{"list":"other","total":83,"rows":[{"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":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"1301.3781","title":"Efficient Estimation of Word Representations in Vector Space","created":"2013-01-16","cited_by_count":4375},{"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":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"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":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"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":"1711.11248","title":"A Closer Look at Spatiotemporal Convolutions for Action Recognition","created":"2017-11-30","cited_by_count":1143},{"id":"2106.13230","title":"Video Swin Transformer","created":"2021-06-24","cited_by_count":1091},{"id":"2110.04544","title":"CLIP-Adapter: Better Vision-Language Models with Feature Adapters","created":"2021-10-09","cited_by_count":1026},{"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":"1608.00859","title":"Temporal Segment Networks: Towards Good Practices for Deep Action Recognition","created":"2016-08-02","cited_by_count":902},{"id":"2104.11227","title":"Multiscale Vision Transformers","created":"2021-04-22","cited_by_count":897},{"id":"1811.08383","title":"TSM: Temporal Shift Module for Efficient Video Understanding","created":"2018-11-20","cited_by_count":856},{"id":"1705.00754","title":"Dense-Captioning Events in Videos","created":"2017-05-02","cited_by_count":793},{"id":"1912.11370","title":"Big Transfer (BiT): General Visual Representation Learning","created":"2019-12-24","cited_by_count":769},{"id":"1708.01641","title":"Localizing Moments in Video with Natural Language","created":"2017-08-04","cited_by_count":663},{"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":"1604.01753","title":"Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding","created":"2016-04-06","cited_by_count":537},{"id":"2303.16727","title":"VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking","created":"2023-03-29","cited_by_count":528},{"id":"1705.08421","title":"AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions","created":"2017-05-23","cited_by_count":449},{"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":"2005.00200","title":"HERO: Hierarchical Encoder for Video+Language Omni-representation Pre-training","created":"2020-05-01","cited_by_count":362},{"id":"1808.01340","title":"A Short Note about Kinetics-600","created":"2018-08-03","cited_by_count":333},{"id":"1609.08675","title":"YouTube-8M: A Large-Scale Video Classification Benchmark","created":"2016-09-27","cited_by_count":324},{"id":"1903.02874","title":"COIN: A Large-scale Dataset for Comprehensive Instructional Video Analysis","created":"2019-03-07","cited_by_count":318},{"id":"1907.06987","title":"A Short Note on the Kinetics-700 Human Action Dataset","created":"2019-07-15","cited_by_count":310},{"id":"2004.06704","title":"FineGym: A Hierarchical Video Dataset for Fine-grained Action Understanding","created":"2020-04-14","cited_by_count":234},{"id":"2005.00343","title":"The EPIC-KITCHENS Dataset: Collection, Challenges and Baselines","created":"2020-04-29","cited_by_count":225},{"id":"1801.03150","title":"Moments in Time Dataset: one million videos for event understanding","created":"2018-01-09","cited_by_count":215},{"id":"2001.09099","title":"TVR: A Large-Scale Dataset for Video-Subtitle Moment Retrieval","created":"2020-01-24","cited_by_count":215},{"id":"1501.02530","title":"A Dataset for Movie Description","created":"2015-01-12","cited_by_count":195},{"id":"2208.03550","title":"Frozen CLIP Models are Efficient Video Learners","created":"2022-08-06","cited_by_count":182},{"id":"1605.03705","title":"Movie Description","created":"2016-05-12","cited_by_count":181},{"id":"2212.03640","title":"Fine-tuned CLIP Models are Efficient Video Learners","created":"2022-12-06","cited_by_count":179},{"id":"2203.07303","title":"All in One: Exploring Unified Video-Language Pre-training","created":"2022-03-14","cited_by_count":171},{"id":"1409.8403","title":"Evaluation of Output Embeddings for Fine-Grained Image Classification","created":"2014-09-30","cited_by_count":166},{"id":"1503.08677","title":"Label-Embedding for Image Classification","created":"2015-03-30","cited_by_count":165},{"id":"1912.04487","title":"Listen to Look: Action Recognition by Previewing Audio","created":"2019-12-10","cited_by_count":163},{"id":"1611.05088","title":"Learning a Deep Embedding Model for Zero-Shot Learning","created":"2016-11-15","cited_by_count":153},{"id":"2209.07526","title":"OmniVL:One Foundation Model for Image-Language and Video-Language Tasks","created":"2022-09-15","cited_by_count":143},{"id":"1811.00347","title":"How2: A Large-scale Dataset for Multimodal Language Understanding","created":"2018-11-01","cited_by_count":138},{"id":"1604.02748","title":"TGIF: A New Dataset and Benchmark on Animated GIF Description","created":"2016-04-10","cited_by_count":124},{"id":"2210.09263","title":"Vision-Language Pre-training: Basics, Recent Advances, and Future Trends","created":"2022-10-17","cited_by_count":117},{"id":"2212.05051","title":"VindLU: A Recipe for Effective Video-and-Language Pretraining","created":"2022-12-09","cited_by_count":87},{"id":"2101.06184","title":"Temporal-Relational CrossTransformers for Few-Shot Action Recognition","created":"2021-01-15","cited_by_count":84},{"id":"2105.07404","title":"MultiSports: A Multi-Person Video Dataset of Spatio-Temporally Localized Sports Actions","created":"2021-05-16","cited_by_count":84},{"id":"2003.01455","title":"Rethinking Zero-shot Video Classification: End-to-end Training for Realistic Applications","created":"2020-03-03","cited_by_count":80},{"id":"2204.00679","title":"Learning Audio-Video Modalities from Image Captions","created":"2022-04-01","cited_by_count":80},{"id":"2108.02833","title":"Elaborative Rehearsal for Zero-shot Action Recognition","created":"2021-08-05","cited_by_count":77},{"id":"2105.11107","title":"FineAction: A Fine-Grained Video Dataset for Temporal Action Localization","created":"2021-05-24","cited_by_count":61},{"id":"1403.6173","title":"Coherent Multi-Sentence Video Description with Variable Level of Detail","created":"2014-03-24","cited_by_count":45},{"id":"1605.00743","title":"Learning Attributes Equals Multi-Source Domain Generalization","created":"2016-05-03","cited_by_count":44},{"id":"1803.08460","title":"Towards Universal Representation for Unseen Action Recognition","created":"2018-03-22","cited_by_count":44},{"id":"2003.11618","title":"VIOLIN: A Large-Scale Dataset for Video-and-Language Inference","created":"2020-03-25","cited_by_count":41},{"id":"2207.07885","title":"Clover: Towards A Unified Video-Language Alignment and Fusion Model","created":"2022-07-16","cited_by_count":41},{"id":"1503.01070","title":"Using Descriptive Video Services to Create a Large Data Source for Video Annotation Research","created":"2015-03-03","cited_by_count":33},{"id":"1511.04458","title":"Transductive Zero-Shot Action Recognition by Word-Vector Embedding","created":"2015-11-13","cited_by_count":31},{"id":"1607.02104","title":"Zero-Shot Visual Recognition via Bidirectional Latent Embedding","created":"2016-07-07","cited_by_count":27},{"id":"1611.08663","title":"Multi-Task Zero-Shot Action Recognition with Prioritised Data Augmentation","created":"2016-11-26","cited_by_count":27},{"id":"1706.09317","title":"Alternative Semantic Representations for Zero-Shot Human Action Recognition","created":"2017-06-28","cited_by_count":27},{"id":"1510.06939","title":"Objects2action: Classifying and localizing actions without any video example","created":"2015-10-23","cited_by_count":26},{"id":"1502.01540","title":"Semantic Embedding Space for Zero-Shot Action Recognition","created":"2015-02-05","cited_by_count":19},{"id":"1901.00484","title":"Action2Vec: A Crossmodal Embedding Approach to Action Learning","created":"2019-01-02","cited_by_count":19},{"id":"2204.00486","title":"GEB+: A Benchmark for Generic Event Boundary Captioning, Grounding and Retrieval","created":"2022-04-01","cited_by_count":19},{"id":"2310.17942","title":"Diversifying Spatial-Temporal Perception for Video Domain Generalization","created":"2023-10-27","cited_by_count":19},{"id":"2007.05515","title":"AViD Dataset: Anonymized Videos from Diverse Countries","created":"2020-07-10","cited_by_count":18},{"id":"2008.12432","title":"All About Knowledge Graphs for Actions","created":"2020-08-28","cited_by_count":16},{"id":"2104.13473","title":"TRECVID 2020: A comprehensive campaign for evaluating video retrieval tasks across multiple application domains","created":"2021-04-27","cited_by_count":16},{"id":"2104.04715","title":"Object Priors for Classifying and Localizing Unseen Actions","created":"2021-04-10","cited_by_count":15},{"id":"2205.01657","title":"Cross-modal Representation Learning for Zero-shot Action Recognition","created":"2022-05-03","cited_by_count":15},{"id":"2203.15381","title":"Alignment-Uniformity aware Representation Learning for Zero-shot Video Classification","created":"2022-03-29","cited_by_count":11},{"id":"2209.12362","title":"Multi-dataset Training of Transformers for Robust Action Recognition","created":"2022-09-26","cited_by_count":10},{"id":"2110.13479","title":"Zero-Shot Action Recognition from Diverse Object-Scene Compositions","created":"2021-10-26","cited_by_count":8},{"id":"2012.02426","title":"Spatial-Temporal Alignment Network for Action Recognition and Detection","created":"2020-12-04","cited_by_count":3},{"id":"2311.17118","title":"Towards Weakly Supervised End-to-end Learning for Long-video Action Recognition","created":"2023-11-28","cited_by_count":2}],"next_cursor":null}