{"total":152,"rows":[{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681,"area":null},{"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,"area":null},{"id":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175,"area":null},{"id":"2303.16727","title":"VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking","created":"2023-03-29","cited_by_count":528,"area":null},{"id":"2212.03191","title":"InternVideo: General Video Foundation Models via Generative and Discriminative Learning","created":"2022-12-06","cited_by_count":447,"area":null},{"id":"2205.09113","title":"Masked Autoencoders As Spatiotemporal Learners","created":"2022-05-18","cited_by_count":429,"area":null},{"id":"2301.05712","title":"A Survey on Self-supervised Learning: Algorithms, Applications, and Future Trends","created":"2023-01-13","cited_by_count":207,"area":null},{"id":"2303.16058","title":"Unmasked Teacher: Towards Training-Efficient Video Foundation Models","created":"2023-03-28","cited_by_count":199,"area":null},{"id":"2211.14813","title":"SegCLIP: Patch Aggregation with Learnable Centers for Open-Vocabulary Semantic Segmentation","created":"2022-11-27","cited_by_count":164,"area":null},{"id":"2302.03024","title":"AIM: Adapting Image Models for Efficient Video Action Recognition","created":"2023-02-06","cited_by_count":148,"area":null},{"id":"2209.07526","title":"OmniVL:One Foundation Model for Image-Language and Video-Language Tasks","created":"2022-09-15","cited_by_count":143,"area":null},{"id":"2406.09399","title":"OmniTokenizer: A Joint Image-Video Tokenizer for Visual Generation","created":"2024-06-13","cited_by_count":118,"area":null},{"id":"2406.07548","title":"Image and Video Tokenization with Binary Spherical Quantization","created":"2024-06-11","cited_by_count":112,"area":null},{"id":"2206.08356","title":"OmniMAE: Single Model Masked Pretraining on Images and Videos","created":"2022-06-16","cited_by_count":99,"area":null},{"id":"2203.01318","title":"Protecting Celebrities from DeepFake with Identity Consistency Transformer","created":"2022-03-02","cited_by_count":95,"area":null},{"id":"2207.00419","title":"Self-Supervised Learning for Videos: A Survey","created":"2022-06-18","cited_by_count":85,"area":null},{"id":"2307.16368","title":"AntGPT: Can Large Language Models Help Long-term Action Anticipation from Videos?","created":"2023-07-31","cited_by_count":81,"area":null},{"id":"2312.02116","title":"GIVT: Generative Infinite-Vocabulary Transformers","created":"2023-12-04","cited_by_count":80,"area":null},{"id":"2203.14681","title":"ObjectFormer for Image Manipulation Detection and Localization","created":"2022-03-28","cited_by_count":78,"area":null},{"id":"2207.04978","title":"Wave-ViT: Unifying Wavelet and Transformers for Visual Representation Learning","created":"2022-07-11","cited_by_count":78,"area":null},{"id":"2209.01540","title":"An Empirical Study of End-to-End Video-Language Transformers with Masked Visual Modeling","created":"2022-09-04","cited_by_count":74,"area":null},{"id":"2209.06430","title":"CLIP-ViP: Adapting Pre-trained Image-Text Model to Video-Language Representation Alignment","created":"2022-09-14","cited_by_count":74,"area":null},{"id":"2211.13222","title":"SVFormer: Semi-supervised Video Transformer for Action Recognition","created":"2022-11-23","cited_by_count":68,"area":null},{"id":"2304.14407","title":"ChatVideo: A Tracklet-centric Multimodal and Versatile Video Understanding System","created":"2023-04-27","cited_by_count":65,"area":null},{"id":"2201.05991","title":"Video Transformers: A Survey","created":"2022-01-16","cited_by_count":63,"area":null},{"id":"2503.16421","title":"MagicMotion: Controllable Video Generation with Dense-to-Sparse Trajectory Guidance","created":"2025-03-20","cited_by_count":61,"area":null},{"id":"2207.07116","title":"Bootstrapped Masked Autoencoders for Vision BERT Pretraining","created":"2022-07-14","cited_by_count":60,"area":null},{"id":"2208.00173","title":"A Survey on Masked Autoencoder for Self-supervised Learning in Vision and Beyond","created":"2022-07-30","cited_by_count":58,"area":null},{"id":"2304.05919","title":"Hard Patches Mining for Masked Image Modeling","created":"2023-04-12","cited_by_count":57,"area":null},{"id":"2212.02031","title":"Prototypical Residual Networks for Anomaly Detection and Localization","created":"2022-12-05","cited_by_count":56,"area":null},{"id":"2301.02074","title":"Test of Time: Instilling Video-Language Models with a Sense of Time","created":"2023-01-05","cited_by_count":51,"area":null},{"id":"2212.03229","title":"Rethinking Video ViTs: Sparse Video Tubes for Joint Image and Video Learning","created":"2022-12-06","cited_by_count":49,"area":null},{"id":"2212.05922","title":"Audiovisual Masked Autoencoders","created":"2022-12-09","cited_by_count":49,"area":null},{"id":"2211.09120","title":"AdaMAE: Adaptive Masking for Efficient Spatiotemporal Learning with Masked Autoencoders","created":"2022-11-16","cited_by_count":43,"area":null},{"id":"2212.10368","title":"Masked Event Modeling: Self-Supervised Pretraining for Event Cameras","created":"2022-12-20","cited_by_count":41,"area":null},{"id":"2308.10794","title":"MGMAE: Motion Guided Masking for Video Masked Autoencoding","created":"2023-08-21","cited_by_count":41,"area":null},{"id":"2203.15187","title":"ASM-Loc: Action-aware Segment Modeling for Weakly-Supervised Temporal Action Localization","created":"2022-03-29","cited_by_count":40,"area":null},{"id":"2210.06096","title":"Masked Motion Encoding for Self-Supervised Video Representation Learning","created":"2022-10-12","cited_by_count":39,"area":null},{"id":"2201.08071","title":"Temporal Sentence Grounding in Videos: A Survey and Future Directions","created":"2022-01-20","cited_by_count":37,"area":null},{"id":"2303.14124","title":"Towards Scalable Neural Representation for Diverse Videos","created":"2023-03-24","cited_by_count":37,"area":null},{"id":"2205.05076","title":"Reduce Information Loss in Transformers for Pluralistic Image Inpainting","created":"2022-05-10","cited_by_count":36,"area":null},{"id":"2212.06138","title":"CLIP Itself is a Strong Fine-tuner: Achieving 85.7% and 88.0% Top-1 Accuracy with ViT-B and ViT-L on ImageNet","created":"2022-12-12","cited_by_count":35,"area":null},{"id":"2207.06101","title":"Global-local Motion Transformer for Unsupervised Skeleton-based Action Learning","created":"2022-07-13","cited_by_count":33,"area":null},{"id":"2304.06306","title":"Efficient Multimodal Fusion via Interactive Prompting","created":"2023-04-13","cited_by_count":32,"area":null},{"id":"2309.07911","title":"Disentangling Spatial and Temporal Learning for Efficient Image-to-Video Transfer Learning","created":"2023-09-14","cited_by_count":32,"area":null},{"id":"2203.17276","title":"Bringing Old Films Back to Life","created":"2022-03-31","cited_by_count":31,"area":null},{"id":"2308.12962","title":"Motion-Guided Masking for Spatiotemporal Representation Learning","created":"2023-08-24","cited_by_count":30,"area":null},{"id":"2207.11660","title":"MAR: Masked Autoencoders for Efficient Action Recognition","created":"2022-07-24","cited_by_count":29,"area":null},{"id":"2206.01038","title":"A Survey on Video Action Recognition in Sports: Datasets, Methods and Applications","created":"2022-06-02","cited_by_count":28,"area":null},{"id":"2206.09325","title":"EATFormer: Improving Vision Transformer Inspired by Evolutionary Algorithm","created":"2022-06-19","cited_by_count":27,"area":null},{"id":"2501.09754","title":"Lost in Translation, Found in Context: Sign Language Translation with Contextual Cues","created":"2025-01-16","cited_by_count":26,"area":null},{"id":"2206.03484","title":"Detection Hub: Unifying Object Detection Datasets via Query Adaptation on Language Embedding","created":"2022-06-07","cited_by_count":25,"area":null},{"id":"2205.01818","title":"i-Code: An Integrative and Composable Multimodal Learning Framework","created":"2022-05-03","cited_by_count":24,"area":null},{"id":"2305.04075","title":"PointCMP: Contrastive Mask Prediction for Self-supervised Learning on Point Cloud Videos","created":"2023-05-06","cited_by_count":22,"area":null},{"id":"2209.01578","title":"Spatial-Temporal Transformer for Video Snapshot Compressive Imaging","created":"2022-09-04","cited_by_count":21,"area":null},{"id":"2303.15591","title":"Learning Expressive Prompting With Residuals for Vision Transformers","created":"2023-03-27","cited_by_count":21,"area":null},{"id":"2210.04154","title":"Self-supervised Video Representation Learning with Motion-Aware Masked Autoencoders","created":"2022-10-09","cited_by_count":20,"area":null},{"id":"2308.09245","title":"Masked Spatio-Temporal Structure Prediction for Self-supervised Learning on Point Cloud Videos","created":"2023-08-18","cited_by_count":19,"area":null},{"id":"2302.14138","title":"Layer Grafted Pre-training: Bridging Contrastive Learning And Masked Image Modeling For Label-Efficient Representations","created":"2023-02-27","cited_by_count":18,"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":"2405.04741","title":"All in One Framework for Multimodal Re-identification in the Wild","created":"2024-05-08","cited_by_count":18,"area":null},{"id":"2212.13805","title":"Swin MAE: Masked Autoencoders for Small Datasets","created":"2022-12-28","cited_by_count":17,"area":null},{"id":"2211.11446","title":"SMAUG: Sparse Masked Autoencoder for Efficient Video-Language Pre-training","created":"2022-11-21","cited_by_count":15,"area":null},{"id":"2303.12001","title":"ViC-MAE: Self-Supervised Representation Learning from Images and Video with Contrastive Masked Autoencoders","created":"2023-03-21","cited_by_count":14,"area":null},{"id":"2310.01324","title":"ZeroI2V: Zero-Cost Adaptation of Pre-trained Transformers from Image to Video","created":"2023-10-02","cited_by_count":14,"area":null},{"id":"2407.15447","title":"SIGMA: Sinkhorn-Guided Masked Video Modeling","created":"2024-07-22","cited_by_count":14,"area":null},{"id":"2412.17726","title":"VidTwin: Video VAE with Decoupled Structure and Dynamics","created":"2024-12-23","cited_by_count":14,"area":null},{"id":"2309.06799","title":"When Geoscience Meets Foundation Models: Towards General Geoscience Artificial Intelligence System","created":"2023-09-13","cited_by_count":13,"area":null},{"id":"2401.00897","title":"Masked Modeling for Self-supervised Representation Learning on Vision and Beyond","created":"2023-12-31","cited_by_count":13,"area":null},{"id":"2412.19178","title":"Reversed in Time: A Novel Temporal-Emphasized Benchmark for Cross-Modal Video-Text Retrieval","created":"2024-12-26","cited_by_count":13,"area":null},{"id":"2303.14926","title":"Continuous Intermediate Token Learning with Implicit Motion Manifold for Keyframe Based Motion Interpolation","created":"2023-03-27","cited_by_count":12,"area":null},{"id":"2304.03378","title":"Self-Supervised Video Similarity Learning","created":"2023-04-06","cited_by_count":12,"area":null},{"id":"2311.18825","title":"CAST: Cross-Attention in Space and Time for Video Action Recognition","created":"2023-11-30","cited_by_count":12,"area":null},{"id":"2212.00986","title":"Masked Contrastive Pre-Training for Efficient Video-Text Retrieval","created":"2022-12-02","cited_by_count":11,"area":null},{"id":"2301.06018","title":"CMAE-V: Contrastive Masked Autoencoders for Video Action Recognition","created":"2023-01-15","cited_by_count":11,"area":null},{"id":"2307.03353","title":"A Survey of Deep Learning in Sports Applications: Perception, Comprehension, and Decision","created":"2023-07-07","cited_by_count":11,"area":null},{"id":"2508.12586","title":"Foundation Model for Skeleton-Based Human Action Understanding","created":"2025-08-18","cited_by_count":11,"area":null},{"id":"2210.05234","title":"It Takes Two: Masked Appearance-Motion Modeling for Self-supervised Video Transformer Pre-training","created":"2022-10-11","cited_by_count":10,"area":null},{"id":"2302.02060","title":"Representation Deficiency in Masked Language Modeling","created":"2023-02-04","cited_by_count":10,"area":null},{"id":"2512.13684","title":"Recurrent Video Masked Autoencoders","created":"2025-12-15","cited_by_count":10,"area":null},{"id":"2409.06154","title":"Static for Dynamic: Towards a Deeper Understanding of Dynamic Facial Expressions Using Static Expression Data","created":"2024-09-10","cited_by_count":9,"area":null},{"id":"2504.00527","title":"SMILE: Infusing Spatial and Motion Semantics in Masked Video Learning","created":"2025-04-01","cited_by_count":9,"area":null},{"id":"2308.04343","title":"Unifying Two-Stream Encoders with Transformers for Cross-Modal Retrieval","created":"2023-08-08","cited_by_count":8,"area":null},{"id":"2309.08035","title":"Interpretability-Aware Vision Transformer","created":"2023-09-14","cited_by_count":8,"area":null},{"id":"2506.09385","title":"ReID5o: Achieving Omni Multi-modal Person Re-identification in a Single Model","created":"2025-06-11","cited_by_count":8,"area":null},{"id":"2404.00513","title":"Transformer based Pluralistic Image Completion with Reduced Information Loss","created":"2024-03-31","cited_by_count":7,"area":null},{"id":"2309.02450","title":"Self-Supervised Video Transformers for Isolated Sign Language Recognition","created":"2023-09-02","cited_by_count":6,"area":null},{"id":"2311.04496","title":"PersonMAE: Person Re-Identification Pre-Training with Masked AutoEncoders","created":"2023-11-08","cited_by_count":6,"area":null},{"id":"2401.15900","title":"MV2MAE: Multi-View Video Masked Autoencoders","created":"2024-01-29","cited_by_count":6,"area":null},{"id":"2403.16128","title":"Enhancing Video Transformers for Action Understanding with VLM-aided Training","created":"2024-03-24","cited_by_count":6,"area":null},{"id":"2406.17086","title":"BrainMAE: A Region-aware Self-supervised Learning Framework for Brain Signals","created":"2024-06-24","cited_by_count":6,"area":null},{"id":"2408.13126","title":"CathAction: A Benchmark for Endovascular Intervention Understanding","created":"2024-08-23","cited_by_count":6,"area":null},{"id":"2503.14237","title":"Make Your Training Flexible: Towards Deployment-Efficient Video Models","created":"2025-03-18","cited_by_count":6,"area":null},{"id":"2305.07910","title":"Mask to reconstruct: Cooperative Semantics Completion for Video-text Retrieval","created":"2023-05-13","cited_by_count":5,"area":null},{"id":"2305.12959","title":"Contrastive Predictive Autoencoders for Dynamic Point Cloud Self-Supervised Learning","created":"2023-05-22","cited_by_count":5,"area":null},{"id":"2405.15160","title":"ARVideo: Autoregressive Pretraining for Self-Supervised Video Representation Learning","created":"2024-05-24","cited_by_count":5,"area":null},{"id":"2507.09513","title":"Animal behavioral analysis and neural encoding with transformer-based self-supervised pretraining","created":"2025-07-13","cited_by_count":5,"area":null},{"id":"2304.04175","title":"Token Boosting for Robust Self-Supervised Visual Transformer Pre-training","created":"2023-04-09","cited_by_count":4,"area":null},{"id":"2306.02014","title":"Uncovering the Hidden Dynamics of Video Self-supervised Learning under Distribution Shifts","created":"2023-06-03","cited_by_count":4,"area":null},{"id":"2311.11845","title":"Entangled View-Epipolar Information Aggregation for Generalizable Neural Radiance Fields","created":"2023-11-20","cited_by_count":4,"area":null}],"next_cursor":"100"}