{"list":"other","total":54,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"2206.00364","title":"Elucidating the Design Space of Diffusion-Based Generative Models","created":"2022-06-01","cited_by_count":3045},{"id":"1910.03771","title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing","created":"2019-10-09","cited_by_count":2218},{"id":"2304.08818","title":"Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models","created":"2023-04-18","cited_by_count":1476},{"id":"2111.09886","title":"SimMIM: A Simple Framework for Masked Image Modeling","created":"2021-11-18","cited_by_count":1153},{"id":"1612.00410","title":"Deep Variational Information Bottleneck","created":"2016-12-01","cited_by_count":930},{"id":"2111.14822","title":"Vector Quantized Diffusion Model for Text-to-Image Synthesis","created":"2021-11-29","cited_by_count":774},{"id":"2003.00196","title":"First Order Motion Model for Image Animation","created":"2020-02-29","cited_by_count":704},{"id":"2104.10157","title":"VideoGPT: Video Generation using VQ-VAE and Transformers","created":"2021-04-20","cited_by_count":658},{"id":"1903.08527","title":"Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set","created":"2019-03-20","cited_by_count":482},{"id":"2011.15126","title":"One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing","created":"2020-11-30","cited_by_count":444},{"id":"1910.05453","title":"vq-wav2vec: Self-Supervised Learning of Discrete Speech Representations","created":"2019-10-12","cited_by_count":340},{"id":"1809.00496","title":"LRS3-TED: a large-scale dataset for visual speech recognition","created":"2018-09-03","cited_by_count":308},{"id":"2208.06366","title":"BEiT v2: Masked Image Modeling with Vector-Quantized Visual Tokenizers","created":"2022-08-12","cited_by_count":303},{"id":"2111.12417","title":"N\\\"UWA: Visual Synthesis Pre-training for Neural visUal World creAtion","created":"2021-11-24","cited_by_count":253},{"id":"2109.15047","title":"Deep Contextual Video Compression","created":"2021-09-30","cited_by_count":221},{"id":"1706.01350","title":"Emergence of Invariance and Disentanglement in Deep Representations","created":"2017-06-05","cited_by_count":215},{"id":"2112.01554","title":"Neural Head Avatars from Monocular RGB Videos","created":"2021-12-02","cited_by_count":213},{"id":"2407.03168","title":"LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Control","created":"2024-07-03","cited_by_count":206},{"id":"2109.15102","title":"Fake It Till You Make It: Face analysis in the wild using synthetic data alone","created":"2021-09-30","cited_by_count":200},{"id":"2203.09043","title":"Latent Image Animator: Learning to Animate Images via Latent Space Navigation","created":"2022-03-17","cited_by_count":175},{"id":"2302.14402","title":"Neural Video Compression with Diverse Contexts","created":"2023-02-28","cited_by_count":165},{"id":"2207.05894","title":"Hybrid Spatial-Temporal Entropy Modelling for Neural Video Compression","created":"2022-07-13","cited_by_count":128},{"id":"1803.02991","title":"Disentangled Sequential Autoencoder","created":"2018-03-08","cited_by_count":120},{"id":"2111.13850","title":"Temporal Context Mining for Learned Video Compression","created":"2021-11-27","cited_by_count":117},{"id":"2012.08261","title":"HeadGAN: One-shot Neural Head Synthesis and Editing","created":"2020-12-15","cited_by_count":105},{"id":"2311.17901","title":"SODA: Bottleneck Diffusion Models for Representation Learning","created":"2023-11-29","cited_by_count":77},{"id":"2204.02776","title":"3D face reconstruction with dense landmarks","created":"2022-04-06","cited_by_count":70},{"id":"2405.03121","title":"AniTalker: Animate Vivid and Diverse Talking Faces through Identity-Decoupled Facial Motion Encoding","created":"2024-05-06","cited_by_count":67},{"id":"2005.11437","title":"S3VAE: Self-Supervised Sequential VAE for Representation Disentanglement and Data Generation","created":"2020-05-23","cited_by_count":63},{"id":"2307.09906","title":"Implicit Identity Representation Conditioned Memory Compensation Network for Talking Head video Generation","created":"2023-07-19","cited_by_count":61},{"id":"2307.10797","title":"HyperReenact: One-Shot Reenactment via Jointly Learning to Refine and Retarget Faces","created":"2023-07-20","cited_by_count":48},{"id":"2210.01794","title":"Implicit Warping for Animation with Image Sets","created":"2022-10-04","cited_by_count":45},{"id":"2304.10168","title":"High-Fidelity and Freely Controllable Talking Head Video Generation","created":"2023-04-20","cited_by_count":42},{"id":"2110.12091","title":"Contrastively Disentangled Sequential Variational Autoencoder","created":"2021-10-22","cited_by_count":34},{"id":"2201.04029","title":"Motion-Focused Contrastive Learning of Video Representations","created":"2022-01-11","cited_by_count":23},{"id":"2203.09208","title":"Neural Compression-Based Feature Learning for Video Restoration","created":"2022-03-17","cited_by_count":23},{"id":"2410.11520","title":"Look Ma, no markers: holistic performance capture without the hassle","created":"2024-10-15","cited_by_count":23},{"id":"2101.07496","title":"Disentangled Recurrent Wasserstein Autoencoder","created":"2021-01-19","cited_by_count":22},{"id":"2211.11960","title":"Disentangled Feature Learning for Real-Time Neural Speech Coding","created":"2022-11-22","cited_by_count":10},{"id":"2305.15924","title":"Sample and Predict Your Latent: Modality-free Sequential Disentanglement via Contrastive Estimation","created":"2023-05-25","cited_by_count":10},{"id":"2406.18131","title":"Sequential Disentanglement by Extracting Static Information From A Single Sequence Element","created":"2024-06-26","cited_by_count":7},{"id":"2408.05599","title":"Sequential Representation Learning via Static-Dynamic Conditional Disentanglement","created":"2024-08-10","cited_by_count":4}],"next_cursor":null}