{"list":"other","total":54,"rows":[{"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"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":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"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":"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":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"id":"2104.08821","title":"SimCSE: Simple Contrastive Learning of Sentence Embeddings","created":"2021-04-18","cited_by_count":2173},{"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":"1906.00067","title":"OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge","created":"2019-05-31","cited_by_count":1121},{"id":"2311.12793","title":"ShareGPT4V: Improving Large Multi-Modal Models with Better Captions","created":"2023-11-21","cited_by_count":1005},{"id":"2308.00692","title":"LISA: Reasoning Segmentation via Large Language Model","created":"2023-08-01","cited_by_count":776},{"id":"2407.07895","title":"LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models","created":"2024-07-10","cited_by_count":584},{"id":"2305.11175","title":"VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks","created":"2023-05-18","cited_by_count":501},{"id":"2307.06942","title":"InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation","created":"2023-07-13","cited_by_count":497},{"id":"2212.03191","title":"InternVideo: General Video Foundation Models via Generative and Discriminative Learning","created":"2022-12-06","cited_by_count":447},{"id":"1611.08669","title":"Visual Dialog","created":"2016-11-26","cited_by_count":377},{"id":"2403.15377","title":"InternVideo2: Scaling Foundation Models for Multimodal Video Understanding","created":"2024-03-22","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":"2407.05282","title":"UltraEdit: Instruction-based Fine-Grained Image Editing at Scale","created":"2024-07-07","cited_by_count":268},{"id":"2108.04024","title":"Image Retrieval on Real-life Images with Pre-trained Vision-and-Language Models","created":"2021-08-09","cited_by_count":251},{"id":"2306.14610","title":"SugarCrepe: Fixing Hackable Benchmarks for Vision-Language Compositionality","created":"2023-06-26","cited_by_count":243},{"id":"2302.11713","title":"Can Pre-trained Vision and Language Models Answer Visual Information-Seeking Questions?","created":"2023-02-23","cited_by_count":207},{"id":"2303.16058","title":"Unmasked Teacher: Towards Training-Efficient Video Foundation Models","created":"2023-03-28","cited_by_count":199},{"id":"1604.03968","title":"Visual Storytelling","created":"2016-04-13","cited_by_count":176},{"id":"2303.15247","title":"Zero-Shot Composed Image Retrieval with Textual Inversion","created":"2023-03-27","cited_by_count":176},{"id":"2407.02392","title":"TokenPacker: Efficient Visual Projector for Multimodal LLM","created":"2024-07-02","cited_by_count":172},{"id":"2311.17136","title":"UniIR: Training and Benchmarking Universal Multimodal Information Retrievers","created":"2023-11-28","cited_by_count":166},{"id":"2403.19651","title":"MagicLens: Self-Supervised Image Retrieval with Open-Ended Instructions","created":"2024-03-28","cited_by_count":119},{"id":"2302.11154","title":"Open-domain Visual Entity Recognition: Towards Recognizing Millions of Wikipedia Entities","created":"2023-02-22","cited_by_count":113},{"id":"2305.14167","title":"DetGPT: Detect What You Need via Reasoning","created":"2023-05-23","cited_by_count":112},{"id":"2306.09224","title":"Encyclopedic VQA: Visual questions about detailed properties of fine-grained categories","created":"2023-06-15","cited_by_count":107},{"id":"2402.04252","title":"EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters","created":"2024-02-06","cited_by_count":99},{"id":"2007.12163","title":"Smooth-AP: Smoothing the Path Towards Large-Scale Image Retrieval","created":"2020-07-23","cited_by_count":98},{"id":"2103.16553","title":"Thinking Fast and Slow: Efficient Text-to-Visual Retrieval with Transformers","created":"2021-03-30","cited_by_count":93},{"id":"2307.16645","title":"Scaling Sentence Embeddings with Large Language Models","created":"2023-07-31","cited_by_count":85},{"id":"2310.05473","title":"Sentence-level Prompts Benefit Composed Image Retrieval","created":"2023-10-09","cited_by_count":59},{"id":"2309.17133","title":"Fine-grained Late-interaction Multi-modal Retrieval for Retrieval Augmented Visual Question Answering","created":"2023-09-29","cited_by_count":51},{"id":"2306.07969","title":"GeneCIS: A Benchmark for General Conditional Image Similarity","created":"2023-06-13","cited_by_count":47},{"id":"2403.20312","title":"Learn \"No\" to Say \"Yes\" Better: Improving Vision-Language Models via Negations","created":"2024-03-29","cited_by_count":46},{"id":"2406.20092","title":"Efficient Large Multi-modal Models via Visual Context Compression","created":"2024-06-28","cited_by_count":46},{"id":"2402.08327","title":"PreFLMR: Scaling Up Fine-Grained Late-Interaction Multi-modal Retrievers","created":"2024-02-13","cited_by_count":42},{"id":"2406.18530","title":"MatchTime: Towards Automatic Soccer Game Commentary Generation","created":"2024-06-26","cited_by_count":37},{"id":"2408.12957","title":"Image Segmentation in Foundation Model Era: A Survey","created":"2024-08-23","cited_by_count":35},{"id":"2306.07272","title":"Zero-shot Composed Text-Image Retrieval","created":"2023-06-12","cited_by_count":32},{"id":"2106.04128","title":"Conversational Fashion Image Retrieval via Multiturn Natural Language Feedback","created":"2021-06-08","cited_by_count":29},{"id":"2310.19001","title":"Uncovering Prototypical Knowledge for Weakly Open-Vocabulary Semantic Segmentation","created":"2023-10-29","cited_by_count":27}],"next_cursor":null}