{"list":"other","total":76,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"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":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"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":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"2303.03378","title":"PaLM-E: An Embodied Multimodal Language Model","created":"2023-03-06","cited_by_count":2071},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"id":"1805.01978","title":"Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination","created":"2018-05-05","cited_by_count":1845},{"id":"2001.04451","title":"Reformer: The Efficient Transformer","created":"2020-01-13","cited_by_count":1668},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620},{"id":"2006.04768","title":"Linformer: Self-Attention with Linear Complexity","created":"2020-06-08","cited_by_count":1474},{"id":"1504.00325","title":"Microsoft COCO Captions: Data Collection and Evaluation Server","created":"2015-04-01","cited_by_count":1462},{"id":"2203.12602","title":"VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training","created":"2022-03-23","cited_by_count":1322},{"id":"1711.11248","title":"A Closer Look at Spatiotemporal Convolutions for Action Recognition","created":"2017-11-30","cited_by_count":1143},{"id":"2103.03206","title":"Perceiver: General Perception with Iterative Attention","created":"2021-03-04","cited_by_count":1104},{"id":"2106.13230","title":"Video Swin Transformer","created":"2021-06-24","cited_by_count":1091},{"id":"1406.2199","title":"Two-Stream Convolutional Networks for Action Recognition in Videos","created":"2014-06-09","cited_by_count":1068},{"id":"2304.14178","title":"mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality","created":"2023-04-27","cited_by_count":1040},{"id":"2106.04560","title":"Scaling Vision Transformers","created":"2021-06-08","cited_by_count":999},{"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":"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":"2308.09126","title":"EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding","created":"2023-08-17","cited_by_count":680},{"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":"2112.04482","title":"FLAVA: A Foundational Language And Vision Alignment Model","created":"2021-12-08","cited_by_count":649},{"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":"2309.00071","title":"YaRN: Efficient Context Window Extension of Large Language Models","created":"2023-08-31","cited_by_count":601},{"id":"2302.14045","title":"Language Is Not All You Need: Aligning Perception with Language Models","created":"2023-02-27","cited_by_count":543},{"id":"2204.00598","title":"Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language","created":"2022-04-01","cited_by_count":513},{"id":"1912.06430","title":"End-to-End Learning of Visual Representations from Uncurated Instructional Videos","created":"2019-12-13","cited_by_count":507},{"id":"2212.03191","title":"InternVideo: General Video Foundation Models via Generative and Discriminative Learning","created":"2022-12-06","cited_by_count":447},{"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":"2212.00794","title":"Scaling Language-Image Pre-training via Masking","created":"2022-12-01","cited_by_count":317},{"id":"2305.13786","title":"Perception Test: A Diagnostic Benchmark for Multimodal Video Models","created":"2023-05-23","cited_by_count":314},{"id":"2106.02636","title":"MERLOT: Multimodal Neural Script Knowledge Models","created":"2021-06-04","cited_by_count":311},{"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":"2305.06988","title":"Self-Chained Image-Language Model for Video Localization and Question Answering","created":"2023-05-11","cited_by_count":203},{"id":"2206.13559","title":"ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learning","created":"2022-06-27","cited_by_count":193},{"id":"2201.08383","title":"MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition","created":"2022-01-20","cited_by_count":189},{"id":"2111.12681","title":"VIOLET : End-to-End Video-Language Transformers with Masked Visual-token Modeling","created":"2021-11-24","cited_by_count":188},{"id":"2206.01720","title":"Revisiting the \"Video\" in Video-Language Understanding","created":"2022-06-03","cited_by_count":169},{"id":"2201.04288","title":"Multiview Transformers for Video Recognition","created":"2022-01-12","cited_by_count":148},{"id":"2106.11310","title":"Towards Long-Form Video Understanding","created":"2021-06-21","cited_by_count":146},{"id":"2209.07526","title":"OmniVL:One Foundation Model for Image-Language and Video-Language Tasks","created":"2022-09-15","cited_by_count":143},{"id":"2206.03428","title":"Revealing Single Frame Bias for Video-and-Language Learning","created":"2022-06-07","cited_by_count":133},{"id":"2310.09199","title":"PaLI-3 Vision Language Models: Smaller, Faster, Stronger","created":"2023-10-13","cited_by_count":126},{"id":"2205.10747","title":"Language Models with Image Descriptors are Strong Few-Shot Video-Language Learners","created":"2022-05-22","cited_by_count":117},{"id":"2204.01692","title":"Long Movie Clip Classification with State-Space Video Models","created":"2022-04-04","cited_by_count":106},{"id":"1611.02155","title":"Spatiotemporal Residual Networks for Video Action Recognition","created":"2016-11-07","cited_by_count":91},{"id":"2306.07915","title":"Image Captioners Are Scalable Vision Learners Too","created":"2023-06-13","cited_by_count":89},{"id":"2212.05051","title":"VindLU: A Recipe for Effective Video-and-Language Pretraining","created":"2022-12-09","cited_by_count":87},{"id":"2204.00679","title":"Learning Audio-Video Modalities from Image Captions","created":"2022-04-01","cited_by_count":80},{"id":"2209.01540","title":"An Empirical Study of End-to-End Video-Language Transformers with Masked Visual Modeling","created":"2022-09-04","cited_by_count":74},{"id":"2206.07160","title":"LAVENDER: Unifying Video-Language Understanding as Masked Language Modeling","created":"2022-06-14","cited_by_count":73},{"id":"2301.01821","title":"Parameter-Efficient Fine-Tuning Design Spaces","created":"2023-01-04","cited_by_count":67},{"id":"2301.11116","title":"Revisiting Temporal Modeling for CLIP-based Image-to-Video Knowledge Transferring","created":"2023-01-26","cited_by_count":58},{"id":"2212.03229","title":"Rethinking Video ViTs: Sparse Video Tubes for Joint Image and Video Learning","created":"2022-12-06","cited_by_count":49},{"id":"2211.09119","title":"Token Turing Machines","created":"2022-11-16","cited_by_count":25},{"id":"2211.15103","title":"VLTinT: Visual-Linguistic Transformer-in-Transformer for Coherent Video Paragraph Captioning","created":"2022-11-28","cited_by_count":25},{"id":"2212.03490","title":"SimVTP: Simple Video Text Pre-training with Masked Autoencoders","created":"2022-12-07","cited_by_count":21},{"id":"1907.06670","title":"Slow Feature Analysis for Human Action Recognition","created":"2019-07-15","cited_by_count":16},{"id":"2210.11929","title":"LiteVL: Efficient Video-Language Learning with Enhanced Spatial-Temporal Modeling","created":"2022-10-21","cited_by_count":16},{"id":"2211.11446","title":"SMAUG: Sparse Masked Autoencoder for Efficient Video-Language Pre-training","created":"2022-11-21","cited_by_count":15},{"id":"2210.04889","title":"Turbo Training with Token Dropout","created":"2022-10-10","cited_by_count":14},{"id":"2209.12797","title":"Rethinking Resolution in the Context of Efficient Video Recognition","created":"2022-09-26","cited_by_count":8}],"next_cursor":null}