{"list":"other","total":55,"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":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1301.3781","title":"Efficient Estimation of Word Representations in Vector Space","created":"2013-01-16","cited_by_count":4375},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"2101.00190","title":"Prefix-Tuning: Optimizing Continuous Prompts for Generation","created":"2021-01-01","cited_by_count":3915},{"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":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"1311.2524","title":"Rich feature hierarchies for accurate object detection and semantic segmentation","created":"2013-11-11","cited_by_count":2162},{"id":"1409.7495","title":"Unsupervised Domain Adaptation by Backpropagation","created":"2014-09-26","cited_by_count":1917},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"id":"2112.03857","title":"Grounded Language-Image Pre-training","created":"2021-12-07","cited_by_count":1156},{"id":"2110.04544","title":"CLIP-Adapter: Better Vision-Language Models with Feature Adapters","created":"2021-10-09","cited_by_count":1026},{"id":"2104.13921","title":"Open-vocabulary Object Detection via Vision and Language Knowledge Distillation","created":"2021-04-28","cited_by_count":906},{"id":"2201.03546","title":"Language-driven Semantic Segmentation","created":"2022-01-10","cited_by_count":717},{"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":"2112.01518","title":"DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting","created":"2021-12-02","cited_by_count":532},{"id":"2202.11094","title":"GroupViT: Semantic Segmentation Emerges from Text Supervision","created":"2022-02-22","cited_by_count":531},{"id":"2112.02413","title":"PointCLIP: Point Cloud Understanding by CLIP","created":"2021-12-04","cited_by_count":463},{"id":"2005.00052","title":"MAD-X: An Adapter-Based Framework for Multi-Task Cross-Lingual Transfer","created":"2020-04-30","cited_by_count":445},{"id":"2111.03930","title":"Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modeling","created":"2021-11-06","cited_by_count":431},{"id":"2106.13043","title":"AudioCLIP: Extending CLIP to Image, Text and Audio","created":"2021-06-24","cited_by_count":339},{"id":"2109.08472","title":"ActionCLIP: A New Paradigm for Video Action Recognition","created":"2021-09-17","cited_by_count":320},{"id":"1712.00981","title":"Feature Generating Networks for Zero-Shot Learning","created":"2017-12-04","cited_by_count":257},{"id":"2201.03514","title":"Black-Box Tuning for Language-Model-as-a-Service","created":"2022-01-10","cited_by_count":256},{"id":"1903.10132","title":"f-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learning","created":"2019-03-25","cited_by_count":164},{"id":"2302.03024","title":"AIM: Adapting Image Models for Efficient Video Action Recognition","created":"2023-02-06","cited_by_count":148},{"id":"1704.08345","title":"Semantic Autoencoder for Zero-Shot Learning","created":"2017-04-26","cited_by_count":133},{"id":"1712.03878","title":"Generalized Zero-Shot Learning via Synthesized Examples","created":"2017-12-11","cited_by_count":114},{"id":"2108.05988","title":"TVT: Transferable Vision Transformer for Unsupervised Domain Adaptation","created":"2021-08-12","cited_by_count":81},{"id":"1904.03451","title":"Doodle to Search: Practical Zero-Shot Sketch-based Image Retrieval","created":"2019-04-06","cited_by_count":79},{"id":"2303.13440","title":"CLIP for All Things Zero-Shot Sketch-Based Image Retrieval, Fine-Grained or Not","created":"2023-03-23","cited_by_count":79},{"id":"1509.04767","title":"Zero-Shot Learning via Semantic Similarity Embedding","created":"2015-09-15","cited_by_count":74},{"id":"1807.11724","title":"A Zero-Shot Framework for Sketch-based Image Retrieval","created":"2018-07-31","cited_by_count":71},{"id":"1703.05605","title":"Deep Sketch Hashing: Fast Free-hand Sketch-Based Image Retrieval","created":"2017-03-16","cited_by_count":68},{"id":"1712.01928","title":"Zero-Shot Visual Recognition using Semantics-Preserving Adversarial Embedding Networks","created":"2017-12-05","cited_by_count":66},{"id":"1908.05832","title":"Transferable Contrastive Network for Generalized Zero-Shot Learning","created":"2019-08-16","cited_by_count":64},{"id":"1903.03372","title":"Semantically Tied Paired Cycle Consistency for Zero-Shot Sketch-based Image Retrieval","created":"2019-03-08","cited_by_count":57},{"id":"2103.15706","title":"StyleMeUp: Towards Style-Agnostic Sketch-Based Image Retrieval","created":"2021-03-29","cited_by_count":50},{"id":"1803.02284","title":"Zero-Shot Sketch-Image Hashing","created":"2018-03-06","cited_by_count":43},{"id":"1904.03208","title":"Semantic-Aware Knowledge Preservation for Zero-Shot Sketch-Based Image Retrieval","created":"2019-04-05","cited_by_count":40},{"id":"2103.13990","title":"More Photos are All You Need: Semi-Supervised Learning for Fine-Grained Sketch Based Image Retrieval","created":"2021-03-25","cited_by_count":38},{"id":"2203.14691","title":"Sketch3T: Test-Time Training for Zero-Shot SBIR","created":"2022-03-28","cited_by_count":34},{"id":"2303.14348","title":"Zero-Shot Everything Sketch-Based Image Retrieval, and in Explainable Style","created":"2023-03-25","cited_by_count":25},{"id":"1711.05820","title":"Zero-Shot Learning via Class-Conditioned Deep Generative Models","created":"2017-11-15","cited_by_count":21},{"id":"2102.04016","title":"An Efficient Framework for Zero-Shot Sketch-Based Image Retrieval","created":"2021-02-08","cited_by_count":15},{"id":"2111.00667","title":"Unsupervised Domain Adaptation with Adapter","created":"2021-11-01","cited_by_count":14},{"id":"2106.11841","title":"Domain-Smoothing Network for Zero-Shot Sketch-Based Image Retrieval","created":"2021-06-22","cited_by_count":13},{"id":"2003.09869","title":"Progressive Domain-Independent Feature Decomposition Network for Zero-Shot Sketch-Based Image Retrieval","created":"2020-03-22","cited_by_count":10},{"id":"2204.05666","title":"Three-Stream Joint Network for Zero-Shot Sketch-Based Image Retrieval","created":"2022-04-12","cited_by_count":2}],"next_cursor":null}