{"list":"other","total":55,"rows":[{"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":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"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":"2004.11362","title":"Supervised Contrastive Learning","created":"2020-04-23","cited_by_count":2829},{"id":"2107.07651","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","created":"2021-07-16","cited_by_count":1619},{"id":"2006.10029","title":"Big Self-Supervised Models are Strong Semi-Supervised Learners","created":"2020-06-17","cited_by_count":1380},{"id":"2109.14084","title":"VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding","created":"2021-09-28","cited_by_count":602},{"id":"1903.01945","title":"MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation","created":"2019-03-05","cited_by_count":373},{"id":"2202.10401","title":"Vision-Language Pre-Training with Triple Contrastive Learning","created":"2022-02-21","cited_by_count":212},{"id":"2208.03550","title":"Frozen CLIP Models are Efficient Video Learners","created":"2022-08-06","cited_by_count":182},{"id":"2303.07399","title":"RTMPose: Real-Time Multi-Person Pose Estimation based on MMPose","created":"2023-03-13","cited_by_count":175},{"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":"2208.10741","title":"Hierarchically Decomposed Graph Convolutional Networks for Skeleton-Based Action Recognition","created":"2022-08-23","cited_by_count":85},{"id":"1806.07110","title":"Modality Distillation with Multiple Stream Networks for Action Recognition","created":"2018-06-19","cited_by_count":83},{"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":"1803.10699","title":"Weakly-Supervised Action Segmentation with Iterative Soft Boundary Assignment","created":"2018-03-28","cited_by_count":74},{"id":"1703.08132","title":"Weakly Supervised Action Learning with RNN based Fine-to-coarse Modeling","created":"2017-03-23","cited_by_count":70},{"id":"1805.06875","title":"NeuralNetwork-Viterbi: A Framework for Weakly Supervised Video Learning","created":"2018-05-17","cited_by_count":67},{"id":"2303.03729","title":"Learning Discriminative Representations for Skeleton Based Action Recognition","created":"2023-03-07","cited_by_count":62},{"id":"1509.01947","title":"An end-to-end generative framework for video segmentation and recognition","created":"2015-09-07","cited_by_count":61},{"id":"1909.13155","title":"Weakly Supervised Energy-Based Learning for Action Segmentation","created":"2019-09-28","cited_by_count":53},{"id":"2105.13353","title":"Unsupervised Action Segmentation by Joint Representation Learning and Online Clustering","created":"2021-05-27","cited_by_count":49},{"id":"1407.1208","title":"Weakly Supervised Action Labeling in Videos Under Ordering Constraints","created":"2014-07-04","cited_by_count":48},{"id":"1610.02237","title":"Weakly supervised learning of actions from transcripts","created":"2016-10-07","cited_by_count":46},{"id":"2208.05318","title":"Generative Action Description Prompts for Skeleton-based Action Recognition","created":"2022-08-10","cited_by_count":43},{"id":"2010.14982","title":"Toyota Smarthome Untrimmed: Real-World Untrimmed Videos for Activity Detection","created":"2020-10-28","cited_by_count":42},{"id":"2307.07205","title":"Multimodal Motion Conditioned Diffusion Model for Skeleton-based Video Anomaly Detection","created":"2023-07-14","cited_by_count":42},{"id":"2105.08141","title":"VPN++: Rethinking Video-Pose embeddings for understanding Activities of Daily Living","created":"2021-05-17","cited_by_count":35},{"id":"2312.07526","title":"RTMO: Towards High-Performance One-Stage Real-Time Multi-Person Pose Estimation","created":"2023-12-12","cited_by_count":34},{"id":"2108.03619","title":"Learning an Augmented RGB Representation with Cross-Modal Knowledge Distillation for Action Detection","created":"2021-08-08","cited_by_count":32},{"id":"1904.03116","title":"Fast Weakly Supervised Action Segmentation Using Mutual Consistency","created":"2019-04-05","cited_by_count":30},{"id":"1912.10982","title":"DMCL: Distillation Multiple Choice Learning for Multimodal Action Recognition","created":"2019-12-23","cited_by_count":30},{"id":"2205.11169","title":"PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models","created":"2022-05-23","cited_by_count":30},{"id":"2109.01305","title":"Video Pose Distillation for Few-Shot, Fine-Grained Sports Action Recognition","created":"2021-09-03","cited_by_count":29},{"id":"2307.07483","title":"Multimodal Distillation for Egocentric Action Recognition","created":"2023-07-14","cited_by_count":28},{"id":"2204.10435","title":"PreTraM: Self-Supervised Pre-training via Connecting Trajectory and Map","created":"2022-04-21","cited_by_count":25},{"id":"2103.09458","title":"Learning Discriminative Prototypes with Dynamic Time Warping","created":"2021-03-17","cited_by_count":23},{"id":"2303.15167","title":"Prompt-Guided Zero-Shot Anomaly Action Recognition using Pretrained Deep Skeleton Features","created":"2023-03-27","cited_by_count":21},{"id":"2212.05638","title":"Cross-Modal Learning with 3D Deformable Attention for Action Recognition","created":"2022-12-12","cited_by_count":20},{"id":"2006.03732","title":"WOAD: Weakly Supervised Online Action Detection in Untrimmed Videos","created":"2020-06-05","cited_by_count":19},{"id":"2311.18840","title":"Just Add $\\pi$! Pose Induced Video Transformers for Understanding Activities of Daily Living","created":"2023-11-30","cited_by_count":19},{"id":"2203.13371","title":"FitCLIP: Refining Large-Scale Pretrained Image-Text Models for Zero-Shot Video Understanding Tasks","created":"2022-03-24","cited_by_count":16},{"id":"2210.11065","title":"MovieCLIP: Visual Scene Recognition in Movies","created":"2022-10-20","cited_by_count":16},{"id":"2308.14500","title":"LAC: Latent Action Composition for Skeleton-based Action Segmentation","created":"2023-08-28","cited_by_count":15},{"id":"2212.04761","title":"Leveraging Spatio-Temporal Dependency for Skeleton-Based Action Recognition","created":"2022-12-09","cited_by_count":13},{"id":"2301.00794","title":"STEPs: Self-Supervised Key Step Extraction and Localization from Unlabeled Procedural Videos","created":"2023-01-02","cited_by_count":13},{"id":"2203.13309","title":"Weakly-Supervised Online Action Segmentation in Multi-View Instructional Videos","created":"2022-03-24","cited_by_count":12},{"id":"2303.17285","title":"Decomposed Cross-modal Distillation for RGB-based Temporal Action Detection","created":"2023-03-30","cited_by_count":12},{"id":"2110.05697","title":"Hierarchical Modeling for Task Recognition and Action Segmentation in Weakly-Labeled Instructional Videos","created":"2021-10-12","cited_by_count":11},{"id":"2308.05681","title":"Hard No-Box Adversarial Attack on Skeleton-Based Human Action Recognition with Skeleton-Motion-Informed Gradient","created":"2023-08-10","cited_by_count":10},{"id":"2205.10227","title":"Label Anchored Contrastive Learning for Language Understanding","created":"2022-04-26","cited_by_count":7},{"id":"2309.09088","title":"Enhancing GAN-Based Vocoders with Contrastive Learning Under Data-limited Condition","created":"2023-09-16","cited_by_count":2}],"next_cursor":null}