{"list":"other","total":54,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"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":"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":"1502.01852","title":"Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification","created":"2015-02-06","cited_by_count":3611},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1611.01144","title":"Categorical Reparameterization with Gumbel-Softmax","created":"2016-11-03","cited_by_count":2739},{"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":"2205.01917","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","created":"2022-05-04","cited_by_count":1274},{"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":"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":"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":"1804.02748","title":"Scaling Egocentric Vision: The EPIC-KITCHENS Dataset","created":"2018-04-08","cited_by_count":795},{"id":"1904.01766","title":"VideoBERT: A Joint Model for Video and Language Representation Learning","created":"2019-04-03","cited_by_count":703},{"id":"1904.00962","title":"Large Batch Optimization for Deep Learning: Training BERT in 76 minutes","created":"2019-04-01","cited_by_count":674},{"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":"2109.14084","title":"VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding","created":"2021-09-28","cited_by_count":602},{"id":"1611.05267","title":"Temporal Convolutional Networks for Action Segmentation and Detection","created":"2016-11-16","cited_by_count":508},{"id":"1912.06430","title":"End-to-End Learning of Visual Representations from Uncurated Instructional Videos","created":"2019-12-13","cited_by_count":507},{"id":"1711.08496","title":"Temporal Relational Reasoning in Videos","created":"2017-11-22","cited_by_count":324},{"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":"2203.14712","title":"Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activities","created":"2022-03-28","cited_by_count":287},{"id":"1705.02953","title":"Temporal Segment Networks for Action Recognition in Videos","created":"2017-05-08","cited_by_count":279},{"id":"2011.07231","title":"ActBERT: Learning Global-Local Video-Text Representations","created":"2020-11-14","cited_by_count":267},{"id":"2104.01633","title":"MIST: Multiple Instance Self-Training Framework for Video Anomaly Detection","created":"2021-04-04","cited_by_count":138},{"id":"2105.09996","title":"VLM: Task-agnostic Video-Language Model Pre-training for Video Understanding","created":"2021-05-20","cited_by_count":102},{"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":"2111.00273","title":"Cross-Modality Fusion Transformer for Multispectral Object Detection","created":"2021-10-30","cited_by_count":86},{"id":"2201.05078","title":"CLIP-Event: Connecting Text and Images with Event Structures","created":"2022-01-13","cited_by_count":86},{"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":"1901.02598","title":"D3TW: Discriminative Differentiable Dynamic Time Warping for Weakly Supervised Action Alignment and Segmentation","created":"2019-01-09","cited_by_count":83},{"id":"1904.04189","title":"Unsupervised learning of action classes with continuous temporal embedding","created":"2019-04-08","cited_by_count":76},{"id":"2006.15418","title":"Counting Out Time: Class Agnostic Video Repetition Counting in the Wild","created":"2020-06-27","cited_by_count":68},{"id":"2210.06031","title":"Long-Form Video-Language Pre-Training with Multimodal Temporal Contrastive Learning","created":"2022-10-12","cited_by_count":59},{"id":"2209.00638","title":"Unified Fully and Timestamp Supervised Temporal Action Segmentation via Sequence to Sequence Translation","created":"2022-09-01","cited_by_count":55},{"id":"2105.13353","title":"Unsupervised Action Segmentation by Joint Representation Learning and Online Clustering","created":"2021-05-27","cited_by_count":49},{"id":"2204.01018","title":"TransRAC: Encoding Multi-scale Temporal Correlation with Transformers for Repetitive Action Counting","created":"2022-04-03","cited_by_count":44},{"id":"2207.10362","title":"LocVTP: Video-Text Pre-training for Temporal Localization","created":"2022-07-21","cited_by_count":44},{"id":"2106.09212","title":"Long-Short Temporal Contrastive Learning of Video Transformers","created":"2021-06-17","cited_by_count":42},{"id":"2204.00325","title":"CAT-Det: Contrastively Augmented Transformer for Multi-modal 3D Object Detection","created":"2022-04-01","cited_by_count":32},{"id":"2203.14957","title":"Frame-wise Action Representations for Long Videos via Sequence Contrastive Learning","created":"2022-03-28","cited_by_count":27},{"id":"2112.06447","title":"SVIP: Sequence VerIfication for Procedures in Videos","created":"2021-12-13","cited_by_count":16},{"id":"2205.01657","title":"Cross-modal Representation Learning for Zero-shot Action Recognition","created":"2022-05-03","cited_by_count":15}],"next_cursor":null}