{"list":"other","total":64,"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":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"id":"1411.7766","title":"Deep Learning Face Attributes in the Wild","created":"2014-11-28","cited_by_count":3693},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"2107.13586","title":"Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing","created":"2021-07-28","cited_by_count":2234},{"id":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"id":"2203.05557","title":"Conditional Prompt Learning for Vision-Language Models","created":"2022-03-10","cited_by_count":1433},{"id":"1908.03557","title":"VisualBERT: A Simple and Performant Baseline for Vision and Language","created":"2019-08-09","cited_by_count":1296},{"id":"2004.06165","title":"Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks","created":"2020-04-13","cited_by_count":1214},{"id":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175},{"id":"2110.04544","title":"CLIP-Adapter: Better Vision-Language Models with Feature Adapters","created":"2021-10-09","cited_by_count":1026},{"id":"2112.02413","title":"PointCLIP: Point Cloud Understanding by CLIP","created":"2021-12-04","cited_by_count":463},{"id":"2111.03930","title":"Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modeling","created":"2021-11-06","cited_by_count":431},{"id":"2104.11178","title":"VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text","created":"2021-04-22","cited_by_count":429},{"id":"2103.15436","title":"Transformer Tracking","created":"2021-03-29","cited_by_count":412},{"id":"2310.01852","title":"LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment","created":"2023-10-03","cited_by_count":370},{"id":"2207.09519","title":"Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classification","created":"2022-07-19","cited_by_count":362},{"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":"2212.05171","title":"ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding","created":"2022-12-10","cited_by_count":267},{"id":"2112.00374","title":"CLIPstyler: Image Style Transfer with a Single Text Condition","created":"2021-12-01","cited_by_count":203},{"id":"2305.08275","title":"ULIP-2: Towards Scalable Multimodal Pre-training for 3D Understanding","created":"2023-05-14","cited_by_count":202},{"id":"2309.00615","title":"Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D Understanding, Generation, and Instruction Following","created":"2023-09-01","cited_by_count":194},{"id":"2211.11682","title":"PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learning","created":"2022-11-21","cited_by_count":187},{"id":"2109.11797","title":"CPT: Colorful Prompt Tuning for Pre-trained Vision-Language Models","created":"2021-09-24","cited_by_count":183},{"id":"2105.03889","title":"Conformer: Local Features Coupling Global Representations for Visual Recognition","created":"2021-05-09","cited_by_count":164},{"id":"2302.10035","title":"Large-scale Multi-Modal Pre-trained Models: A Comprehensive Survey","created":"2023-02-20","cited_by_count":153},{"id":"2108.05015","title":"VisEvent: Reliable Object Tracking via Collaboration of Frame and Event Flows","created":"2021-08-11","cited_by_count":129},{"id":"2209.14169","title":"CALIP: Zero-Shot Enhancement of CLIP with Parameter-free Attention","created":"2022-09-28","cited_by_count":103},{"id":"1901.06783","title":"Dynamic Curriculum Learning for Imbalanced Data Classification","created":"2019-01-21","cited_by_count":93},{"id":"1709.09930","title":"HydraPlus-Net: Attentive Deep Features for Pedestrian Analysis","created":"2017-09-28","cited_by_count":89},{"id":"1702.05891","title":"Learning Spatial Regularization with Image-level Supervisions for Multi-label Image Classification","created":"2017-02-20","cited_by_count":85},{"id":"1807.03903","title":"Deep Imbalanced Attribute Classification using Visual Attention Aggregation","created":"2018-07-10","cited_by_count":56},{"id":"2302.14007","title":"Joint-MAE: 2D-3D Joint Masked Autoencoders for 3D Point Cloud Pre-training","created":"2023-02-27","cited_by_count":52},{"id":"1901.07474","title":"Pedestrian Attribute Recognition: A Survey","created":"2019-01-22","cited_by_count":50},{"id":"1910.04562","title":"Improving Pedestrian Attribute Recognition With Weakly-Supervised Multi-Scale Attribute-Specific Localization","created":"2019-10-10","cited_by_count":46},{"id":"2307.16634","title":"CDUL: CLIP-Driven Unsupervised Learning for Multi-Label Image Classification","created":"2023-07-31","cited_by_count":39},{"id":"1505.01197","title":"Contextual Action Recognition with R*CNN","created":"2015-05-05","cited_by_count":34},{"id":"1603.07054","title":"A Richly Annotated Dataset for Pedestrian Attribute Recognition","created":"2016-03-23","cited_by_count":33},{"id":"2109.05686","title":"Spatial and Semantic Consistency Regularizations for Pedestrian Attribute Recognition","created":"2021-09-13","cited_by_count":32},{"id":"2107.03576","title":"Rethinking of Pedestrian Attribute Recognition: A Reliable Evaluation under Zero-Shot Pedestrian Identity Setting","created":"2021-07-08","cited_by_count":27},{"id":"1709.08553","title":"Attribute Recognition by Joint Recurrent Learning of Context and Correlation","created":"2017-09-25","cited_by_count":25},{"id":"2203.04006","title":"Visual-Language Navigation Pretraining via Prompt-based Environmental Self-exploration","created":"2022-03-08","cited_by_count":25},{"id":"1311.5591","title":"PANDA: Pose Aligned Networks for Deep Attribute Modeling","created":"2013-11-21","cited_by_count":23},{"id":"2205.13125","title":"Prompt-based Learning for Unpaired Image Captioning","created":"2022-05-26","cited_by_count":23},{"id":"2002.03683","title":"Deep Multi-task Multi-label CNN for Effective Facial Attribute Classification","created":"2020-02-10","cited_by_count":22},{"id":"1601.00400","title":"Multi-task CNN Model for Attribute Prediction","created":"2016-01-04","cited_by_count":21},{"id":"2304.07230","title":"PARFormer: Transformer-based Multi-Task Network for Pedestrian Attribute Recognition","created":"2023-04-14","cited_by_count":19},{"id":"1610.03670","title":"Multi-Task Curriculum Transfer Deep Learning of Clothing Attributes","created":"2016-10-12","cited_by_count":18},{"id":"2208.08829","title":"Learning Spatial-Frequency Transformer for Visual Object Tracking","created":"2022-08-18","cited_by_count":18},{"id":"1804.06964","title":"GNAS: A Greedy Neural Architecture Search Method for Multi-Attribute Learning","created":"2018-04-19","cited_by_count":17},{"id":"1412.0069","title":"Pedestrian Detection aided by Deep Learning Semantic Tasks","created":"2014-11-29","cited_by_count":16},{"id":"1704.08740","title":"Improving Facial Attribute Prediction using Semantic Segmentation","created":"2017-04-27","cited_by_count":16},{"id":"1708.08728","title":"Curriculum Learning for Multi-Task Classification of Visual Attributes","created":"2017-08-29","cited_by_count":13},{"id":"1911.11351","title":"Distraction-Aware Feature Learning for Human Attribute Recognition via Coarse-to-Fine Attention Mechanism","created":"2019-11-26","cited_by_count":11},{"id":"1907.11837","title":"Attribute Aware Pooling for Pedestrian Attribute Recognition","created":"2019-07-27","cited_by_count":9},{"id":"2108.06946","title":"Video Person Re-identification using Attribute-enhanced Features","created":"2021-08-16","cited_by_count":7},{"id":"1608.03217","title":"DeepCAMP: Deep Convolutional Action & Attribute Mid-Level Patterns","created":"2016-08-10","cited_by_count":3}],"next_cursor":null}