{"list":"other","total":51,"rows":[{"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"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":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"1502.03044","title":"Show, Attend and Tell: Neural Image Caption Generation with Visual Attention","created":"2015-02-10","cited_by_count":1423},{"id":"1906.07155","title":"MMDetection: Open MMLab Detection Toolbox and Benchmark","created":"2019-06-17","cited_by_count":1385},{"id":"1807.10221","title":"Unified Perceptual Parsing for Scene Understanding","created":"2018-07-26","cited_by_count":1271},{"id":"2104.08860","title":"CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval","created":"2021-04-18","cited_by_count":651},{"id":"2109.14084","title":"VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding","created":"2021-09-28","cited_by_count":602},{"id":"2109.08472","title":"ActionCLIP: A New Paradigm for Video Action Recognition","created":"2021-09-17","cited_by_count":320},{"id":"2207.07285","title":"X-CLIP: End-to-End Multi-grained Contrastive Learning for Video-Text Retrieval","created":"2022-07-15","cited_by_count":280},{"id":"2106.11097","title":"CLIP2Video: Mastering Video-Text Retrieval via Image CLIP","created":"2021-06-21","cited_by_count":225},{"id":"1502.04623","title":"DRAW: A Recurrent Neural Network For Image Generation","created":"2015-02-16","cited_by_count":191},{"id":"2212.03640","title":"Fine-tuned CLIP Models are Efficient Video Learners","created":"2022-12-06","cited_by_count":179},{"id":"2206.01720","title":"Revisiting the \"Video\" in Video-Language Understanding","created":"2022-06-03","cited_by_count":169},{"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":"1510.06479","title":"Generic decoding of seen and imagined objects using hierarchical visual features","created":"2015-10-22","cited_by_count":120},{"id":"2303.05334","title":"Natural scene reconstruction from fMRI signals using generative latent diffusion","created":"2023-03-09","cited_by_count":97},{"id":"1411.6422","title":"Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Brain's Ventral Visual Pathway","created":"2014-11-24","cited_by_count":94},{"id":"2210.06681","title":"Brain Network Transformer","created":"2022-10-13","cited_by_count":94},{"id":"2210.01769","title":"Mind Reader: Reconstructing complex images from brain activities","created":"2022-09-30","cited_by_count":85},{"id":"1609.00344","title":"Deep Learning Human Mind for Automated Visual Classification","created":"2016-09-01","cited_by_count":77},{"id":"2209.06430","title":"CLIP-ViP: Adapting Pre-trained Image-Text Model to Video-Language Representation Alignment","created":"2022-09-14","cited_by_count":74},{"id":"2206.01685","title":"Toward a realistic model of speech processing in the brain with self-supervised learning","created":"2022-06-03","cited_by_count":63},{"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":"2309.10091","title":"Unified Coarse-to-Fine Alignment for Video-Text Retrieval","created":"2023-09-18","cited_by_count":49},{"id":"2304.03195","title":"Micron-BERT: BERT-based Facial Micro-Expression Recognition","created":"2023-04-06","cited_by_count":43},{"id":"2206.11417","title":"Self-Supervised Learning of Brain Dynamics from Broad Neuroimaging Data","created":"2022-06-22","cited_by_count":39},{"id":"2301.03198","title":"The Algonauts Project 2023 Challenge: How the Human Brain Makes Sense of Natural Scenes","created":"2023-01-09","cited_by_count":36},{"id":"2307.05916","title":"SwiFT: Swin 4D fMRI Transformer","created":"2023-07-12","cited_by_count":36},{"id":"2309.07911","title":"Disentangling Spatial and Temporal Learning for Efficient Image-to-Video Transfer Learning","created":"2023-09-14","cited_by_count":32},{"id":"2311.15206","title":"Insect-Foundation: A Foundation Model and Large-scale 1M Dataset for Visual Insect Understanding","created":"2023-11-26","cited_by_count":29},{"id":"2107.14344","title":"Towards robust vision by multi-task learning on monkey visual cortex","created":"2021-07-29","cited_by_count":28},{"id":"2206.09398","title":"Aligning individual brains with Fused Unbalanced Gromov-Wasserstein","created":"2022-06-19","cited_by_count":23},{"id":"2204.09151","title":"Multi-Camera Multiple 3D Object Tracking on the Move for Autonomous Vehicles","created":"2022-04-19","cited_by_count":20},{"id":"1703.05463","title":"Using Human Brain Activity to Guide Machine Learning","created":"2017-03-16","cited_by_count":15},{"id":"2205.15948","title":"Two-Dimensional Quantum Material Identification via Self-Attention and Soft-labeling in Deep Learning","created":"2022-05-31","cited_by_count":15},{"id":"2205.10738","title":"OTAdapt: Optimal Transport-based Approach For Unsupervised Domain Adaptation","created":"2022-05-22","cited_by_count":12},{"id":"2308.00262","title":"The Algonauts Project 2023 Challenge: UARK-UAlbany Team Solution","created":"2023-08-01","cited_by_count":11},{"id":"2304.07408","title":"Fairness in Visual Clustering: A Novel Transformer Clustering Approach","created":"2023-04-14","cited_by_count":10},{"id":"2301.00345","title":"MTNeuro: A Benchmark for Evaluating Representations of Brain Structure Across Multiple Levels of Abstraction","created":"2023-01-01","cited_by_count":7},{"id":"1905.10037","title":"Brain-mediated Transfer Learning of Convolutional Neural Networks","created":"2019-05-24","cited_by_count":5},{"id":"2206.13448","title":"Distinguishing Learning Rules with Brain Machine Interfaces","created":"2022-06-27","cited_by_count":5},{"id":"2305.11275","title":"Explaining V1 Properties with a Biologically Constrained Deep Learning Architecture","created":"2023-05-18","cited_by_count":4},{"id":"2401.07669","title":"SRL-CLIP: Efficient CLIP Video Adaptation via Structured Semantic Role Labels","created":"2024-01-15","cited_by_count":4},{"id":"2402.16774","title":"Video-Based Autism Detection with Deep Learning","created":"2024-02-26","cited_by_count":2}],"next_cursor":null}