{"total":21,"rows":[{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620,"area":null},{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620,"area":null},{"id":"2104.11178","title":"VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text","created":"2021-04-22","cited_by_count":429,"area":null},{"id":"2106.05392","title":"Keeping Your Eye on the Ball: Trajectory Attention in Video Transformers","created":"2021-06-09","cited_by_count":224,"area":null},{"id":"2111.15667","title":"Adaptive Token Sampling For Efficient Vision Transformers","created":"2021-11-30","cited_by_count":183,"area":null},{"id":"2201.04288","title":"Multiview Transformers for Video Recognition","created":"2022-01-12","cited_by_count":148,"area":null},{"id":"2106.05968","title":"Space-time Mixing Attention for Video Transformer","created":"2021-06-10","cited_by_count":84,"area":null},{"id":"2201.05991","title":"Video Transformers: A Survey","created":"2022-01-16","cited_by_count":63,"area":null},{"id":"2111.12993","title":"PolyViT: Co-training Vision Transformers on Images, Videos and Audio","created":"2021-11-25","cited_by_count":58,"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":"2108.11575","title":"Shifted Chunk Transformer for Spatio-Temporal Representational Learning","created":"2021-08-26","cited_by_count":20,"area":null},{"id":"2307.06947","title":"Video-FocalNets: Spatio-Temporal Focal Modulation for Video Action Recognition","created":"2023-07-13","cited_by_count":18,"area":null},{"id":"2203.08897","title":"Gate-Shift-Fuse for Video Action Recognition","created":"2022-03-16","cited_by_count":15,"area":null},{"id":"2105.07085","title":"MutualNet: Adaptive ConvNet via Mutual Learning from Different Model Configurations","created":"2021-05-14","cited_by_count":13,"area":null},{"id":"2106.03959","title":"Generative Flows with Invertible Attentions","created":"2021-06-07","cited_by_count":13,"area":null},{"id":"2102.05348","title":"Regional Attention with Architecture-Rebuilt 3D Network for RGB-D Gesture Recognition","created":"2021-02-10","cited_by_count":10,"area":null},{"id":"2202.02212","title":"Video Violence Recognition and Localization Using a Semi-Supervised Hard Attention Model","created":"2022-02-04","cited_by_count":6,"area":null},{"id":"2208.01753","title":"Two-Stream Transformer Architecture for Long Video Understanding","created":"2022-08-02","cited_by_count":4,"area":null},{"id":"2107.00451","title":"VideoLightFormer: Lightweight Action Recognition using Transformers","created":"2021-07-01","cited_by_count":3,"area":null},{"id":"2302.04064","title":"Weakly-supervised Representation Learning for Video Alignment and Analysis","created":"2023-02-08","cited_by_count":3,"area":null},{"id":"2111.07547","title":"Searching for TrioNet: Combining Convolution with Local and Global Self-Attention","created":"2021-11-15","cited_by_count":2,"area":null}],"next_cursor":null}