{"list":"other","total":71,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"1903.12261","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","created":"2019-03-28","cited_by_count":2877},{"id":"2104.08718","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","created":"2021-04-18","cited_by_count":2424},{"id":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"id":"2204.03458","title":"Video Diffusion Models","created":"2022-04-07","cited_by_count":2305},{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"id":"2311.17982","title":"VBench: Comprehensive Benchmark Suite for Video Generative Models","created":"2023-11-29","cited_by_count":1822},{"id":"2210.02303","title":"Imagen Video: High Definition Video Generation with Diffusion Models","created":"2022-10-05","cited_by_count":1778},{"id":"2209.14792","title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","created":"2022-09-29","cited_by_count":1742},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"2304.08818","title":"Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models","created":"2023-04-18","cited_by_count":1476},{"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":"1801.01401","title":"Demystifying MMD GANs","created":"2018-01-04","cited_by_count":1293},{"id":"1812.01717","title":"Towards Accurate Generative Models of Video: A New Metric & Challenges","created":"2018-12-03","cited_by_count":1234},{"id":"2103.03206","title":"Perceiver: General Perception with Iterative Attention","created":"2021-03-04","cited_by_count":1104},{"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":"2205.15868","title":"CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers","created":"2022-05-29","cited_by_count":985},{"id":"2212.11565","title":"Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation","created":"2022-12-22","cited_by_count":961},{"id":"2002.04745","title":"On Layer Normalization in the Transformer Architecture","created":"2020-02-12","cited_by_count":922},{"id":"1512.02134","title":"A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation","created":"2015-12-07","cited_by_count":881},{"id":"2410.18072","title":"WorldSimBench: Towards Video Generation Models as World Simulators","created":"2024-10-23","cited_by_count":881},{"id":"2302.05442","title":"Scaling Vision Transformers to 22 Billion Parameters","created":"2023-02-10","cited_by_count":694},{"id":"2303.13439","title":"Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generators","created":"2023-03-23","cited_by_count":670},{"id":"2308.06571","title":"ModelScope Text-to-Video Technical Report","created":"2023-08-12","cited_by_count":658},{"id":"2412.20404","title":"Open-Sora: Democratizing Efficient Video Production for All","created":"2024-12-29","cited_by_count":652},{"id":"2107.14795","title":"Perceiver IO: A General Architecture for Structured Inputs & Outputs","created":"2021-07-30","cited_by_count":629},{"id":"2302.03011","title":"Structure and Content-Guided Video Synthesis with Diffusion Models","created":"2023-02-06","cited_by_count":590},{"id":"2401.09047","title":"VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models","created":"2024-01-17","cited_by_count":579},{"id":"2310.19512","title":"VideoCrafter1: Open Diffusion Models for High-Quality Video Generation","created":"2023-10-30","cited_by_count":535},{"id":"2303.16727","title":"VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking","created":"2023-03-29","cited_by_count":528},{"id":"2003.14338","title":"TartanAir: A Dataset to Push the Limits of Visual SLAM","created":"2020-03-31","cited_by_count":506},{"id":"2211.11018","title":"MagicVideo: Efficient Video Generation With Latent Diffusion Models","created":"2022-11-20","cited_by_count":465},{"id":"2211.13221","title":"Latent Video Diffusion Models for High-Fidelity Long Video Generation","created":"2022-11-23","cited_by_count":388},{"id":"2203.03570","title":"Kubric: A scalable dataset generator","created":"2022-03-07","cited_by_count":381},{"id":"2310.11440","title":"EvalCrafter: Benchmarking and Evaluating Large Video Generation Models","created":"2023-10-17","cited_by_count":340},{"id":"1808.01340","title":"A Short Note about Kinetics-600","created":"2018-08-03","cited_by_count":333},{"id":"2303.08320","title":"VideoFusion: Decomposed Diffusion Models for High-Quality Video Generation","created":"2023-03-15","cited_by_count":331},{"id":"2312.06662","title":"Photorealistic Video Generation with Diffusion Models","created":"2023-12-11","cited_by_count":306},{"id":"2309.15818","title":"Show-1: Marrying Pixel and Latent Diffusion Models for Text-to-Video Generation","created":"2023-09-27","cited_by_count":302},{"id":"2307.15055","title":"PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Tracking","created":"2023-07-27","cited_by_count":276},{"id":"2211.03726","title":"TAP-Vid: A Benchmark for Tracking Any Point in a Video","created":"2022-11-07","cited_by_count":263},{"id":"2104.14806","title":"GODIVA: Generating Open-DomaIn Videos from nAtural Descriptions","created":"2021-04-30","cited_by_count":256},{"id":"1808.00449","title":"Learning Blind Video Temporal Consistency","created":"2018-08-01","cited_by_count":253},{"id":"2111.12417","title":"N\\\"UWA: Visual Synthesis Pre-training for Neural visUal World creAtion","created":"2021-11-24","cited_by_count":253},{"id":"2406.03520","title":"VideoPhy: Evaluating Physical Commonsense for Video Generation","created":"2024-06-05","cited_by_count":228},{"id":"2111.13152","title":"Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representations","created":"2021-11-25","cited_by_count":227},{"id":"2311.01813","title":"FETV: A Benchmark for Fine-Grained Evaluation of Open-Domain Text-to-Video Generation","created":"2023-11-03","cited_by_count":122},{"id":"2402.00847","title":"BootsTAP: Bootstrapped Training for Tracking-Any-Point","created":"2024-02-01","cited_by_count":120},{"id":"2306.01923","title":"The Surprising Effectiveness of Diffusion Models for Optical Flow and Monocular Depth Estimation","created":"2023-06-02","cited_by_count":116},{"id":"2104.14544","title":"AutoFlow: Learning a Better Training Set for Optical Flow","created":"2021-04-29","cited_by_count":102},{"id":"2010.02054","title":"Improving Generative Imagination in Object-Centric World Models","created":"2020-10-05","cited_by_count":71},{"id":"2312.02087","title":"VideoSwap: Customized Video Subject Swapping with Interactive Semantic Point Correspondence","created":"2023-12-04","cited_by_count":69},{"id":"2304.01816","title":"Toward Verifiable and Reproducible Human Evaluation for Text-to-Image Generation","created":"2023-04-04","cited_by_count":68},{"id":"2407.16124","title":"Fr\\'echet Video Motion Distance: A Metric for Evaluating Motion Consistency in Videos","created":"2024-07-23","cited_by_count":58},{"id":"2404.12391","title":"On the Content Bias in Fr\\'echet Video Distance","created":"2024-04-18","cited_by_count":52},{"id":"2401.07781","title":"Towards A Better Metric for Text-to-Video Generation","created":"2024-01-15","cited_by_count":51},{"id":"2310.08584","title":"Is ImageNet worth 1 video? Learning strong image encoders from 1 long unlabelled video","created":"2023-10-12","cited_by_count":40},{"id":"2203.10712","title":"Disentangling Architecture and Training for Optical Flow","created":"2022-03-21","cited_by_count":32},{"id":"2311.10111","title":"VideoCon: Robust Video-Language Alignment via Contrast Captions","created":"2023-11-15","cited_by_count":30},{"id":"2308.11606","title":"StoryBench: A Multifaceted Benchmark for Continuous Story Visualization","created":"2023-08-22","cited_by_count":29},{"id":"2410.05203","title":"Beyond FVD: Enhanced Evaluation Metrics for Video Generation Quality","created":"2024-10-07","cited_by_count":22},{"id":"2310.10624","title":"DynVideo-E: Harnessing Dynamic NeRF for Large-Scale Motion- and View-Change Human-Centric Video Editing","created":"2023-10-16","cited_by_count":17},{"id":"2312.05359","title":"Learning 3D Particle-based Simulators from RGB-D Videos","created":"2023-12-08","cited_by_count":17},{"id":"2411.05927","title":"Moving Off-the-Grid: Scene-Grounded Video Representations","created":"2024-11-08","cited_by_count":11},{"id":"2403.09669","title":"STREAM: Spatio-TempoRal Evaluation and Analysis Metric for Video Generative Models","created":"2024-01-30","cited_by_count":6}],"next_cursor":null}