{"list":"other","total":100,"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":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"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":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"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":"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":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"2209.14988","title":"DreamFusion: Text-to-3D using 2D Diffusion","created":"2022-09-29","cited_by_count":3025},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"2303.12712","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","created":"2023-03-22","cited_by_count":2592},{"id":"1612.00837","title":"Making the V in VQA Matter: Elevating the Role of Image Understanding in Visual Question Answering","created":"2016-12-02","cited_by_count":2516},{"id":"2307.06281","title":"MMBench: Is Your Multi-modal Model an All-around Player?","created":"2023-07-12","cited_by_count":2141},{"id":"2102.12122","title":"Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions","created":"2021-02-24","cited_by_count":1962},{"id":"2209.09513","title":"Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering","created":"2022-09-20","cited_by_count":1919},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"1904.08920","title":"Towards VQA Models That Can Read","created":"2019-04-18","cited_by_count":1718},{"id":"2306.13394","title":"MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models","created":"2023-06-23","cited_by_count":1652},{"id":"2107.07651","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","created":"2021-07-16","cited_by_count":1619},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"2306.02858","title":"Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding","created":"2023-06-05","cited_by_count":1471},{"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":"2205.01917","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","created":"2022-05-04","cited_by_count":1274},{"id":"2308.02490","title":"MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilities","created":"2023-08-04","cited_by_count":1239},{"id":"2004.06165","title":"Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks","created":"2020-04-13","cited_by_count":1214},{"id":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175},{"id":"1906.00067","title":"OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge","created":"2019-05-31","cited_by_count":1121},{"id":"2311.17005","title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","created":"2023-11-28","cited_by_count":1109},{"id":"2306.05424","title":"Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models","created":"2023-06-08","cited_by_count":1062},{"id":"1908.08530","title":"VL-BERT: Pre-training of Generic Visual-Linguistic Representations","created":"2019-08-22","cited_by_count":954},{"id":"2307.16125","title":"SEED-Bench: Benchmarking Multimodal LLMs with Generative Comprehension","created":"2023-07-30","cited_by_count":940},{"id":"1802.08218","title":"VizWiz Grand Challenge: Answering Visual Questions from Blind People","created":"2018-02-22","cited_by_count":858},{"id":"2305.06355","title":"VideoChat: Chat-Centric Video Understanding","created":"2023-05-10","cited_by_count":857},{"id":"2111.11432","title":"Florence: A New Foundation Model for Computer Vision","created":"2021-11-22","cited_by_count":804},{"id":"1705.00754","title":"Dense-Captioning Events in Videos","created":"2017-05-02","cited_by_count":793},{"id":"2209.06794","title":"PaLI: A Jointly-Scaled Multilingual Language-Image Model","created":"2022-09-14","cited_by_count":766},{"id":"2202.03052","title":"OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework","created":"2022-02-07","cited_by_count":745},{"id":"2211.07636","title":"EVA: Exploring the Limits of Masked Visual Representation Learning at Scale","created":"2022-11-14","cited_by_count":691},{"id":"1708.01641","title":"Localizing Moments in Video with Natural Language","created":"2017-08-04","cited_by_count":663},{"id":"2108.10904","title":"SimVLM: Simple Visual Language Model Pretraining with Weak Supervision","created":"2021-08-24","cited_by_count":647},{"id":"1703.09788","title":"Towards Automatic Learning of Procedures from Web Instructional Videos","created":"2017-03-28","cited_by_count":619},{"id":"2109.14084","title":"VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding","created":"2021-09-28","cited_by_count":602},{"id":"2304.15010","title":"LLaMA-Adapter V2: Parameter-Efficient Visual Instruction Model","created":"2023-04-28","cited_by_count":602},{"id":"1906.02467","title":"ActivityNet-QA: A Dataset for Understanding Complex Web Videos via Question Answering","created":"2019-06-06","cited_by_count":561},{"id":"2311.17043","title":"LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models","created":"2023-11-28","cited_by_count":546},{"id":"2208.10442","title":"Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks","created":"2022-08-22","cited_by_count":511},{"id":"1812.08658","title":"nocaps: novel object captioning at scale","created":"2018-12-20","cited_by_count":444},{"id":"2104.11178","title":"VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text","created":"2021-04-22","cited_by_count":429},{"id":"2111.02358","title":"VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Experts","created":"2021-11-03","cited_by_count":425},{"id":"1904.03493","title":"VATEX: A Large-Scale, High-Quality Multilingual Dataset for Video-and-Language Research","created":"2019-04-06","cited_by_count":414},{"id":"2212.09058","title":"BEATs: Audio Pre-Training with Acoustic Tokenizers","created":"2022-12-18","cited_by_count":388},{"id":"1910.09387","title":"Clotho: An Audio Captioning Dataset","created":"2019-10-21","cited_by_count":358},{"id":"1906.10770","title":"Deep Modular Co-Attention Networks for Visual Question Answering","created":"2019-06-25","cited_by_count":339},{"id":"2106.13043","title":"AudioCLIP: Extending CLIP to Image, Text and Audio","created":"2021-06-24","cited_by_count":339},{"id":"2110.04994","title":"Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scans","created":"2021-10-11","cited_by_count":336},{"id":"2306.16527","title":"OBELICS: An Open Web-Scale Filtered Dataset of Interleaved Image-Text Documents","created":"2023-06-21","cited_by_count":316},{"id":"2403.12013","title":"GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Image","created":"2024-03-18","cited_by_count":286},{"id":"2006.16228","title":"Self-Supervised MultiModal Versatile Networks","created":"2020-06-29","cited_by_count":276},{"id":"2207.06405","title":"Masked Autoencoders that Listen","created":"2022-07-13","cited_by_count":273},{"id":"2212.05171","title":"ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding","created":"2022-12-10","cited_by_count":267},{"id":"2303.17395","title":"WavCaps: A ChatGPT-Assisted Weakly-Labelled Audio Captioning Dataset for Audio-Language Multimodal Research","created":"2023-03-30","cited_by_count":267},{"id":"2206.08155","title":"Zero-Shot Video Question Answering via Frozen Bidirectional Language Models","created":"2022-06-16","cited_by_count":229},{"id":"2111.10337","title":"Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptions","created":"2021-11-19","cited_by_count":226},{"id":"2305.11834","title":"Pengi: An Audio Language Model for Audio Tasks","created":"2023-05-19","cited_by_count":220},{"id":"2201.08377","title":"Omnivore: A Single Model for Many Visual Modalities","created":"2022-01-20","cited_by_count":215},{"id":"2203.14072","title":"Learning to Answer Questions in Dynamic Audio-Visual Scenarios","created":"2022-03-26","cited_by_count":191},{"id":"2312.03700","title":"OneLLM: One Framework to Align All Modalities with Language","created":"2023-12-06","cited_by_count":187},{"id":"1605.03705","title":"Movie Description","created":"2016-05-12","cited_by_count":181},{"id":"2305.18500","title":"VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset","created":"2023-05-29","cited_by_count":169},{"id":"2309.03905","title":"ImageBind-LLM: Multi-modality Instruction Tuning","created":"2023-09-07","cited_by_count":142},{"id":"2304.08345","title":"VALOR: Vision-Audio-Language Omni-Perception Pretraining Model and Dataset","created":"2023-04-17","cited_by_count":140},{"id":"2307.10802","title":"Meta-Transformer: A Unified Framework for Multimodal Learning","created":"2023-07-20","cited_by_count":136},{"id":"1604.02748","title":"TGIF: A New Dataset and Benchmark on Animated GIF Description","created":"2016-04-10","cited_by_count":124},{"id":"2110.14378","title":"Towards artificial general intelligence via a multimodal foundation model","created":"2021-10-27","cited_by_count":112},{"id":"2106.04632","title":"VALUE: A Multi-Task Benchmark for Video-and-Language Understanding Evaluation","created":"2021-06-08","cited_by_count":95},{"id":"2309.16058","title":"AnyMAL: An Efficient and Scalable Any-Modality Augmented Language Model","created":"2023-09-27","cited_by_count":93},{"id":"2204.09634","title":"Clotho-AQA: A Crowdsourced Dataset for Audio Question Answering","created":"2022-04-20","cited_by_count":85},{"id":"2011.01843","title":"Tabular Transformers for Modeling Multivariate Time Series","created":"2020-11-03","cited_by_count":77},{"id":"2305.16103","title":"ChatBridge: Bridging Modalities with Large Language Model as a Language Catalyst","created":"2023-05-25","cited_by_count":66},{"id":"2311.15599","title":"UniRepLKNet: A Universal Perception Large-Kernel ConvNet for Audio, Video, Point Cloud, Time-Series and Image Recognition","created":"2023-11-27","cited_by_count":64},{"id":"2103.03516","title":"Slow-Fast Auditory Streams For Audio Recognition","created":"2021-03-05","cited_by_count":56},{"id":"2007.14895","title":"Reliable Tuberculosis Detection using Chest X-ray with Deep Learning, Segmentation and Visualization","created":"2020-07-29","cited_by_count":50},{"id":"2303.16839","title":"MaMMUT: A Simple Architecture for Joint Learning for MultiModal Tasks","created":"2023-03-29","cited_by_count":24},{"id":"2303.13009","title":"MELTR: Meta Loss Transformer for Learning to Fine-tune Video Foundation Models","created":"2023-03-23","cited_by_count":15},{"id":"2305.17993","title":"Multi-Scale Attention for Audio Question Answering","created":"2023-05-29","cited_by_count":13},{"id":"2312.12441","title":"DiffSpectralNet : Unveiling the Potential of Diffusion Models for Hyperspectral Image Classification","created":"2023-10-29","cited_by_count":4}],"next_cursor":null}