{"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"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":"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":"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":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"2004.04906","title":"Dense Passage Retrieval for Open-Domain Question Answering","created":"2020-04-10","cited_by_count":3824},{"id":"2112.10741","title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","created":"2021-12-20","cited_by_count":3614},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"2305.06500","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","created":"2023-05-11","cited_by_count":2876},{"id":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"id":"2307.06281","title":"MMBench: Is Your Multi-modal Model an All-around Player?","created":"2023-07-12","cited_by_count":2141},{"id":"2311.16502","title":"MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI","created":"2023-11-27","cited_by_count":2080},{"id":"2205.01917","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","created":"2022-05-04","cited_by_count":1274},{"id":"2004.12832","title":"ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT","created":"2020-04-27","cited_by_count":1178},{"id":"2212.07143","title":"Reproducible scaling laws for contrastive language-image learning","created":"2022-12-14","cited_by_count":1173},{"id":"2311.12983","title":"GAIA: a benchmark for General AI Assistants","created":"2023-11-21","cited_by_count":1128},{"id":"1511.07247","title":"NetVLAD: CNN architecture for weakly supervised place recognition","created":"2015-11-23","cited_by_count":941},{"id":"2307.16125","title":"SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension","created":"2023-07-30","cited_by_count":940},{"id":"2111.14818","title":"Blended Diffusion for Text-driven Editing of Natural Images","created":"2021-11-29","cited_by_count":927},{"id":"2304.06364","title":"AGIEval: A Human-Centric Benchmark for Evaluating Foundation Models","created":"2023-04-13","cited_by_count":716},{"id":"2407.07726","title":"PaliGemma: A versatile 3B VLM for transfer","created":"2024-07-10","cited_by_count":696},{"id":"2312.07533","title":"VILA: On Pre-training for Visual Language Models","created":"2023-12-12","cited_by_count":692},{"id":"1901.04085","title":"Passage Re-ranking with BERT","created":"2019-01-13","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":"2210.01936","title":"When and why vision-language models behave like bags-of-words, and what to do about it?","created":"2022-10-04","cited_by_count":610},{"id":"2004.01804","title":"Google Landmarks Dataset v2 -- A Large-Scale Benchmark for Instance-Level Recognition and Retrieval","created":"2020-04-03","cited_by_count":309},{"id":"2003.07820","title":"Overview of the TREC 2019 deep learning track","created":"2020-03-17","cited_by_count":286},{"id":"2309.17425","title":"Data Filtering Networks","created":"2023-09-29","cited_by_count":250},{"id":"2306.14610","title":"SugarCrepe: Fixing Hackable Benchmarks for Vision-Language Compositionality","created":"2023-06-26","cited_by_count":243},{"id":"2211.14305","title":"SpaText: Spatio-Textual Representation for Controllable Image Generation","created":"2022-11-25","cited_by_count":217},{"id":"2306.09265","title":"LVLM-eHub: A Comprehensive Evaluation Benchmark for Large Vision-Language Models","created":"2023-06-15","cited_by_count":217},{"id":"2102.07662","title":"Overview of the TREC 2020 deep learning track","created":"2021-02-15","cited_by_count":196},{"id":"2111.12233","title":"Scaling Up Vision-Language Pre-training for Image Captioning","created":"2021-11-24","cited_by_count":196},{"id":"2405.17247","title":"An Introduction to Vision-Language Modeling","created":"2024-05-27","cited_by_count":178},{"id":"2306.06687","title":"LAMM: Language-Assisted Multi-Modal Instruction-Tuning Dataset, Framework, and Benchmark","created":"2023-06-11","cited_by_count":169},{"id":"2103.16483","title":"Benchmarking Representation Learning for Natural World Image Collections","created":"2021-03-30","cited_by_count":168},{"id":"2311.18803","title":"BioCLIP: A Vision Foundation Model for the Tree of Life","created":"2023-11-30","cited_by_count":161},{"id":"2111.06119","title":"Fine-Grained Image Analysis with Deep Learning: A Survey","created":"2021-11-11","cited_by_count":135},{"id":"2308.12213","title":"CLIPN for Zero-Shot OOD Detection: Teaching CLIP to Say No","created":"2023-08-23","cited_by_count":130},{"id":"2306.09224","title":"Encyclopedic VQA: Visual questions about detailed properties of fine-grained categories","created":"2023-06-15","cited_by_count":107},{"id":"2304.01008","title":"Self-Supervised Multimodal Learning: A Survey","created":"2023-03-31","cited_by_count":58},{"id":"2305.03689","title":"COLA: A Benchmark for Compositional Text-to-image Retrieval","created":"2023-05-05","cited_by_count":53},{"id":"2005.00771","title":"ProtoQA: A Question Answering Dataset for Prototypical Common-Sense Reasoning","created":"2020-05-02","cited_by_count":46},{"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":"2305.14897","title":"Text encoders bottleneck compositionality in contrastive vision-language models","created":"2023-05-24","cited_by_count":34},{"id":"2404.08071","title":"Overview of the TREC 2023 NeuCLIR Track","created":"2024-04-11","cited_by_count":17},{"id":"2306.16048","title":"Benchmarking Zero-Shot Recognition with Vision-Language Models: Challenges on Granularity and Specificity","created":"2023-06-28","cited_by_count":14}],"next_cursor":null}