{"list":"other","total":61,"rows":[{"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":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"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":"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":"2311.10122","title":"Video-LLaVA: Learning United Visual Representation by Alignment Before Projection","created":"2023-11-16","cited_by_count":1402},{"id":"1706.04261","title":"The \"something something\" video database for learning and evaluating visual common sense","created":"2017-06-13","cited_by_count":1103},{"id":"2401.09417","title":"Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model","created":"2024-01-17","cited_by_count":1056},{"id":"2104.11227","title":"Multiscale Vision Transformers","created":"2021-04-22","cited_by_count":897},{"id":"2208.04933","title":"Simplified State Space Layers for Sequence Modeling","created":"2022-08-09","cited_by_count":788},{"id":"2110.13985","title":"Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layers","created":"2021-10-26","cited_by_count":608},{"id":"2303.16727","title":"VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking","created":"2023-03-29","cited_by_count":528},{"id":"2206.11893","title":"On the Parameterization and Initialization of Diagonal State Space Models","created":"2022-06-23","cited_by_count":424},{"id":"2303.06349","title":"Resurrecting Recurrent Neural Networks for Long Sequences","created":"2023-03-11","cited_by_count":408},{"id":"2310.01852","title":"LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment","created":"2023-10-03","cited_by_count":370},{"id":"1903.02874","title":"COIN: A Large-scale Dataset for Comprehensive Instructional Video Analysis","created":"2019-03-07","cited_by_count":318},{"id":"1907.06987","title":"A Short Note on the Kinetics-700 Human Action Dataset","created":"2019-07-15","cited_by_count":310},{"id":"2406.04264","title":"MLVU: Benchmarking Multi-task Long Video Understanding","created":"2024-06-06","cited_by_count":292},{"id":"2306.00989","title":"Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles","created":"2023-06-01","cited_by_count":290},{"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},{"id":"2407.08083","title":"MambaVision: A Hybrid Mamba-Transformer Vision Backbone","created":"2024-07-10","cited_by_count":224},{"id":"2201.08377","title":"Omnivore: A Single Model for Many Visual Modalities","created":"2022-01-20","cited_by_count":215},{"id":"2201.04676","title":"UniFormer: Unified Transformer for Efficient Spatiotemporal Representation Learning","created":"2022-01-12","cited_by_count":184},{"id":"2208.03550","title":"Frozen CLIP Models are Efficient Video Learners","created":"2022-08-06","cited_by_count":182},{"id":"2212.08013","title":"FlexiViT: One Model for All Patch Sizes","created":"2022-12-15","cited_by_count":152},{"id":"2302.03024","title":"AIM: Adapting Image Models for Efficient Video Action Recognition","created":"2023-02-06","cited_by_count":148},{"id":"2106.11310","title":"Towards Long-Form Video Understanding","created":"2021-06-21","cited_by_count":146},{"id":"2008.01065","title":"Memory-augmented Dense Predictive Coding for Video Representation Learning","created":"2020-08-03","cited_by_count":137},{"id":"2206.12037","title":"How to Train Your HiPPO: State Space Models with Generalized Orthogonal Basis Projections","created":"2022-06-24","cited_by_count":122},{"id":"2305.13035","title":"Getting ViT in Shape: Scaling Laws for Compute-Optimal Model Design","created":"2023-05-22","cited_by_count":89},{"id":"2504.02259","title":"T*: Re-thinking Temporal Search for Long-Form Video Understanding","created":"2025-04-03","cited_by_count":82},{"id":"2403.07392","title":"ViT-CoMer: Vision Transformer with Convolutional Multi-scale Feature Interaction for Dense Predictions","created":"2024-03-12","cited_by_count":66},{"id":"2404.04346","title":"Koala: Key frame-conditioned long video-LLM","created":"2024-04-05","cited_by_count":57},{"id":"2411.05222","title":"Don't Look Twice: Faster Video Transformers with Run-Length Tokenization","created":"2024-11-07","cited_by_count":43},{"id":"2308.11358","title":"How Much Temporal Long-Term Context is Needed for Action Segmentation?","created":"2023-08-22","cited_by_count":36},{"id":"2212.00776","title":"ResFormer: Scaling ViTs with Multi-Resolution Training","created":"2022-12-01","cited_by_count":34},{"id":"2304.02560","title":"VicTR: Video-conditioned Text Representations for Activity Recognition","created":"2023-04-05","cited_by_count":28},{"id":"2105.00067","title":"Unsupervised Discriminative Embedding for Sub-Action Learning in Complex Activities","created":"2021-04-30","cited_by_count":26},{"id":"2403.18361","title":"ViTAR: Vision Transformer with Any Resolution","created":"2024-03-27","cited_by_count":25},{"id":"2405.06887","title":"FineParser: A Fine-grained Spatio-temporal Action Parser for Human-centric Action Quality Assessment","created":"2024-05-11","cited_by_count":25},{"id":"2312.05719","title":"DVANet: Disentangling View and Action Features for Multi-View Action Recognition","created":"2023-12-10","cited_by_count":19},{"id":"2209.01425","title":"Dynamic Spatio-Temporal Specialization Learning for Fine-Grained Action Recognition","created":"2022-09-03","cited_by_count":17},{"id":"2503.20781","title":"BASKET: A Large-Scale Video Dataset for Fine-Grained Skill Estimation","created":"2025-03-26","cited_by_count":17},{"id":"2312.01897","title":"Adapting Short-Term Transformers for Action Detection in Untrimmed Videos","created":"2023-12-04","cited_by_count":16},{"id":"2308.13077","title":"Preserving Modality Structure Improves Multi-Modal Learning","created":"2023-08-24","cited_by_count":13},{"id":"2311.18825","title":"CAST: Cross-Attention in Space and Time for Video Action Recognition","created":"2023-11-30","cited_by_count":12},{"id":"2403.11999","title":"HIRI-ViT: Scaling Vision Transformer with High Resolution Inputs","created":"2024-03-18","cited_by_count":12},{"id":"2312.13008","title":"No More Shortcuts: Realizing the Potential of Temporal Self-Supervision","created":"2023-12-20","cited_by_count":11},{"id":"2503.12009","title":"UniMamba: Unified Spatial-Channel Representation Learning with Group-Efficient Mamba for LiDAR-based 3D Object Detection","created":"2025-03-15","cited_by_count":10},{"id":"2211.09992","title":"Look More but Care Less in Video Recognition","created":"2022-11-18","cited_by_count":6},{"id":"2503.14237","title":"Make Your Training Flexible: Towards Deployment-Efficient Video Models","created":"2025-03-18","cited_by_count":6},{"id":"2407.09073","title":"Open Vocabulary Multi-Label Video Classification","created":"2024-07-12","cited_by_count":5},{"id":"2510.11204","title":"Class Prototypes based Contrastive Learning for Classifying Multi-Label and Fine-Grained Educational Videos","created":"2025-10-13","cited_by_count":4},{"id":"2501.08837","title":"MANTA: Diffusion Mamba for Efficient and Effective Stochastic Long-Term Dense Anticipation","created":"2025-01-15","cited_by_count":3},{"id":"2303.14817","title":"Frame Flexible Network","created":"2023-03-26","cited_by_count":2},{"id":"2507.15212","title":"MeshMamba: State Space Models for Articulated 3D Mesh Generation and Reconstruction","created":"2025-07-21","cited_by_count":2}],"next_cursor":null}