{"list":"other","total":285,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"2005.12872","title":"End-to-End Object Detection with Transformers","created":"2020-05-26","cited_by_count":7414},{"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":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"1301.3781","title":"Efficient Estimation of Word Representations in Vector Space","created":"2013-01-16","cited_by_count":4375},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"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":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"1909.11942","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","created":"2019-09-26","cited_by_count":2790},{"id":"1804.02767","title":"YOLOv3: An Incremental Improvement","created":"2018-04-08","cited_by_count":2659},{"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":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"id":"2106.08254","title":"BEiT: BERT Pre-Training of Image Transformers","created":"2021-06-15","cited_by_count":2375},{"id":"1709.07871","title":"FiLM: Visual Reasoning with a General Conditioning Layer","created":"2017-09-22","cited_by_count":2333},{"id":"2107.13586","title":"Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing","created":"2021-07-28","cited_by_count":2234},{"id":"2006.03654","title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","created":"2020-06-05","cited_by_count":2181},{"id":"1311.2524","title":"Rich feature hierarchies for accurate object detection and semantic segmentation","created":"2013-11-11","cited_by_count":2162},{"id":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"1909.08053","title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism","created":"2019-09-17","cited_by_count":1868},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"id":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803},{"id":"2210.02303","title":"Imagen Video: High Definition Video Generation with Diffusion Models","created":"2022-10-05","cited_by_count":1778},{"id":"2209.14792","title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","created":"2022-09-29","cited_by_count":1742},{"id":"1904.08920","title":"Towards VQA Models That Can Read","created":"2019-04-18","cited_by_count":1718},{"id":"2110.13900","title":"WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing","created":"2021-10-26","cited_by_count":1657},{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620},{"id":"2111.02114","title":"LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs","created":"2021-11-03","cited_by_count":1555},{"id":"1609.08144","title":"Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation","created":"2016-09-26","cited_by_count":1475},{"id":"1504.00325","title":"Microsoft COCO Captions: Data Collection and Evaluation Server","created":"2015-04-01","cited_by_count":1462},{"id":"1612.06890","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","created":"2016-12-20","cited_by_count":1457},{"id":"1707.07998","title":"Bottom-Up and Top-Down Attention for Image Captioning and Visual Question Answering","created":"2017-07-25","cited_by_count":1312},{"id":"1908.03557","title":"VisualBERT: A Simple and Performant Baseline for Vision and Language","created":"2019-08-09","cited_by_count":1296},{"id":"2206.10789","title":"Scaling Autoregressive Models for Content-Rich Text-to-Image Generation","created":"2022-06-22","cited_by_count":1295},{"id":"2205.01917","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","created":"2022-05-04","cited_by_count":1274},{"id":"2102.03334","title":"ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision","created":"2021-02-05","cited_by_count":1230},{"id":"1908.03195","title":"LVIS: A Dataset for Large Vocabulary Instance Segmentation","created":"2019-08-08","cited_by_count":1217},{"id":"2102.08981","title":"Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts","created":"2021-02-17","cited_by_count":1216},{"id":"2004.06165","title":"Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks","created":"2020-04-13","cited_by_count":1214},{"id":"2104.00650","title":"Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval","created":"2021-04-01","cited_by_count":1177},{"id":"1906.00067","title":"OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge","created":"2019-05-31","cited_by_count":1121},{"id":"2209.00796","title":"Diffusion Models: A Comprehensive Survey of Methods and Applications","created":"2022-09-02","cited_by_count":1114},{"id":"1706.04261","title":"The \"something something\" video database for learning and evaluating visual common sense","created":"2017-06-13","cited_by_count":1103},{"id":"1810.03993","title":"Model Cards for Model Reporting","created":"2018-10-05","cited_by_count":1080},{"id":"1608.00272","title":"Modeling Context in Referring Expressions","created":"2016-07-31","cited_by_count":1063},{"id":"1711.07280","title":"Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments","created":"2017-11-20","cited_by_count":1027},{"id":"2110.04544","title":"CLIP-Adapter: Better Vision-Language Models with Feature Adapters","created":"2021-10-09","cited_by_count":1026},{"id":"1412.2306","title":"Deep Visual-Semantic Alignments for Generating Image Descriptions","created":"2014-12-07","cited_by_count":968},{"id":"1906.03327","title":"HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips","created":"2019-06-07","cited_by_count":950},{"id":"2104.13921","title":"Open-vocabulary Object Detection via Vision and Language Knowledge Distillation","created":"2021-04-28","cited_by_count":906},{"id":"1511.02283","title":"Generation and Comprehension of Unambiguous Object Descriptions","created":"2015-11-07","cited_by_count":904},{"id":"1411.4555","title":"Show and Tell: A Neural Image Caption Generator","created":"2014-11-17","cited_by_count":879},{"id":"1802.08218","title":"VizWiz Grand Challenge: Answering Visual Questions from Blind People","created":"2018-02-22","cited_by_count":858},{"id":"1607.08822","title":"SPICE: Semantic Propositional Image Caption Evaluation","created":"2016-07-29","cited_by_count":824},{"id":"2104.12763","title":"MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding","created":"2021-04-26","cited_by_count":819},{"id":"2205.06175","title":"A Generalist Agent","created":"2022-05-12","cited_by_count":808},{"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":"2111.14822","title":"Vector Quantized Diffusion Model for Text-to-Image Synthesis","created":"2021-11-29","cited_by_count":774},{"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":"2105.08276","title":"NExT-QA:Next Phase of Question-Answering to Explaining Temporal Actions","created":"2021-05-18","cited_by_count":744},{"id":"2202.10054","title":"Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distribution","created":"2022-02-21","cited_by_count":739},{"id":"2201.03546","title":"Language-driven Semantic Segmentation","created":"2022-01-10","cited_by_count":717},{"id":"2206.01718","title":"A-OKVQA: A Benchmark for Visual Question Answering using World Knowledge","created":"2022-06-03","cited_by_count":710},{"id":"1904.01766","title":"VideoBERT: A Joint Model for Video and Language Representation Learning","created":"2019-04-03","cited_by_count":703},{"id":"2105.13290","title":"CogView: Mastering Text-to-Image Generation via Transformers","created":"2021-05-26","cited_by_count":694},{"id":"1708.01641","title":"Localizing Moments in Video with Natural Language","created":"2017-08-04","cited_by_count":663},{"id":"2104.08860","title":"CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval","created":"2021-04-18","cited_by_count":651},{"id":"2201.02605","title":"Detecting Twenty-thousand Classes using Image-level Supervision","created":"2022-01-07","cited_by_count":614},{"id":"1612.03242","title":"StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks","created":"2016-12-10","cited_by_count":577},{"id":"1811.10830","title":"From Recognition to Cognition: Visual Commonsense Reasoning","created":"2018-11-27","cited_by_count":556},{"id":"2205.14100","title":"GIT: A Generative Image-to-text Transformer for Vision and Language","created":"2022-05-27","cited_by_count":537},{"id":"2112.01518","title":"DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting","created":"2021-12-02","cited_by_count":532},{"id":"2204.00598","title":"Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language","created":"2022-04-01","cited_by_count":513},{"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":"1912.06430","title":"End-to-End Learning of Visual Representations from Uncurated Instructional Videos","created":"2019-12-13","cited_by_count":507},{"id":"2203.13131","title":"Make-A-Scene: Scene-Based Text-to-Image Generation with Human Priors","created":"2022-03-24","cited_by_count":487},{"id":"1411.4389","title":"Long-term Recurrent Convolutional Networks for Visual Recognition and Description","created":"2014-11-17","cited_by_count":484},{"id":"2102.06183","title":"Less is More: ClipBERT for Video-and-Language Learning via Sparse Sampling","created":"2021-02-11","cited_by_count":484},{"id":"2210.02399","title":"Phenaki: Variable Length Video Generation From Open Domain Textual Description","created":"2022-10-05","cited_by_count":484},{"id":"1812.08658","title":"nocaps: novel object captioning at scale","created":"2018-12-20","cited_by_count":444},{"id":"2112.12750","title":"SLIP: Self-supervision meets Language-Image Pre-training","created":"2021-12-23","cited_by_count":436},{"id":"1801.08186","title":"MAttNet: Modular Attention Network for Referring Expression Comprehension","created":"2018-01-24","cited_by_count":431},{"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":"2206.08916","title":"Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks","created":"2022-06-17","cited_by_count":421},{"id":"1803.08024","title":"Stacked Cross Attention for Image-Text Matching","created":"2018-03-21","cited_by_count":416},{"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":"2110.05208","title":"Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm","created":"2021-10-11","cited_by_count":405},{"id":"2003.12462","title":"TextCaps: a Dataset for Image Captioning with Reading Comprehension","created":"2020-03-24","cited_by_count":400},{"id":"2007.10639","title":"Multi-modal Transformer for Video Retrieval","created":"2020-07-21","cited_by_count":395}],"next_cursor":"100"}