{"list":"other","total":59,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"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":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"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":"2210.11416","title":"Scaling Instruction-Finetuned Language Models","created":"2022-10-20","cited_by_count":3024},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"id":"1412.6550","title":"FitNets: Hints for Thin Deep Nets","created":"2014-12-19","cited_by_count":1653},{"id":"1502.03044","title":"Show, Attend and Tell: Neural Image Caption Generation with Visual Attention","created":"2015-02-10","cited_by_count":1423},{"id":"2007.00398","title":"DocVQA: A Dataset for VQA on Document Images","created":"2020-07-01","cited_by_count":1317},{"id":"2304.14178","title":"mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality","created":"2023-04-27","cited_by_count":1040},{"id":"2111.14818","title":"Blended Diffusion for Text-driven Editing of Natural Images","created":"2021-11-29","cited_by_count":927},{"id":"1912.01734","title":"ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks","created":"2019-12-03","cited_by_count":783},{"id":"2211.07636","title":"EVA: Exploring the Limits of Masked Visual Representation Learning at Scale","created":"2022-11-14","cited_by_count":691},{"id":"2304.15010","title":"LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model","created":"2023-04-28","cited_by_count":602},{"id":"1808.10654","title":"Gibson Env: Real-World Perception for Embodied Agents","created":"2018-08-31","cited_by_count":481},{"id":"1811.00491","title":"A Corpus for Reasoning About Natural Language Grounded in Photographs","created":"2018-11-01","cited_by_count":459},{"id":"2004.12993","title":"DeeBERT: Dynamic Early Exiting for Accelerating BERT Inference","created":"2020-04-27","cited_by_count":332},{"id":"2210.07574","title":"Is synthetic data from generative models ready for image recognition?","created":"2022-10-14","cited_by_count":320},{"id":"2306.05425","title":"MIMIC-IT: Multi-Modal In-Context Instruction Tuning","created":"2023-06-08","cited_by_count":267},{"id":"2304.06939","title":"Multimodal C4: An Open, Billion-scale Corpus of Images Interleaved with Text","created":"2023-04-14","cited_by_count":208},{"id":"2104.06039","title":"MultiModalQA: Complex Question Answering over Text, Tables and Images","created":"2021-04-13","cited_by_count":179},{"id":"2301.04883","title":"SlideVQA: A Dataset for Document Visual Question Answering on Multiple Images","created":"2023-01-12","cited_by_count":179},{"id":"1604.03968","title":"Visual Storytelling","created":"2016-04-13","cited_by_count":176},{"id":"1812.02784","title":"StoryGAN: A Sequential Conditional GAN for Story Visualization","created":"2018-12-06","cited_by_count":138},{"id":"1708.01311","title":"Automatic Spatially-aware Fashion Concept Discovery","created":"2017-08-03","cited_by_count":134},{"id":"1808.10584","title":"Learning to Describe Differences Between Pairs of Similar Images","created":"2018-08-31","cited_by_count":114},{"id":"2109.00590","title":"WebQA: Multihop and Multimodal QA","created":"2021-09-01","cited_by_count":109},{"id":"2302.02503","title":"Leaving Reality to Imagination: Robust Classification via Generated Datasets","created":"2023-02-05","cited_by_count":91},{"id":"1809.00812","title":"RecipeQA: A Challenge Dataset for Multimodal Comprehension of Cooking Recipes","created":"2018-09-04","cited_by_count":74},{"id":"2209.06192","title":"StoryDALL-E: Adapting Pretrained Text-to-Image Transformers for Story Continuation","created":"2022-09-13","cited_by_count":74},{"id":"2208.02515","title":"Fine-Grained Semantically Aligned Vision-Language Pre-Training","created":"2022-08-04","cited_by_count":68},{"id":"2203.13049","title":"Compositional Temporal Grounding with Structured Variational Cross-Graph Correspondence Learning","created":"2022-03-24","cited_by_count":59},{"id":"2209.09019","title":"LAVIS: A Library for Language-Vision Intelligence","created":"2022-09-15","cited_by_count":55},{"id":"1804.03608","title":"Imagine This! Scripts to Compositions to Videos","created":"2018-04-10","cited_by_count":54},{"id":"1906.07689","title":"Expressing Visual Relationships via Language","created":"2019-06-18","cited_by_count":49},{"id":"2305.19164","title":"LANCE: Stress-testing Visual Models by Generating Language-guided Counterfactual Images","created":"2023-05-30","cited_by_count":46},{"id":"1611.05118","title":"The Amazing Mysteries of the Gutter: Drawing Inferences Between Panels in Comic Book Narratives","created":"2016-11-16","cited_by_count":42},{"id":"1911.07450","title":"Unsupervised Reinforcement Learning of Transferable Meta-Skills for Embodied Navigation","created":"2019-11-18","cited_by_count":40},{"id":"2001.08034","title":"ManyModalQA: Modality Disambiguation and QA over Diverse Inputs","created":"2020-01-22","cited_by_count":38},{"id":"2303.13221","title":"Explore the Power of Synthetic Data on Few-shot Object Detection","created":"2023-03-23","cited_by_count":38},{"id":"1909.04101","title":"Neural Naturalist: Generating Fine-Grained Image Comparisons","created":"2019-09-09","cited_by_count":36},{"id":"2303.13233","title":"Visually-Prompted Language Model for Fine-Grained Scene Graph Generation in an Open World","created":"2023-03-23","cited_by_count":35},{"id":"1908.04342","title":"Why Does a Visual Question Have Different Answers?","created":"2019-08-12","cited_by_count":34},{"id":"2112.06558","title":"MAGIC: Multimodal relAtional Graph adversarIal inferenCe for Diverse and Unpaired Text-based Image Captioning","created":"2021-12-13","cited_by_count":27},{"id":"2008.11976","title":"Visual Question Answering on Image Sets","created":"2020-08-27","cited_by_count":26},{"id":"2306.07890","title":"VISION Datasets: A Benchmark for Vision-based InduStrial InspectiON","created":"2023-06-13","cited_by_count":25},{"id":"2303.06571","title":"Gradient-Regulated Meta-Prompt Learning for Generalizable Vision-Language Models","created":"2023-03-12","cited_by_count":21},{"id":"2203.08013","title":"End-to-End Modeling via Information Tree for One-Shot Natural Language Spatial Video Grounding","created":"2022-03-15","cited_by_count":19},{"id":"2305.12799","title":"Interactive Data Synthesis for Systematic Vision Adaptation via LLMs-AIGCs Collaboration","created":"2023-05-22","cited_by_count":12}],"next_cursor":null}