{"list":"other","total":56,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"2111.00396","title":"Efficiently Modeling Long Sequences with Structured State Spaces","created":"2021-10-31","cited_by_count":2465},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620},{"id":"2311.10122","title":"Video-LLaVA: Learning United Visual Representation by Alignment Before Projection","created":"2023-11-16","cited_by_count":1402},{"id":"2306.05424","title":"Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models","created":"2023-06-08","cited_by_count":1062},{"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":"1707.02968","title":"Revisiting Unreasonable Effectiveness of Data in Deep Learning Era","created":"2017-07-10","cited_by_count":919},{"id":"2104.11227","title":"Multiscale Vision Transformers","created":"2021-04-22","cited_by_count":897},{"id":"1804.02748","title":"Scaling Egocentric Vision: The EPIC-KITCHENS Dataset","created":"2018-04-08","cited_by_count":795},{"id":"1604.01753","title":"Hollywood in Homes: Crowdsourcing Data Collection for Activity Understanding","created":"2016-04-06","cited_by_count":537},{"id":"2312.02051","title":"TimeChat: A Time-sensitive Multimodal Large Language Model for Long Video Understanding","created":"2023-12-04","cited_by_count":406},{"id":"1903.01945","title":"MS-TCN: Multi-Stage Temporal Convolutional Network for Action Segmentation","created":"2019-03-05","cited_by_count":373},{"id":"2402.15648","title":"MambaIR: A Simple Baseline for Image Restoration with State-Space Model","created":"2024-02-23","cited_by_count":352},{"id":"1907.09702","title":"BMN: Boundary-Matching Network for Temporal Action Proposal Generation","created":"2019-07-23","cited_by_count":329},{"id":"1806.02964","title":"BSN: Boundary Sensitive Network for Temporal Action Proposal Generation","created":"2018-06-08","cited_by_count":271},{"id":"1704.06228","title":"Temporal Action Detection with Structured Segment Networks","created":"2017-04-20","cited_by_count":267},{"id":"2401.13560","title":"SegMamba: Long-range Sequential Modeling Mamba For 3D Medical Image Segmentation","created":"2024-01-24","cited_by_count":266},{"id":"1911.11462","title":"G-TAD: Sub-Graph Localization for Temporal Action Detection","created":"2019-11-26","cited_by_count":249},{"id":"2212.03640","title":"Fine-tuned CLIP Models are Efficient Video Learners","created":"2022-12-06","cited_by_count":179},{"id":"2402.03302","title":"Swin-UMamba: Mamba-based UNet with ImageNet-based pretraining","created":"2024-02-05","cited_by_count":179},{"id":"1703.07814","title":"R-C3D: Region Convolutional 3D Network for Temporal Activity Detection","created":"2017-03-22","cited_by_count":161},{"id":"1605.08110","title":"Video Summarization with Long Short-term Memory","created":"2016-05-26","cited_by_count":142},{"id":"1710.06236","title":"Single Shot Temporal Action Detection","created":"2017-10-17","cited_by_count":123},{"id":"2107.00650","title":"CLIP-It! Language-Guided Video Summarization","created":"2021-07-01","cited_by_count":99},{"id":"2402.15584","title":"State Space Models for Event Cameras","created":"2024-02-23","cited_by_count":75},{"id":"2402.12192","title":"Pan-Mamba: Effective pan-sharpening with State Space Model","created":"2024-02-19","cited_by_count":73},{"id":"1812.01969","title":"Summarizing Videos with Attention","created":"2018-12-05","cited_by_count":69},{"id":"2104.09496","title":"Temporal Query Networks for Fine-grained Video Understanding","created":"2021-04-19","cited_by_count":68},{"id":"2303.07284","title":"Align and Attend: Multimodal Summarization with Dual Contrastive Losses","created":"2023-03-13","cited_by_count":65},{"id":"1903.11328","title":"Rethinking the Evaluation of Video Summaries","created":"2019-03-27","cited_by_count":62},{"id":"2212.14427","title":"Efficient Movie Scene Detection using State-Space Transformers","created":"2022-12-29","cited_by_count":51},{"id":"2010.14982","title":"Toyota Smarthome Untrimmed: Real-World Untrimmed Videos for Activity Detection","created":"2020-10-28","cited_by_count":42},{"id":"2112.03902","title":"MS-TCT: Multi-Scale Temporal ConvTransformer for Action Detection","created":"2021-12-07","cited_by_count":42},{"id":"1803.06316","title":"Temporal Gaussian Mixture Layer for Videos","created":"2018-03-16","cited_by_count":40},{"id":"2103.03027","title":"Modeling Multi-Label Action Dependencies for Temporal Action Localization","created":"2021-03-04","cited_by_count":32},{"id":"1712.01938","title":"Learning Latent Super-Events to Detect Multiple Activities in Videos","created":"2017-12-05","cited_by_count":30},{"id":"2103.01302","title":"Coarse-Fine Networks for Temporal Activity Detection in Videos","created":"2021-03-01","cited_by_count":28},{"id":"2305.15701","title":"Action Sensitivity Learning for Temporal Action Localization","created":"2023-05-25","cited_by_count":28},{"id":"2104.11530","title":"Supervised Video Summarization via Multiple Feature Sets with Parallel Attention","created":"2021-04-23","cited_by_count":26},{"id":"2211.09119","title":"Token Turing Machines","created":"2022-11-16","cited_by_count":25},{"id":"2405.11905","title":"CSTA: CNN-based Spatiotemporal Attention for Video Summarization","created":"2024-05-20","cited_by_count":23},{"id":"2210.11035","title":"PointTAD: Multi-Label Temporal Action Detection with Learnable Query Points","created":"2022-10-20","cited_by_count":22},{"id":"2201.02494","title":"Progressive Video Summarization via Multimodal Self-supervised Learning","created":"2022-01-07","cited_by_count":21},{"id":"2404.00653","title":"Dual DETRs for Multi-Label Temporal Action Detection","created":"2024-03-31","cited_by_count":20},{"id":"2110.13473","title":"CTRN: Class-Temporal Relational Network for Action Detection","created":"2021-10-26","cited_by_count":15},{"id":"2008.08360","title":"Query Twice: Dual Mixture Attention Meta Learning for Video Summarization","created":"2020-08-19","cited_by_count":14},{"id":"2404.07705","title":"ViM-UNet: Vision Mamba for Biomedical Segmentation","created":"2024-04-11","cited_by_count":11},{"id":"2112.13478","title":"Video Joint Modelling Based on Hierarchical Transformer for Co-summarization","created":"2021-12-27","cited_by_count":10},{"id":"1812.06203","title":"TAN: Temporal Aggregation Network for Dense Multi-label Action Recognition","created":"2018-12-14","cited_by_count":9}],"next_cursor":null}