{"list":"other","total":70,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"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":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2409.12191","title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","created":"2024-09-18","cited_by_count":4234},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"2111.02114","title":"LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs","created":"2021-11-03","cited_by_count":1555},{"id":"1504.00325","title":"Microsoft COCO Captions: Data Collection and Evaluation Server","created":"2015-04-01","cited_by_count":1462},{"id":"1906.07155","title":"MMDetection: Open MMLab Detection Toolbox and Benchmark","created":"2019-06-17","cited_by_count":1385},{"id":"2205.01917","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","created":"2022-05-04","cited_by_count":1274},{"id":"1807.10221","title":"Unified Perceptual Parsing for Scene Understanding","created":"2018-07-26","cited_by_count":1271},{"id":"2502.14786","title":"SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features","created":"2025-02-20","cited_by_count":1188},{"id":"1412.2306","title":"Deep Visual-Semantic Alignments for Generating Image Descriptions","created":"2014-12-07","cited_by_count":968},{"id":"2303.15389","title":"EVA-CLIP: Improved Training Techniques for CLIP at Scale","created":"2023-03-27","cited_by_count":798},{"id":"2109.01903","title":"Robust fine-tuning of zero-shot models","created":"2021-09-04","cited_by_count":797},{"id":"2211.07636","title":"EVA: Exploring the Limits of Masked Visual Representation Learning at Scale","created":"2022-11-14","cited_by_count":691},{"id":"1901.02446","title":"Panoptic Feature Pyramid Networks","created":"2019-01-08","cited_by_count":645},{"id":"2304.14108","title":"DataComp: In search of the next generation of multimodal datasets","created":"2023-04-27","cited_by_count":644},{"id":"2205.08534","title":"Vision Transformer Adapter for Dense Predictions","created":"2022-05-17","cited_by_count":565},{"id":"2211.05778","title":"InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions","created":"2022-11-10","cited_by_count":482},{"id":"2112.12750","title":"SLIP: Self-supervision meets Language-Image Pre-training","created":"2021-12-23","cited_by_count":436},{"id":"2110.05208","title":"Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm","created":"2021-10-11","cited_by_count":405},{"id":"2303.11331","title":"EVA-02: A Visual Representation for Neon Genesis","created":"2023-03-20","cited_by_count":381},{"id":"2212.00794","title":"Scaling Language-Image Pre-training via Masking","created":"2022-12-01","cited_by_count":317},{"id":"2403.15378","title":"Long-CLIP: Unlocking the Long-Text Capability of CLIP","created":"2024-03-22","cited_by_count":300},{"id":"2309.16671","title":"Demystifying CLIP Data","created":"2023-09-28","cited_by_count":270},{"id":"2106.05237","title":"Knowledge distillation: A good teacher is patient and consistent","created":"2021-06-09","cited_by_count":259},{"id":"2309.17425","title":"Data Filtering Networks","created":"2023-09-29","cited_by_count":250},{"id":"2305.20088","title":"Improving CLIP Training with Language Rewrites","created":"2023-05-31","cited_by_count":217},{"id":"1411.2539","title":"Unifying Visual-Semantic Embeddings with Multimodal Neural Language Models","created":"2014-11-10","cited_by_count":198},{"id":"2303.14189","title":"FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization","created":"2023-03-24","cited_by_count":162},{"id":"2404.19753","title":"DOCCI: Descriptions of Connected and Contrasting Images","created":"2024-04-30","cited_by_count":132},{"id":"2101.05022","title":"Re-labeling ImageNet: from Single to Multi-Labels, from Global to Localized Labels","created":"2021-01-13","cited_by_count":118},{"id":"2206.04040","title":"MobileOne: An Improved One millisecond Mobile Backbone","created":"2022-06-08","cited_by_count":109},{"id":"2312.08578","title":"A Picture is Worth More Than 77 Text Tokens: Evaluating CLIP-Style Models on Dense Captions","created":"2023-12-14","cited_by_count":108},{"id":"2311.17049","title":"MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training","created":"2023-11-28","cited_by_count":96},{"id":"2307.10350","title":"Improving Multimodal Datasets with Image Captioning","created":"2023-07-19","cited_by_count":93},{"id":"2309.12314","title":"TinyCLIP: CLIP Distillation via Affinity Mimicking and Weight Inheritance","created":"2023-09-21","cited_by_count":90},{"id":"2406.08478","title":"What If We Recaption Billions of Web Images with LLaMA-3?","created":"2024-06-12","cited_by_count":87},{"id":"2305.07017","title":"An Inverse Scaling Law for CLIP Training","created":"2023-05-11","cited_by_count":77},{"id":"2404.07177","title":"Scaling Laws for Data Filtering -- Data Curation cannot be Compute Agnostic","created":"2024-04-10","cited_by_count":77},{"id":"2412.13303","title":"FastVLM: Efficient Vision Encoding for Vision Language Models","created":"2024-12-17","cited_by_count":77},{"id":"2403.17007","title":"DreamLIP: Language-Image Pre-training with Long Captions","created":"2024-03-25","cited_by_count":72},{"id":"2308.08428","title":"ALIP: Adaptive Language-Image Pre-training with Synthetic Caption","created":"2023-08-16","cited_by_count":70},{"id":"2303.13496","title":"The effectiveness of MAE pre-pretraining for billion-scale pretraining","created":"2023-03-23","cited_by_count":68},{"id":"2402.01832","title":"SynthCLIP: Are We Ready for a Fully Synthetic CLIP Training?","created":"2024-02-02","cited_by_count":64},{"id":"2305.17530","title":"PuMer: Pruning and Merging Tokens for Efficient Vision Language Models","created":"2023-05-27","cited_by_count":53},{"id":"2112.01528","title":"A Fast Knowledge Distillation Framework for Visual Recognition","created":"2021-12-02","cited_by_count":50},{"id":"2209.03917","title":"Exploring Target Representations for Masked Autoencoders","created":"2022-09-08","cited_by_count":46},{"id":"2406.17711","title":"Data curation via joint example selection further accelerates multimodal learning","created":"2024-06-25","cited_by_count":33},{"id":"2201.05729","title":"CLIP-TD: CLIP Targeted Distillation for Vision-Language Tasks","created":"2022-01-15","cited_by_count":32},{"id":"2312.05328","title":"Bad Students Make Great Teachers: Active Learning Accelerates Large-Scale Visual Understanding","created":"2023-12-08","cited_by_count":28},{"id":"2204.10496","title":"Multimodal Adaptive Distillation for Leveraging Unimodal Encoders for Vision-Language Tasks","created":"2022-04-22","cited_by_count":23},{"id":"2411.16828","title":"CLIPS: An Enhanced CLIP Framework for Learning with Synthetic Captions","created":"2024-11-25","cited_by_count":22},{"id":"2410.10034","title":"TULIP: Token-length Upgraded CLIP","created":"2024-10-13","cited_by_count":19},{"id":"2405.13777","title":"No Filter: Cultural and Socioeconomic Diversity in Contrastive Vision-Language Models","created":"2024-05-22","cited_by_count":16},{"id":"2405.16915","title":"Multilingual Diversity Improves Vision-Language Representations","created":"2024-05-27","cited_by_count":14},{"id":"2303.08983","title":"Reinforce Data, Multiply Impact: Improved Model Accuracy and Robustness with Dataset Reinforcement","created":"2023-03-15","cited_by_count":11},{"id":"2301.06958","title":"RILS: Masked Visual Reconstruction in Language Semantic Space","created":"2023-01-17","cited_by_count":10},{"id":"2404.15653","title":"CatLIP: CLIP-level Visual Recognition Accuracy with 2.7x Faster Pre-training on Web-scale Image-Text Data","created":"2024-04-24","cited_by_count":10},{"id":"2405.08911","title":"CLIP with Quality Captions: A Strong Pretraining for Vision Tasks","created":"2024-05-14","cited_by_count":7},{"id":"2407.06723","title":"Graph-Based Captioning: Enhancing Visual Descriptions by Interconnecting Region Captions","created":"2024-07-09","cited_by_count":7}],"next_cursor":null}