{"list":"other","total":58,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"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":"2004.04730","title":"X3D: Expanding Architectures for Efficient Video Recognition","created":"2020-04-09","cited_by_count":637},{"id":"1703.09788","title":"Towards Automatic Learning of Procedures from Web Instructional Videos","created":"2017-03-28","cited_by_count":619},{"id":"1604.01753","title":"Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding","created":"2016-04-06","cited_by_count":537},{"id":"2112.01526","title":"MViTv2: Improved Multiscale Vision Transformers for Classification and Detection","created":"2021-12-02","cited_by_count":519},{"id":"1705.08421","title":"AVA: A Video Dataset of Spatio-temporally Localized Atomic Visual Actions","created":"2017-05-23","cited_by_count":449},{"id":"1602.03012","title":"EndoNet: A Deep Architecture for Recognition Tasks on Laparoscopic Videos","created":"2016-02-09","cited_by_count":367},{"id":"1907.09702","title":"BMN: Boundary-Matching Network for Temporal Action Proposal Generation","created":"2019-07-23","cited_by_count":329},{"id":"2208.02816","title":"Expanding Language-Image Pretrained Models for General Video Recognition","created":"2022-08-04","cited_by_count":321},{"id":"2202.07925","title":"ActionFormer: Localizing Moments of Actions with Transformers","created":"2022-02-16","cited_by_count":311},{"id":"1904.02811","title":"Video Classification with Channel-Separated Convolutional Networks","created":"2019-04-04","cited_by_count":290},{"id":"1911.11462","title":"G-TAD: Sub-Graph Localization for Temporal Action Detection","created":"2019-11-26","cited_by_count":249},{"id":"1806.11230","title":"Human Action Recognition and Prediction: A Survey","created":"2018-06-28","cited_by_count":227},{"id":"2005.00343","title":"The EPIC-KITCHENS Dataset: Collection, Challenges and Baselines","created":"2020-04-29","cited_by_count":225},{"id":"1909.03252","title":"Graph Convolutional Networks for Temporal Action Localization","created":"2019-09-07","cited_by_count":208},{"id":"2212.03640","title":"Fine-tuned CLIP Models are Efficient Video Learners","created":"2022-12-06","cited_by_count":179},{"id":"2303.07347","title":"TriDet: Temporal Action Detection with Relative Boundary Modeling","created":"2023-03-13","cited_by_count":142},{"id":"2003.10751","title":"TeCNO: Surgical Phase Recognition with Multi-Stage Temporal Convolutional Networks","created":"2020-03-24","cited_by_count":141},{"id":"2109.03223","title":"Rendezvous: Attention Mechanisms for the Recognition of Surgical Action Triplets in Endoscopic Videos","created":"2021-09-07","cited_by_count":141},{"id":"1905.09035","title":"What Would You Expect? Anticipating Egocentric Actions with Rolling-Unrolling LSTMs and Modality Attention","created":"2019-05-22","cited_by_count":105},{"id":"2011.14598","title":"Video Self-Stitching Graph Network for Temporal Action Localization","created":"2020-11-30","cited_by_count":104},{"id":"2208.02049","title":"AutoLaparo: A New Dataset of Integrated Multi-tasks for Image-guided Surgical Automation in Laparoscopic Hysterectomy","created":"2022-08-03","cited_by_count":85},{"id":"2203.14291","title":"Video Polyp Segmentation: A Deep Learning Perspective","created":"2022-03-27","cited_by_count":82},{"id":"2011.11479","title":"TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks","created":"2020-11-23","cited_by_count":77},{"id":"2002.08945","title":"Spatiotemporal Relationship Reasoning for Pedestrian Intent Prediction","created":"2020-02-20","cited_by_count":71},{"id":"2207.01297","title":"Revisiting Classifier: Transferring Vision-Language Models for Video Recognition","created":"2022-07-04","cited_by_count":71},{"id":"2307.11307","title":"EndoSurf: Neural Surface Reconstruction of Deformable Tissues with Stereo Endoscope Videos","created":"2023-07-21","cited_by_count":69},{"id":"2307.15220","title":"Learning Multi-modal Representations by Watching Hundreds of Surgical Video Lectures","created":"2023-07-27","cited_by_count":68},{"id":"2007.05405","title":"Recognition of Instrument-Tissue Interactions in Endoscopic Videos via Action Triplets","created":"2020-07-10","cited_by_count":66},{"id":"2107.12960","title":"Enriching Local and Global Contexts for Temporal Action Localization","created":"2021-07-27","cited_by_count":64},{"id":"2103.03873","title":"OperA: Attention-Regularized Transformers for Surgical Phase Recognition","created":"2021-03-05","cited_by_count":60},{"id":"2109.14956","title":"Comparative Validation of Machine Learning Algorithms for Surgical Workflow and Skill Analysis with the HeiChole Benchmark","created":"2021-09-30","cited_by_count":60},{"id":"1804.02675","title":"Anticipating Traffic Accidents with Adaptive Loss and Large-scale Incident DB","created":"2018-04-08","cited_by_count":51},{"id":"2301.00182","title":"Bidirectional Cross-Modal Knowledge Exploration for Video Recognition with Pre-trained Vision-Language Models","created":"2022-12-31","cited_by_count":49},{"id":"2005.03501","title":"Heidelberg Colorectal Data Set for Surgical Data Science in the Sensor Operating Room","created":"2020-05-07","cited_by_count":47},{"id":"2405.10075","title":"HecVL: Hierarchical Video-Language Pretraining for Zero-shot Surgical Phase Recognition","created":"2024-05-16","cited_by_count":42},{"id":"2104.03214","title":"Self-Supervised Learning for Semi-Supervised Temporal Action Proposal","created":"2021-04-07","cited_by_count":39},{"id":"1610.09278","title":"The TUM LapChole dataset for the M2CAI 2016 workflow challenge","created":"2016-10-28","cited_by_count":38},{"id":"1711.09726","title":"Exploiting the potential of unlabeled endoscopic video data with self-supervised learning","created":"2017-11-27","cited_by_count":33},{"id":"1909.10360","title":"RAUNet: Residual Attention U-Net for Semantic Segmentation of Cataract Surgical Instruments","created":"2019-09-23","cited_by_count":27},{"id":"1802.03243","title":"RSDNet: Learning to Predict Remaining Surgery Duration from Laparoscopic Videos Without Manual Annotations","created":"2018-02-09","cited_by_count":26},{"id":"1805.08569","title":"Less is More: Surgical Phase Recognition with Less Annotations through Self-Supervised Pre-training of CNN-LSTM Networks","created":"2018-05-22","cited_by_count":24},{"id":"1812.00033","title":"Learning from a tiny dataset of manual annotations: a teacher/student approach for surgical phase recognition","created":"2018-11-30","cited_by_count":21},{"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":"2203.12121","title":"Contrastive Transformer-based Multiple Instance Learning for Weakly Supervised Polyp Frame Detection","created":"2022-03-23","cited_by_count":20},{"id":"2310.13347","title":"NurViD: A Large Expert-Level Video Database for Nursing Procedure Activity Understanding","created":"2023-10-20","cited_by_count":20},{"id":"2210.16674","title":"Semantic-SuPer: A Semantic-aware Surgical Perception Framework for Endoscopic Tissue Identification, Reconstruction, and Tracking","created":"2022-10-29","cited_by_count":19},{"id":"1906.11586","title":"CaDIS: Cataract Dataset for Image Segmentation","created":"2019-06-27","cited_by_count":17},{"id":"2104.14280","title":"Relevance Detection in Cataract Surgery Videos by Spatio-Temporal Action Localization","created":"2021-04-29","cited_by_count":15},{"id":"2107.00875","title":"LensID: A CNN-RNN-Based Framework Towards Lens Irregularity Detection in Cataract Surgery Videos","created":"2021-07-02","cited_by_count":15},{"id":"2303.12370","title":"Weakly Supervised Video Representation Learning with Unaligned Text for Sequential Videos","created":"2023-03-22","cited_by_count":10},{"id":"2312.06295","title":"Cataract-1K: Cataract Surgery Dataset for Scene Segmentation, Phase Recognition, and Irregularity Detection","created":"2023-12-11","cited_by_count":8},{"id":"1702.03684","title":"Unsupervised temporal context learning using convolutional neural networks for laparoscopic workflow analysis","created":"2017-02-13","cited_by_count":7},{"id":"2004.09845","title":"LRTD: Long-Range Temporal Dependency based Active Learning for Surgical Workflow Recognition","created":"2020-04-21","cited_by_count":6},{"id":"2206.10491","title":"Bi-Calibration Networks for Weakly-Supervised Video Representation Learning","created":"2022-06-21","cited_by_count":4}],"next_cursor":null}