{"list":"other","total":51,"rows":[{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"2111.00396","title":"Efficiently Modeling Long Sequences with Structured State Spaces","created":"2021-10-31","cited_by_count":2465},{"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":"2203.12602","title":"VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training","created":"2022-03-23","cited_by_count":1322},{"id":"2106.13230","title":"Video Swin Transformer","created":"2021-06-24","cited_by_count":1091},{"id":"2401.09417","title":"Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model","created":"2024-01-17","cited_by_count":1056},{"id":"2401.10166","title":"VMamba: Visual State Space Model","created":"2024-01-18","cited_by_count":969},{"id":"2008.07669","title":"HiPPO: Recurrent Memory with Optimal Polynomial Projections","created":"2020-08-17","cited_by_count":605},{"id":"2303.16727","title":"VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking","created":"2023-03-29","cited_by_count":528},{"id":"1704.06888","title":"Time-Contrastive Networks: Self-Supervised Learning from Video","created":"2017-04-23","cited_by_count":459},{"id":"1502.04681","title":"Unsupervised Learning of Video Representations using LSTMs","created":"2015-02-16","cited_by_count":435},{"id":"2205.09113","title":"Masked Autoencoders As Spatiotemporal Learners","created":"2022-05-18","cited_by_count":429},{"id":"2008.03800","title":"Spatiotemporal Contrastive Video Representation Learning","created":"2020-08-09","cited_by_count":372},{"id":"1602.03012","title":"EndoNet: A Deep Architecture for Recognition Tasks on Laparoscopic Videos","created":"2016-02-09","cited_by_count":367},{"id":"2403.06977","title":"VideoMamba: State Space Model for Efficient Video Understanding","created":"2024-03-11","cited_by_count":328},{"id":"2212.14532","title":"Scale-MAE: A Scale-Aware Masked Autoencoder for Multiscale Geospatial Representation Learning","created":"2022-12-30","cited_by_count":308},{"id":"1708.01246","title":"Unsupervised Representation Learning by Sorting Sequences","created":"2017-08-03","cited_by_count":221},{"id":"2104.14558","title":"A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning","created":"2021-04-29","cited_by_count":214},{"id":"2206.13559","title":"ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learning","created":"2022-06-27","cited_by_count":193},{"id":"2004.06130","title":"SpeedNet: Learning the Speediness in Videos","created":"2020-04-13","cited_by_count":171},{"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":"1904.04289","title":"SCSampler: Sampling Salient Clips from Video for Efficient Action Recognition","created":"2019-04-08","cited_by_count":134},{"id":"2203.14291","title":"Video Polyp Segmentation: A Deep Learning Perspective","created":"2022-03-27","cited_by_count":82},{"id":"2305.14344","title":"Siamese Masked Autoencoders","created":"2023-05-23","cited_by_count":76},{"id":"2306.16741","title":"Foundation Model for Endoscopy Video Analysis via Large-scale Self-supervised Pre-train","created":"2023-06-29","cited_by_count":75},{"id":"2109.15130","title":"Motion-aware Contrastive Video Representation Learning via Foreground-background Merging","created":"2021-09-30","cited_by_count":45},{"id":"2112.03624","title":"Time-Equivariant Contrastive Video Representation Learning","created":"2021-12-07","cited_by_count":44},{"id":"2211.09120","title":"AdaMAE: Adaptive Masking for Efficient Spatiotemporal Learning with Masked Autoencoders","created":"2022-11-16","cited_by_count":43},{"id":"2104.10824","title":"Colonoscopy Polyp Detection and Classification: Dataset Creation and Comparative Evaluations","created":"2021-04-22","cited_by_count":38},{"id":"2204.03946","title":"Probabilistic Representations for Video Contrastive Learning","created":"2022-04-08","cited_by_count":34},{"id":"2309.07911","title":"Disentangling Spatial and Temporal Learning for Efficient Image-to-Video Transfer Learning","created":"2023-09-14","cited_by_count":32},{"id":"2308.12962","title":"Motion-Guided Masking for Spatiotemporal Representation Learning","created":"2023-08-24","cited_by_count":30},{"id":"1809.04094","title":"FIVR: Fine-grained Incident Video Retrieval","created":"2018-09-11","cited_by_count":26},{"id":"1904.07073","title":"A deep learning framework for quality assessment and restoration in video endoscopy","created":"2019-04-15","cited_by_count":24},{"id":"2207.12795","title":"Static and Dynamic Concepts for Self-supervised Video Representation Learning","created":"2022-07-26","cited_by_count":23},{"id":"2308.12394","title":"Self-Supervised Learning for Endoscopic Video Analysis","created":"2023-08-23","cited_by_count":22},{"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":"2402.19082","title":"VideoMAC: Video Masked Autoencoders Meet ConvNets","created":"2024-02-29","cited_by_count":20},{"id":"2204.03101","title":"Hierarchical Self-supervised Representation Learning for Movie Understanding","created":"2022-04-06","cited_by_count":19},{"id":"2107.03609","title":"Multi-frame Collaboration for Effective Endoscopic Video Polyp Detection via Spatial-Temporal Feature Transformation","created":"2021-07-08","cited_by_count":15},{"id":"2303.12001","title":"ViC-MAE: Self-Supervised Representation Learning from Images and Video with Contrastive Masked Autoencoders","created":"2023-03-21","cited_by_count":14},{"id":"2503.15096","title":"When the Future Becomes the Past: Taming Temporal Correspondence for Self-supervised Video Representation Learning","created":"2025-03-19","cited_by_count":14},{"id":"2407.15566","title":"Not All Pairs are Equal: Hierarchical Learning for Average-Precision-Oriented Video Retrieval","created":"2024-07-22","cited_by_count":9},{"id":"2306.08591","title":"Self-Supervised Polyp Re-Identification in Colonoscopy","created":"2023-06-14","cited_by_count":8},{"id":"2011.12957","title":"PS-DeVCEM: Pathology-sensitive deep learning model for video capsule endoscopy based on weakly labeled data","created":"2020-11-22","cited_by_count":6}],"next_cursor":null}