{"total":50,"rows":[{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620,"area":null},{"id":"2104.00650","title":"Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval","created":"2021-04-01","cited_by_count":1177,"area":null},{"id":"2307.06304","title":"Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution","created":"2023-07-12","cited_by_count":229,"area":null},{"id":"2212.08013","title":"FlexiViT: One Model for All Patch Sizes","created":"2022-12-15","cited_by_count":152,"area":null},{"id":"2201.04288","title":"Multiview Transformers for Video Recognition","created":"2022-01-12","cited_by_count":148,"area":null},{"id":"2106.11310","title":"Towards Long-Form Video Understanding","created":"2021-06-21","cited_by_count":146,"area":null},{"id":"2204.01692","title":"Long Movie Clip Classification with State-Space Video Models","created":"2022-04-04","cited_by_count":106,"area":null},{"id":"2106.05968","title":"Space-time Mixing Attention for Video Transformer","created":"2021-06-10","cited_by_count":84,"area":null},{"id":"2111.00772","title":"AdaPool: Exponential Adaptive Pooling for Information-Retaining Downsampling","created":"2021-11-01","cited_by_count":47,"area":null},{"id":"2108.09322","title":"MM-ViT: Multi-Modal Video Transformer for Compressed Video Action Recognition","created":"2021-08-20","cited_by_count":46,"area":null},{"id":"2105.07576","title":"Rethinking \"Batch\" in BatchNorm","created":"2021-05-17","cited_by_count":45,"area":null},{"id":"2105.02668","title":"VideoLT: Large-scale Long-tailed Video Recognition","created":"2021-05-06","cited_by_count":35,"area":null},{"id":"2212.00776","title":"ResFormer: Scaling ViTs with Multi-Resolution Training","created":"2022-12-01","cited_by_count":34,"area":null},{"id":"2203.10233","title":"DirecFormer: A Directed Attention in Transformer Approach to Robust Action Recognition","created":"2022-03-19","cited_by_count":31,"area":null},{"id":"2103.01302","title":"Coarse-Fine Networks for Temporal Activity Detection in Videos","created":"2021-03-01","cited_by_count":28,"area":null},{"id":"2101.00440","title":"Refining activation downsampling with SoftPool","created":"2021-01-02","cited_by_count":26,"area":null},{"id":"2103.15395","title":"No frame left behind: Full Video Action Recognition","created":"2021-03-29","cited_by_count":24,"area":null},{"id":"2103.16565","title":"Learning Representational Invariances for Data-Efficient Action Recognition","created":"2021-03-30","cited_by_count":22,"area":null},{"id":"2103.15233","title":"Low-Fidelity End-to-End Video Encoder Pre-training for Temporal Action Localization","created":"2021-03-28","cited_by_count":20,"area":null},{"id":"2309.16669","title":"Training a Large Video Model on a Single Machine in a Day","created":"2023-09-28","cited_by_count":20,"area":null},{"id":"2102.07624","title":"RMS-Net: Regression and Masking for Soccer Event Spotting","created":"2021-02-15","cited_by_count":19,"area":null},{"id":"2304.06028","title":"RECLIP: Resource-efficient CLIP by Training with Small Images","created":"2023-04-12","cited_by_count":16,"area":null},{"id":"2203.16755","title":"Stochastic Backpropagation: A Memory Efficient Strategy for Training Video Models","created":"2022-03-31","cited_by_count":14,"area":null},{"id":"2210.04889","title":"Turbo Training with Token Dropout","created":"2022-10-10","cited_by_count":14,"area":null},{"id":"2107.07572","title":"Globally Convergent Multilevel Training of Deep Residual Networks","created":"2021-07-15","cited_by_count":11,"area":null},{"id":"2109.15317","title":"Unsupervised Few-Shot Action Recognition via Action-Appearance Aligned Meta-Adaptation","created":"2021-09-30","cited_by_count":11,"area":null},{"id":"2110.14381","title":"Temporal-attentive Covariance Pooling Networks for Video Recognition","created":"2021-10-27","cited_by_count":11,"area":null},{"id":"2409.19429","title":"Fast Encoding and Decoding for Implicit Video Representation","created":"2024-09-28","cited_by_count":11,"area":null},{"id":"2305.14477","title":"A Block-Coordinate Approach of Multi-level Optimization with an Application to Physics-Informed Neural Networks","created":"2023-05-23","cited_by_count":7,"area":null},{"id":"2201.04022","title":"Condensing a Sequence to One Informative Frame for Video Recognition","created":"2022-01-11","cited_by_count":6,"area":null},{"id":"2312.13746","title":"Video Recognition in Portrait Mode","created":"2023-12-21","cited_by_count":6,"area":null},{"id":"2503.14237","title":"Make Your Training Flexible: Towards Deployment-Efficient Video Models","created":"2025-03-18","cited_by_count":6,"area":null},{"id":"2104.14538","title":"Distributed Multigrid Neural Solvers on Megavoxel Domains","created":"2021-04-29","cited_by_count":5,"area":null},{"id":"2201.04021","title":"Optimization Planning for 3D ConvNets","created":"2022-01-11","cited_by_count":5,"area":null},{"id":"2207.12730","title":"P2ANet: A Dataset and Benchmark for Dense Action Detection from Table Tennis Match Broadcasting Videos","created":"2022-07-26","cited_by_count":5,"area":null},{"id":"2410.00053","title":"Frequency-adaptive Multi-scale Deep Neural Networks","created":"2024-09-28","cited_by_count":5,"area":null},{"id":"2207.09927","title":"ViGAT: Bottom-up event recognition and explanation in video using factorized graph attention network","created":"2022-07-20","cited_by_count":4,"area":null},{"id":"2112.05754","title":"PyTorch Connectomics: A Scalable and Flexible Segmentation Framework for EM Connectomics","created":"2021-12-10","cited_by_count":3,"area":null},{"id":"2309.13353","title":"Beyond Grids: Exploring Elastic Input Sampling for Vision Transformers","created":"2023-09-23","cited_by_count":3,"area":null},{"id":"2205.05069","title":"Accelerating the Training of Video Super-Resolution Models","created":"2022-05-10","cited_by_count":2,"area":null},{"id":"2210.00129","title":"An In-depth Study of Stochastic Backpropagation","created":"2022-09-30","cited_by_count":2,"area":null},{"id":"2212.12141","title":"Human Activity Recognition in an Open World","created":"2022-12-23","cited_by_count":2,"area":null},{"id":"2307.07812","title":"Multiscale Memory Comparator Transformer for Few-Shot Video Segmentation","created":"2023-07-15","cited_by_count":2,"area":null},{"id":"2307.14866","title":"Sample Less, Learn More: Efficient Action Recognition via Frame Feature Restoration","created":"2023-07-27","cited_by_count":2,"area":null},{"id":"2208.08438","title":"Learning to Structure an Image with Few Colors and Beyond","created":"2022-08-17","cited_by_count":1,"area":null},{"id":"2209.11316","title":"FuTH-Net: Fusing Temporal Relations and Holistic Features for Aerial Video Classification","created":"2022-09-22","cited_by_count":1,"area":null},{"id":"2403.02243","title":"Better Schedules for Low Precision Training of Deep Neural Networks","created":"2024-03-04","cited_by_count":1,"area":null},{"id":"2409.18013","title":"Spatiotemporal Graph Learning with Direct Volumetric Information Passing and Feature Enhancement","created":"2024-09-26","cited_by_count":1,"area":null},{"id":"2205.01721","title":"In Defense of Image Pre-Training for Spatiotemporal Recognition","created":"2022-05-03","cited_by_count":0,"area":null},{"id":"2404.07999","title":"A Multi-Level Framework for Accelerating Training Transformer Models","created":"2024-04-07","cited_by_count":0,"area":null}],"next_cursor":null}