{"list":"other","total":51,"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":"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":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"1502.01852","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","created":"2015-02-06","cited_by_count":3611},{"id":"1903.12261","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","created":"2019-03-28","cited_by_count":2877},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"2203.05557","title":"Conditional Prompt Learning for Vision-Language Models","created":"2022-03-10","cited_by_count":1433},{"id":"2006.15055","title":"Object-Centric Learning with Slot Attention","created":"2020-06-26","cited_by_count":876},{"id":"1710.09829","title":"Dynamic Routing Between Capsules","created":"2017-10-26","cited_by_count":689},{"id":"2404.19756","title":"KAN: Kolmogorov-Arnold Networks","created":"2024-04-30","cited_by_count":649},{"id":"2104.06405","title":"BARF: Bundle-Adjusting Neural Radiance Fields","created":"2021-04-13","cited_by_count":642},{"id":"2202.11094","title":"GroupViT: Semantic Segmentation Emerges from Text Supervision","created":"2022-02-22","cited_by_count":531},{"id":"2203.13591","title":"Continual Test-Time Domain Adaptation","created":"2022-03-25","cited_by_count":525},{"id":"2304.15004","title":"Are Emergent Abilities of Large Language Models a Mirage?","created":"2023-04-28","cited_by_count":523},{"id":"2006.16971","title":"Improving robustness against common corruptions by covariate shift adaptation","created":"2020-06-30","cited_by_count":431},{"id":"2209.07511","title":"Test-Time Prompt Tuning for Zero-Shot Generalization in Vision-Language Models","created":"2022-09-15","cited_by_count":382},{"id":"2305.17333","title":"Fine-Tuning Language Models with Just Forward Passes","created":"2023-05-27","cited_by_count":345},{"id":"2112.05814","title":"Deep ViT Features as Dense Visual Descriptors","created":"2021-12-10","cited_by_count":330},{"id":"2212.13345","title":"The Forward-Forward Algorithm: Some Preliminary Investigations","created":"2022-12-27","cited_by_count":266},{"id":"1404.5997","title":"One weird trick for parallelizing convolutional neural networks","created":"2014-04-23","cited_by_count":264},{"id":"2209.07522","title":"Test-Time Training with Masked Autoencoders","created":"2022-09-15","cited_by_count":212},{"id":"2303.13899","title":"Robust Test-Time Adaptation in Dynamic Scenarios","created":"2023-03-24","cited_by_count":189},{"id":"2208.05117","title":"NOTE: Robust Continual Test-time Adaptation Against Temporal Correlation","created":"2022-08-10","cited_by_count":151},{"id":"2303.14536","title":"SUDS: Scalable Urban Dynamic Scenes","created":"2023-03-25","cited_by_count":151},{"id":"2102.12627","title":"How to represent part-whole hierarchies in a neural network","created":"2021-02-25","cited_by_count":123},{"id":"1709.08568","title":"The Consciousness Prior","created":"2017-09-25","cited_by_count":107},{"id":"2107.07905","title":"Unsupervised Discovery of Object Radiance Fields","created":"2021-07-16","cited_by_count":101},{"id":"2207.10661","title":"In Defense of Online Models for Video Instance Segmentation","created":"2022-07-21","cited_by_count":97},{"id":"1905.11786","title":"Putting An End to End-to-End: Gradient-Isolated Learning of Representations","created":"2019-05-28","cited_by_count":86},{"id":"2310.10074","title":"SoTTA: Robust Test-Time Adaptation on Noisy Data Streams","created":"2023-10-16","cited_by_count":63},{"id":"2405.03770","title":"Foundation Models for Video Understanding: A Survey","created":"2024-05-06","cited_by_count":46},{"id":"2204.02075","title":"Complex-Valued Autoencoders for Object Discovery","created":"2022-04-05","cited_by_count":40},{"id":"2306.00600","title":"Rotating Features for Object Discovery","created":"2023-06-01","cited_by_count":29},{"id":"2311.16102","title":"Diffusion-TTA: Test-time Adaptation of Discriminative Models via Generative Feedback","created":"2023-11-27","cited_by_count":27},{"id":"2403.02628","title":"Interactive Continual Learning: Fast and Slow Thinking","created":"2024-03-05","cited_by_count":23},{"id":"2312.08010","title":"EZ-CLIP: Efficient Zeroshot Video Action Recognition","created":"2023-12-13","cited_by_count":14},{"id":"2204.07892","title":"Video Action Detection: Analysing Limitations and Challenges","created":"2022-04-17","cited_by_count":12},{"id":"2203.03282","title":"Interpretable part-whole hierarchies and conceptual-semantic relationships in neural networks","created":"2022-03-07","cited_by_count":11},{"id":"2410.19553","title":"On Occlusions in Video Action Detection: Benchmark Datasets And Training Recipes","created":"2024-10-25","cited_by_count":6}],"next_cursor":null}