{"total":1438,"rows":[{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620,"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":"2104.00650","title":"Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval","created":"2021-04-01","cited_by_count":1177,"area":null},{"id":"2106.13230","title":"Video Swin Transformer","created":"2021-06-24","cited_by_count":1091,"area":null},{"id":"2104.11227","title":"Multiscale Vision Transformers","created":"2021-04-22","cited_by_count":897,"area":null},{"id":"2105.05633","title":"Segmenter: Transformer for Semantic Segmentation","created":"2021-05-12","cited_by_count":855,"area":null},{"id":"2205.13535","title":"AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition","created":"2022-05-26","cited_by_count":719,"area":null},{"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,"area":null},{"id":"2112.04482","title":"FLAVA: A Foundational Language And Vision Alignment Model","created":"2021-12-08","cited_by_count":649,"area":null},{"id":"2112.09133","title":"Masked Feature Prediction for Self-Supervised Visual Pre-Training","created":"2021-12-16","cited_by_count":576,"area":null},{"id":"2203.05625","title":"PETR: Position Embedding Transformation for Multi-View 3D Object Detection","created":"2022-03-10","cited_by_count":552,"area":null},{"id":"2202.11094","title":"GroupViT: Semantic Segmentation Emerges from Text Supervision","created":"2022-02-22","cited_by_count":531,"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":"2307.07635","title":"CoTracker: It is Better to Track Together","created":"2023-07-14","cited_by_count":522,"area":null},{"id":"2112.01526","title":"MViTv2: Improved Multiscale Vision Transformers for Classification and Detection","created":"2021-12-02","cited_by_count":519,"area":null},{"id":"2305.11175","title":"VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks","created":"2023-05-18","cited_by_count":501,"area":null},{"id":"2311.18259","title":"Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives","created":"2023-11-30","cited_by_count":490,"area":null},{"id":"2402.17177","title":"Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models","created":"2024-02-27","cited_by_count":477,"area":null},{"id":"2306.02018","title":"VideoComposer: Compositional Video Synthesis with Motion Controllability","created":"2023-06-03","cited_by_count":464,"area":null},{"id":"2104.11178","title":"VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text","created":"2021-04-22","cited_by_count":429,"area":null},{"id":"2205.09113","title":"Masked Autoencoders As Spatiotemporal Learners","created":"2022-05-18","cited_by_count":429,"area":null},{"id":"2202.07800","title":"Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations","created":"2022-02-16","cited_by_count":363,"area":null},{"id":"2106.09681","title":"XCiT: Cross-Covariance Image Transformers","created":"2021-06-17","cited_by_count":338,"area":null},{"id":"2208.02816","title":"Expanding Language-Image Pretrained Models for General Video Recognition","created":"2022-08-04","cited_by_count":321,"area":null},{"id":"2109.08472","title":"ActionCLIP: A New Paradigm for Video Action Recognition","created":"2021-09-17","cited_by_count":320,"area":null},{"id":"2112.04478","title":"Prompting Visual-Language Models for Efficient Video Understanding","created":"2021-12-08","cited_by_count":310,"area":null},{"id":"2306.00989","title":"Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistles","created":"2023-06-01","cited_by_count":290,"area":null},{"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,"area":null},{"id":"2104.05704","title":"Escaping the Big Data Paradigm with Compact Transformers","created":"2021-04-12","cited_by_count":264,"area":null},{"id":"2106.01548","title":"When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations","created":"2021-06-03","cited_by_count":260,"area":null},{"id":"2306.03838","title":"Spherical Fourier Neural Operators: Learning Stable Dynamics on the Sphere","created":"2023-06-06","cited_by_count":233,"area":null},{"id":"2206.01670","title":"Egocentric Video-Language Pretraining","created":"2022-06-03","cited_by_count":232,"area":null},{"id":"2111.10337","title":"Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptions","created":"2021-11-19","cited_by_count":226,"area":null},{"id":"2106.11097","title":"CLIP2Video: Mastering Video-Text Retrieval via Image CLIP","created":"2021-06-21","cited_by_count":225,"area":null},{"id":"2406.11816","title":"VideoLLM-online: Online Video Large Language Model for Streaming Video","created":"2024-06-17","cited_by_count":225,"area":null},{"id":"2106.05392","title":"Keeping Your Eye on the Ball: Trajectory Attention in Video Transformers","created":"2021-06-09","cited_by_count":224,"area":null},{"id":"2201.12288","title":"VRT: A Video Restoration Transformer","created":"2022-01-28","cited_by_count":220,"area":null},{"id":"2201.08377","title":"Omnivore: A Single Model for Many Visual Modalities","created":"2022-01-20","cited_by_count":215,"area":null},{"id":"2201.09450","title":"UniFormer: Unifying Convolution and Self-attention for Visual Recognition","created":"2022-01-24","cited_by_count":206,"area":null},{"id":"2312.17432","title":"Video Understanding with Large Language Models: A Survey","created":"2023-12-29","cited_by_count":206,"area":null},{"id":"2212.04501","title":"Learning Video Representations from Large Language Models","created":"2022-12-08","cited_by_count":205,"area":null},{"id":"2106.02036","title":"Anticipative Video Transformer","created":"2021-06-03","cited_by_count":200,"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":"2206.13559","title":"ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learning","created":"2022-06-27","cited_by_count":193,"area":null},{"id":"2201.08383","title":"MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition","created":"2022-01-20","cited_by_count":189,"area":null},{"id":"2111.12681","title":"VIOLET : End-to-End Video-Language Transformers with Masked Visual-token Modeling","created":"2021-11-24","cited_by_count":188,"area":null},{"id":"2201.02639","title":"MERLOT Reserve: Neural Script Knowledge through Vision and Language and Sound","created":"2022-01-07","cited_by_count":184,"area":null},{"id":"2201.04676","title":"UniFormer: Unified Transformer for Efficient Spatiotemporal Representation Learning","created":"2022-01-12","cited_by_count":184,"area":null},{"id":"2206.05099","title":"SimVP: Simpler yet Better Video Prediction","created":"2022-06-09","cited_by_count":184,"area":null},{"id":"2111.15667","title":"Adaptive Token Sampling For Efficient Vision Transformers","created":"2021-11-30","cited_by_count":183,"area":null},{"id":"2208.03550","title":"Frozen CLIP Models are Efficient Video Learners","created":"2022-08-06","cited_by_count":182,"area":null},{"id":"2212.03640","title":"Fine-tuned CLIP Models are Efficient Video Learners","created":"2022-12-06","cited_by_count":179,"area":null},{"id":"2312.17235","title":"A Simple LLM Framework for Long-Range Video Question-Answering","created":"2023-12-28","cited_by_count":178,"area":null},{"id":"2303.07399","title":"RTMPose: Real-Time Multi-Person Pose Estimation based on MMPose","created":"2023-03-13","cited_by_count":175,"area":null},{"id":"2203.07303","title":"All in One: Exploring Unified Video-Language Pre-training","created":"2022-03-14","cited_by_count":171,"area":null},{"id":"2112.01529","title":"BEVT: BERT Pretraining of Video Transformers","created":"2021-12-02","cited_by_count":169,"area":null},{"id":"2110.08568","title":"ASFormer: Transformer for Action Segmentation","created":"2021-10-16","cited_by_count":168,"area":null},{"id":"2311.16813","title":"Panacea: Panoramic and Controllable Video Generation for Autonomous Driving","created":"2023-11-28","cited_by_count":168,"area":null},{"id":"2309.17024","title":"HoloAssist: an Egocentric Human Interaction Dataset for Interactive AI Assistants in the Real World","created":"2023-09-29","cited_by_count":166,"area":null},{"id":"2102.07074","title":"TransGAN: Two Pure Transformers Can Make One Strong GAN, and That Can Scale Up","created":"2021-02-14","cited_by_count":162,"area":null},{"id":"2111.13196","title":"SwinBERT: End-to-End Transformers with Sparse Attention for Video Captioning","created":"2021-11-25","cited_by_count":162,"area":null},{"id":"2212.05598","title":"Recurrent Vision Transformers for Object Detection with Event Cameras","created":"2022-12-11","cited_by_count":159,"area":null},{"id":"2302.00402","title":"mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video","created":"2023-02-01","cited_by_count":154,"area":null},{"id":"2305.10874","title":"Swap Attention in Spatiotemporal Diffusions for Text-to-Video Generation","created":"2023-05-18","cited_by_count":154,"area":null},{"id":"2207.05833","title":"Earthformer: Exploring Space-Time Transformers for Earth System Forecasting","created":"2022-07-12","cited_by_count":152,"area":null},{"id":"2106.10271","title":"End-to-end Temporal Action Detection with Transformer","created":"2021-06-18","cited_by_count":151,"area":null},{"id":"2110.09408","title":"HRFormer: High-Resolution Transformer for Dense Prediction","created":"2021-10-18","cited_by_count":149,"area":null},{"id":"2112.09583","title":"Align and Prompt: Video-and-Language Pre-training with Entity Prompts","created":"2021-12-17","cited_by_count":149,"area":null},{"id":"2201.04288","title":"Multiview Transformers for Video Recognition","created":"2022-01-12","cited_by_count":148,"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":"2305.02296","title":"DynamicStereo: Consistent Dynamic Depth from Stereo Videos","created":"2023-05-03","cited_by_count":148,"area":null},{"id":"2104.07658","title":"Self-supervised Video Object Segmentation by Motion Grouping","created":"2021-04-15","cited_by_count":147,"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":"2109.03223","title":"Rendezvous: Attention Mechanisms for the Recognition of Surgical Action Triplets in Endoscopic Videos","created":"2021-09-07","cited_by_count":141,"area":null},{"id":"2307.10802","title":"Meta-Transformer: A Unified Framework for Multimodal Learning","created":"2023-07-20","cited_by_count":136,"area":null},{"id":"2103.11511","title":"MoViNets: Mobile Video Networks for Efficient Video Recognition","created":"2021-03-21","cited_by_count":135,"area":null},{"id":"2206.03428","title":"Revealing Single Frame Bias for Video-and-Language Learning","created":"2022-06-07","cited_by_count":133,"area":null},{"id":"2307.05463","title":"EgoVLPv2: Egocentric Video-Language Pre-training with Fusion in the Backbone","created":"2023-07-11","cited_by_count":130,"area":null},{"id":"2106.02689","title":"RegionViT: Regional-to-Local Attention for Vision Transformers","created":"2021-06-04","cited_by_count":127,"area":null},{"id":"2106.11297","title":"TokenLearner: What Can 8 Learned Tokens Do for Images and Videos?","created":"2021-06-21","cited_by_count":127,"area":null},{"id":"2106.12620","title":"IA-RED$^2$: Interpretability-Aware Redundancy Reduction for Vision Transformers","created":"2021-06-23","cited_by_count":127,"area":null},{"id":"2107.10224","title":"CycleMLP: A MLP-like Architecture for Dense Prediction","created":"2021-07-21","cited_by_count":126,"area":null},{"id":"2404.00308","title":"ST-LLM: Large Language Models Are Effective Temporal Learners","created":"2024-03-30","cited_by_count":126,"area":null},{"id":"2112.01522","title":"Uni-Perceiver: Pre-training Unified Architecture for Generic Perception for Zero-shot and Few-shot Tasks","created":"2021-12-02","cited_by_count":125,"area":null},{"id":"2304.09854","title":"Transformer-Based Visual Segmentation: A Survey","created":"2023-04-19","cited_by_count":124,"area":null},{"id":"2111.13817","title":"Video Frame Interpolation Transformer","created":"2021-11-27","cited_by_count":123,"area":null},{"id":"2112.11010","title":"MPViT: Multi-Path Vision Transformer for Dense Prediction","created":"2021-12-21","cited_by_count":122,"area":null},{"id":"2301.06051","title":"DSVT: Dynamic Sparse Voxel Transformer with Rotated Sets","created":"2023-01-15","cited_by_count":122,"area":null},{"id":"2111.12082","title":"PhysFormer: Facial Video-based Physiological Measurement with Temporal Difference Transformer","created":"2021-11-23","cited_by_count":120,"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":"2603.14482","title":"V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning","created":"2026-03-15","cited_by_count":117,"area":null},{"id":"2211.09552","title":"UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer","created":"2022-11-17","cited_by_count":116,"area":null},{"id":"2305.13292","title":"VideoLLM: Modeling Video Sequence with Large Language Models","created":"2023-05-22","cited_by_count":116,"area":null},{"id":"2203.16761","title":"MeMOT: Multi-Object Tracking with Memory","created":"2022-03-31","cited_by_count":114,"area":null},{"id":"2104.11746","title":"VidTr: Video Transformer Without Convolutions","created":"2021-04-23","cited_by_count":112,"area":null},{"id":"2204.01696","title":"Joint Hand Motion and Interaction Hotspots Prediction from Egocentric Videos","created":"2022-04-04","cited_by_count":111,"area":null},{"id":"2107.04589","title":"ViTGAN: Training GANs with Vision Transformers","created":"2021-07-09","cited_by_count":110,"area":null},{"id":"2103.16559","title":"Broaden Your Views for Self-Supervised Video Learning","created":"2021-03-30","cited_by_count":108,"area":null},{"id":"2209.13929","title":"Attention Spiking Neural Networks","created":"2022-09-28","cited_by_count":107,"area":null},{"id":"2204.01692","title":"Long Movie Clip Classification with State-Space Video Models","created":"2022-04-04","cited_by_count":106,"area":null}],"next_cursor":"100"}