{"list":"other","total":57,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1910.01108","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","created":"2019-10-02","cited_by_count":4307},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1812.03982","title":"SlowFast Networks for Video Recognition","created":"2018-12-10","cited_by_count":1867},{"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":"1711.11248","title":"A Closer Look at Spatiotemporal Convolutions for Action Recognition","created":"2017-11-30","cited_by_count":1143},{"id":"2106.13230","title":"Video Swin Transformer","created":"2021-06-24","cited_by_count":1091},{"id":"1608.00859","title":"Temporal Segment Networks: Towards Good Practices for Deep Action Recognition","created":"2016-08-02","cited_by_count":902},{"id":"2104.11227","title":"Multiscale Vision Transformers","created":"2021-04-22","cited_by_count":897},{"id":"1811.08383","title":"TSM: Temporal Shift Module for Efficient Video Understanding","created":"2018-11-20","cited_by_count":856},{"id":"2004.04730","title":"X3D: Expanding Architectures for Efficient Video Recognition","created":"2020-04-09","cited_by_count":637},{"id":"2109.14084","title":"VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding","created":"2021-09-28","cited_by_count":602},{"id":"2112.01526","title":"MViTv2: Improved Multiscale Vision Transformers for Classification and Detection","created":"2021-12-02","cited_by_count":519},{"id":"1806.07011","title":"VirtualHome: Simulating Household Activities via Programs","created":"2018-06-19","cited_by_count":415},{"id":"2206.06488","title":"Multimodal Learning with Transformers: A Survey","created":"2022-06-13","cited_by_count":400},{"id":"1711.10305","title":"Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks","created":"2017-11-28","cited_by_count":387},{"id":"2109.08472","title":"ActionCLIP: A New Paradigm for Video Action Recognition","created":"2021-09-17","cited_by_count":320},{"id":"2203.14712","title":"Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activities","created":"2022-03-28","cited_by_count":287},{"id":"2004.06704","title":"FineGym: A Hierarchical Video Dataset for Fine-grained Action Understanding","created":"2020-04-14","cited_by_count":234},{"id":"2005.02190","title":"Rolling-Unrolling LSTMs for Action Anticipation from First-Person Video","created":"2020-05-04","cited_by_count":120},{"id":"1811.02307","title":"Toward Driving Scene Understanding: A Dataset for Learning Driver Behavior and Causal Reasoning","created":"2018-11-06","cited_by_count":102},{"id":"2205.01580","title":"Better plain ViT baselines for ImageNet-1k","created":"2022-05-03","cited_by_count":98},{"id":"2007.00394","title":"The IKEA ASM Dataset: Understanding People Assembling Furniture through Actions, Objects and Pose","created":"2020-07-01","cited_by_count":95},{"id":"1812.01289","title":"Timeception for Complex Action Recognition","created":"2018-12-04","cited_by_count":89},{"id":"2106.11149","title":"OadTR: Online Action Detection with Transformers","created":"2021-06-21","cited_by_count":83},{"id":"2307.16368","title":"AntGPT: Can Large Language Models Help Long-term Action Anticipation from Videos?","created":"2023-07-31","cited_by_count":81},{"id":"1911.06978","title":"Grounding Human-to-Vehicle Advice for Self-driving Vehicles","created":"2019-11-16","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":"1703.08132","title":"Weakly Supervised Action Learning with RNN based Fine-to-coarse Modeling","created":"2017-03-23","cited_by_count":70},{"id":"1607.01794","title":"VideoLSTM Convolves, Attends and Flows for Action Recognition","created":"2016-07-06","cited_by_count":60},{"id":"2101.01600","title":"Learning the Predictability of the Future","created":"2021-01-01","cited_by_count":49},{"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":"2310.17323","title":"IndustReal: A Dataset for Procedure Step Recognition Handling Execution Errors in Egocentric Videos in an Industrial-Like Setting","created":"2023-10-26","cited_by_count":48},{"id":"2108.09322","title":"MM-ViT: Multi-Modal Video Transformer for Compressed Video Action Recognition","created":"2021-08-20","cited_by_count":46},{"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":"2404.01933","title":"PREGO: online mistake detection in PRocedural EGOcentric videos","created":"2024-04-02","cited_by_count":39},{"id":"2008.01148","title":"HAMLET: A Hierarchical Multimodal Attention-based Human Activity Recognition Algorithm","created":"2020-08-03","cited_by_count":29},{"id":"2003.01920","title":"ETRI-Activity3D: A Large-Scale RGB-D Dataset for Robots to Recognize Daily Activities of the Elderly","created":"2020-03-04","cited_by_count":26},{"id":"2209.05700","title":"Vision Transformers for Action Recognition: A Survey","created":"2022-09-13","cited_by_count":25},{"id":"2311.00180","title":"Object-centric Video Representation for Long-term Action Anticipation","created":"2023-10-31","cited_by_count":24},{"id":"2011.08652","title":"3D CNNs with Adaptive Temporal Feature Resolutions","created":"2020-11-17","cited_by_count":15},{"id":"2203.16795","title":"Deformable Video Transformer","created":"2022-03-31","cited_by_count":15},{"id":"2404.05559","title":"TIM: A Time Interval Machine for Audio-Visual Action Recognition","created":"2024-04-08","cited_by_count":15},{"id":"2306.15045","title":"Action Anticipation with Goal Consistency","created":"2023-06-26","cited_by_count":12}],"next_cursor":null}