{"list":"other","total":56,"rows":[{"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":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"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":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"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":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"1602.07332","title":"Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations","created":"2016-02-23","cited_by_count":2656},{"id":"1504.00325","title":"Microsoft COCO Captions: Data Collection and Evaluation Server","created":"2015-04-01","cited_by_count":1462},{"id":"1907.07174","title":"Natural Adversarial Examples","created":"2019-07-16","cited_by_count":1408},{"id":"1505.04870","title":"Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models","created":"2015-05-19","cited_by_count":1362},{"id":"2212.07143","title":"Reproducible scaling laws for contrastive language-image learning","created":"2022-12-14","cited_by_count":1173},{"id":"2112.03857","title":"Grounded Language-Image Pre-training","created":"2021-12-07","cited_by_count":1156},{"id":"2311.12793","title":"ShareGPT4V: Improving Large Multi-Modal Models with Better Captions","created":"2023-11-21","cited_by_count":1005},{"id":"2104.13921","title":"Open-vocabulary Object Detection via Vision and Language Knowledge Distillation","created":"2021-04-28","cited_by_count":906},{"id":"2306.15195","title":"Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic","created":"2023-06-27","cited_by_count":906},{"id":"2310.00426","title":"PixArt-$\\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis","created":"2023-09-30","cited_by_count":864},{"id":"2304.00685","title":"Vision-Language Models for Vision Tasks: A Survey","created":"2023-04-03","cited_by_count":839},{"id":"2303.15389","title":"EVA-CLIP: Improved Training Techniques for CLIP at Scale","created":"2023-03-27","cited_by_count":798},{"id":"2201.03546","title":"Language-driven Semantic Segmentation","created":"2022-01-10","cited_by_count":717},{"id":"2111.07783","title":"FILIP: Fine-grained Interactive Language-Image Pre-Training","created":"2021-11-09","cited_by_count":627},{"id":"2403.17297","title":"InternLM2 Technical Report","created":"2024-03-26","cited_by_count":397},{"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":"2109.14279","title":"Localizing Objects with Self-Supervised Transformers and no Labels","created":"2021-09-29","cited_by_count":230},{"id":"2305.20088","title":"Improving CLIP Training with Language Rewrites","created":"2023-05-31","cited_by_count":217},{"id":"2208.12262","title":"MaskCLIP: Masked Self-Distillation Advances Contrastive Language-Image Pretraining","created":"2022-08-25","cited_by_count":187},{"id":"2212.03588","title":"ZegCLIP: Towards Adapting CLIP for Zero-shot Semantic Segmentation","created":"2022-12-07","cited_by_count":178},{"id":"2312.03818","title":"Alpha-CLIP: A CLIP Model Focusing on Wherever You Want","created":"2023-12-06","cited_by_count":151},{"id":"2212.04994","title":"Open Vocabulary Semantic Segmentation with Patch Aligned Contrastive Learning","created":"2022-12-09","cited_by_count":115},{"id":"2408.04883","title":"ProxyCLIP: Proxy Attention Improves CLIP for Open-Vocabulary Segmentation","created":"2024-08-09","cited_by_count":111},{"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":"2310.20550","title":"CapsFusion: Rethinking Image-Text Data at Scale","created":"2023-10-31","cited_by_count":90},{"id":"2403.17007","title":"DreamLIP: Language-Image Pre-training with Long Captions","created":"2024-03-25","cited_by_count":72},{"id":"2310.07699","title":"VeCLIP: Improving CLIP Training via Visual-enriched Captions","created":"2023-10-11","cited_by_count":70},{"id":"2507.07095","title":"Go to Zero: Towards Zero-shot Motion Generation with Million-scale Data","created":"2025-07-09","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":"2405.02793","title":"ImageInWords: Unlocking Hyper-Detailed Image Descriptions","created":"2024-05-05","cited_by_count":57},{"id":"2412.03561","title":"FLAIR: VLM with Fine-grained Language-informed Image Representations","created":"2024-12-04","cited_by_count":48},{"id":"2504.02261","title":"WonderTurbo: Generating Interactive 3D World in 0.72 Seconds","created":"2025-04-03","cited_by_count":32},{"id":"2212.09737","title":"Position-guided Text Prompt for Vision-Language Pre-training","created":"2022-12-19","cited_by_count":27},{"id":"2410.05249","title":"LoTLIP: Improving Language-Image Pre-training for Long Text Understanding","created":"2024-10-07","cited_by_count":27},{"id":"2503.20672","title":"BizGen: Advancing Article-level Visual Text Rendering for Infographics Generation","created":"2025-03-26","cited_by_count":20},{"id":"2410.10034","title":"TULIP: Token-length Upgraded CLIP","created":"2024-10-13","cited_by_count":19},{"id":"2406.00670","title":"Cascade-CLIP: Cascaded Vision-Language Embeddings Alignment for Zero-Shot Semantic Segmentation","created":"2024-06-02","cited_by_count":17},{"id":"2505.22523","title":"PrismLayers: Open Data for High-Quality Multi-Layer Transparent Image Generative Models","created":"2025-05-28","cited_by_count":15},{"id":"2401.06397","title":"UMG-CLIP: A Unified Multi-Granularity Vision Generalist for Open-World Understanding","created":"2024-01-12","cited_by_count":13},{"id":"2503.06505","title":"DynamicID: Zero-Shot Multi-ID Image Personalization with Flexible Facial Editability","created":"2025-03-09","cited_by_count":10},{"id":"2507.04547","title":"FB-Diff: Fourier Basis-guided Diffusion for Temporal Interpolation of 4D Medical Imaging","created":"2025-07-06","cited_by_count":6},{"id":"2505.17333","title":"Temporal Differential Fields for 4D Motion Modeling via Image-to-Video Synthesis","created":"2025-05-22","cited_by_count":3},{"id":"2409.08206","title":"ComAlign: Compositional Alignment in Vision-Language Models","created":"2024-09-12","cited_by_count":1}],"next_cursor":null}