{"list":"other","total":57,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1909.13719","title":"RandAugment: Practical automated data augmentation with a reduced search space","created":"2019-09-30","cited_by_count":2269},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"id":"2203.12602","title":"VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training","created":"2022-03-23","cited_by_count":1322},{"id":"2205.01917","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","created":"2022-05-04","cited_by_count":1274},{"id":"1801.07455","title":"Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition","created":"2018-01-23","cited_by_count":1209},{"id":"1803.02155","title":"Self-Attention with Relative Position Representations","created":"2018-03-06","cited_by_count":1120},{"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":"2106.13230","title":"Video Swin Transformer","created":"2021-06-24","cited_by_count":1091},{"id":"2205.13535","title":"AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition","created":"2022-05-26","cited_by_count":719},{"id":"2104.08860","title":"CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval","created":"2021-04-18","cited_by_count":651},{"id":"2112.04482","title":"FLAVA: A Foundational Language And Vision Alignment Model","created":"2021-12-08","cited_by_count":649},{"id":"1905.04757","title":"NTU RGB+D 120: A Large-Scale Benchmark for 3D Human Activity Understanding","created":"2019-05-12","cited_by_count":533},{"id":"2404.08471","title":"Revisiting Feature Prediction for Learning Visual Representations from Video","created":"2024-02-15","cited_by_count":531},{"id":"2311.01378","title":"Vision-Language Foundation Models as Effective Robot Imitators","created":"2023-11-02","cited_by_count":349},{"id":"2109.08472","title":"ActionCLIP: A New Paradigm for Video Action Recognition","created":"2021-09-17","cited_by_count":320},{"id":"2403.15377","title":"InternVideo2: Scaling Foundation Models for Multimodal Video Understanding","created":"2024-03-22","cited_by_count":317},{"id":"2112.04478","title":"Prompting Visual-Language Models for Efficient Video Understanding","created":"2021-12-08","cited_by_count":310},{"id":"2207.07285","title":"X-CLIP: End-to-End Multi-grained Contrastive Learning for Video-Text Retrieval","created":"2022-07-15","cited_by_count":280},{"id":"2206.13559","title":"ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learning","created":"2022-06-27","cited_by_count":193},{"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":"2302.03024","title":"AIM: Adapting Image Models for Efficient Video Action Recognition","created":"2023-02-06","cited_by_count":148},{"id":"2211.09552","title":"UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer","created":"2022-11-17","cited_by_count":116},{"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":"2304.03307","title":"Vita-CLIP: Video and text adaptive CLIP via Multimodal Prompting","created":"2023-04-06","cited_by_count":91},{"id":"2403.14548","title":"DINO-Tracker: Taming DINO for Self-Supervised Point Tracking in a Single Video","created":"2024-03-21","cited_by_count":64},{"id":"2407.20179","title":"Theia: Distilling Diverse Vision Foundation Models for Robot Learning","created":"2024-07-29","cited_by_count":61},{"id":"2301.11116","title":"Revisiting Temporal Modeling for CLIP-based Image-to-Video Knowledge Transferring","created":"2023-01-26","cited_by_count":58},{"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":"2304.10465","title":"Implicit Temporal Modeling with Learnable Alignment for Video Recognition","created":"2023-04-20","cited_by_count":46},{"id":"2310.19522","title":"Are Natural Domain Foundation Models Useful for Medical Image Classification?","created":"2023-10-30","cited_by_count":46},{"id":"2310.02835","title":"Delving into CLIP latent space for Video Anomaly Recognition","created":"2023-10-04","cited_by_count":27},{"id":"2203.00927","title":"TransDARC: Transformer-based Driver Activity Recognition with Latent Space Feature Calibration","created":"2022-03-02","cited_by_count":25},{"id":"1807.06980","title":"Video Time: Properties, Encoders and Evaluation","created":"2018-07-18","cited_by_count":19},{"id":"2308.01313","title":"PerceptionCLIP: Visual Classification by Inferring and Conditioning on Contexts","created":"2023-08-02","cited_by_count":17},{"id":"2404.00262","title":"Image-to-Image Matching via Foundation Models: A New Perspective for Open-Vocabulary Semantic Segmentation","created":"2024-03-30","cited_by_count":15},{"id":"2307.03166","title":"VideoGLUE: Video General Understanding Evaluation of Foundation Models","created":"2023-07-06","cited_by_count":14},{"id":"2312.08010","title":"EZ-CLIP: Efficient Zeroshot Video Action Recognition","created":"2023-12-13","cited_by_count":14},{"id":"2408.06158","title":"OmniCLIP: Adapting CLIP for Video Recognition with Spatial-Temporal Omni-Scale Feature Learning","created":"2024-08-12","cited_by_count":14},{"id":"2401.11649","title":"M2-CLIP: A Multimodal, Multi-task Adapting Framework for Video Action Recognition","created":"2024-01-22","cited_by_count":11},{"id":"2407.18249","title":"Trajectory-aligned Space-time Tokens for Few-shot Action Recognition","created":"2024-07-25","cited_by_count":10},{"id":"1909.09422","title":"Retro-Actions: Learning 'Close' by Time-Reversing 'Open' Videos","created":"2019-09-20","cited_by_count":9},{"id":"2409.01936","title":"Optimizing CLIP Models for Image Retrieval with Maintained Joint-Embedding Alignment","created":"2024-09-03","cited_by_count":6},{"id":"2409.10228","title":"Robust Bird's Eye View Segmentation by Adapting DINOv2","created":"2024-09-16","cited_by_count":6},{"id":"2310.07394","title":"CLIP for Lightweight Semantic Segmentation","created":"2023-10-11","cited_by_count":1}],"next_cursor":null}