Language Model","created":"2024-05-29","cited_by_count":2},{"id":"2406.15537","title":"R&B -- Rhythm and Brain: Cross-subject Decoding of Music from Human Brain Activity","created":"2024-06-21","cited_by_count":2},{"id":"2407.09509","title":"Brain Dialogue Interface (BDI): A User-Friendly fMRI Model for Interactive Brain Decoding","created":"2024-06-17","cited_by_count":2},{"id":"2502.00412","title":"TROI: Cross-Subject Pretraining with Sparse Voxel Selection for Enhanced fMRI Visual Decoding","created":"2025-02-01","cited_by_count":2},{"id":"2308.13820","title":"Video and Audio are Images: A Cross-Modal Mixer for Original Data on Video-Audio Retrieval","created":"2023-08-26","cited_by_count":1}],"next_cursor":null}