{"list":"other","total":54,"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":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1301.3781","title":"Efficient Estimation of Word Representations in Vector Space","created":"2013-01-16","cited_by_count":4375},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"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":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"2004.09297","title":"MPNet: Masked and Permuted Pre-training for Language Understanding","created":"2020-04-20","cited_by_count":981},{"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":"2109.14084","title":"VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding","created":"2021-09-28","cited_by_count":602},{"id":"1912.06430","title":"End-to-End Learning of Visual Representations from Uncurated Instructional Videos","created":"2019-12-13","cited_by_count":507},{"id":"1903.01945","title":"MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation","created":"2019-03-05","cited_by_count":373},{"id":"2208.02816","title":"Expanding Language-Image Pretrained Models for General Video Recognition","created":"2022-08-04","cited_by_count":321},{"id":"2109.08472","title":"ActionCLIP: A New Paradigm for Video Action Recognition","created":"2021-09-17","cited_by_count":320},{"id":"1903.02874","title":"COIN: A Large-scale Dataset for Comprehensive Instructional Video Analysis","created":"2019-03-07","cited_by_count":318},{"id":"2112.04478","title":"Prompting Visual-Language Models for Efficient Video Understanding","created":"2021-12-08","cited_by_count":310},{"id":"2203.14712","title":"Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activities","created":"2022-03-28","cited_by_count":287},{"id":"2209.03320","title":"What does a platypus look like? Generating customized prompts for zero-shot image classification","created":"2022-09-07","cited_by_count":267},{"id":"2212.04501","title":"Learning Video Representations from Large Language Models","created":"2022-12-08","cited_by_count":205},{"id":"2212.03640","title":"Fine-tuned CLIP Models are Efficient Video Learners","created":"2022-12-06","cited_by_count":179},{"id":"2112.09583","title":"Align and Prompt: Video-and-Language Pre-training with Entity Prompts","created":"2021-12-17","cited_by_count":149},{"id":"2307.05463","title":"EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbone","created":"2023-07-11","cited_by_count":130},{"id":"2106.09141","title":"Probing Image-Language Transformers for Verb Understanding","created":"2021-06-16","cited_by_count":109},{"id":"2007.00394","title":"The IKEA ASM Dataset: Understanding People Assembling Furniture through Actions, Objects and Pose","created":"2020-07-01","cited_by_count":95},{"id":"2301.00184","title":"Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?","created":"2022-12-31","cited_by_count":90},{"id":"2201.10990","title":"Learning To Recognize Procedural Activities with Distant Supervision","created":"2022-01-26","cited_by_count":85},{"id":"2204.02968","title":"Temporal Alignment Networks for Long-term Video","created":"2022-04-06","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":"2108.02833","title":"Elaborative Rehearsal for Zero-shot Action Recognition","created":"2021-08-05","cited_by_count":77},{"id":"2304.06708","title":"Verbs in Action: Improving verb understanding in video-language models","created":"2023-04-13","cited_by_count":76},{"id":"2207.01297","title":"Revisiting Classifier: Transferring Vision-Language Models for Video Recognition","created":"2022-07-04","cited_by_count":71},{"id":"2211.11733","title":"Teaching Structured Vision&Language Concepts to Vision&Language Models","created":"2022-11-21","cited_by_count":71},{"id":"2301.02311","title":"HierVL: Learning Hierarchical Video-Language Embeddings","created":"2023-01-05","cited_by_count":66},{"id":"2207.08184","title":"Zero-Shot Temporal Action Detection via Vision-Language Prompting","created":"2022-07-17","cited_by_count":65},{"id":"1904.08703","title":"Out-of-Distribution Detection for Generalized Zero-Shot Action Recognition","created":"2019-04-18","cited_by_count":54},{"id":"2105.04489","title":"Spoken Moments: Learning Joint Audio-Visual Representations from Video Descriptions","created":"2021-05-10","cited_by_count":53},{"id":"2303.17839","title":"Learning Procedure-aware Video Representation from Instructional Videos and Their Narrations","created":"2023-03-31","cited_by_count":46},{"id":"2212.01758","title":"Improving Zero-shot Generalization and Robustness of Multi-modal Models","created":"2022-12-04","cited_by_count":45},{"id":"2208.05318","title":"Generative Action Description Prompts for Skeleton-based Action Recognition","created":"2022-08-10","cited_by_count":43},{"id":"2303.08914","title":"MAtch, eXpand and Improve: Unsupervised Finetuning for Zero-Shot Action Recognition with Language Knowledge","created":"2023-03-15","cited_by_count":43},{"id":"2305.10683","title":"Paxion: Patching Action Knowledge in Video-Language Foundation Models","created":"2023-05-18","cited_by_count":42},{"id":"2207.07885","title":"Clover: Towards A Unified Video-Language Alignment and Fusion Model","created":"2022-07-16","cited_by_count":41},{"id":"2207.07635","title":"Is a Caption Worth a Thousand Images? A Controlled Study for Representation Learning","created":"2022-07-15","cited_by_count":39},{"id":"2404.01933","title":"PREGO: online mistake detection in PRocedural EGOcentric videos","created":"2024-04-02","cited_by_count":39},{"id":"2304.13265","title":"StepFormer: Self-supervised Step Discovery and Localization in Instructional Videos","created":"2023-04-26","cited_by_count":37},{"id":"2306.03802","title":"Learning to Ground Instructional Articles in Videos through Narrations","created":"2023-06-06","cited_by_count":28},{"id":"1510.06939","title":"Objects2action: Classifying and localizing actions without any video example","created":"2015-10-23","cited_by_count":26},{"id":"1909.06423","title":"Zero-Shot Action Recognition in Videos: A Survey","created":"2019-09-13","cited_by_count":19},{"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":"2307.10922","title":"Language-based Action Concept Spaces Improve Video Self-Supervised Learning","created":"2023-07-20","cited_by_count":10},{"id":"2308.16689","title":"ViLTA: Enhancing Vision-Language Pre-training through Textual Augmentation","created":"2023-08-31","cited_by_count":6}],"next_cursor":null}