{"list":"other","total":55,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"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":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"2006.11477","title":"wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations","created":"2020-06-20","cited_by_count":3905},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"2003.04297","title":"Improved Baselines with Momentum Contrastive Learning","created":"2020-03-09","cited_by_count":2287},{"id":"1904.05866","title":"Expressive Body Capture: 3D Hands, Face, and Body from a Single Image","created":"2019-04-11","cited_by_count":1612},{"id":"2307.04725","title":"AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning","created":"2023-07-10","cited_by_count":1433},{"id":"1812.07035","title":"On the Continuity of Rotation Representations in Neural Networks","created":"2018-12-17","cited_by_count":1214},{"id":"1612.01925","title":"FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks","created":"2016-12-06","cited_by_count":784},{"id":"2311.17117","title":"Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation","created":"2023-11-28","cited_by_count":688},{"id":"2008.10010","title":"A Lip Sync Expert Is All You Need for Speech to Lip Generation In The Wild","created":"2020-08-23","cited_by_count":672},{"id":"1711.09078","title":"Video Enhancement with Task-Oriented Flow","created":"2017-11-24","cited_by_count":619},{"id":"1906.08172","title":"MediaPipe: A Framework for Building Perception Pipelines","created":"2019-06-14","cited_by_count":583},{"id":"2203.08063","title":"MotionCLIP: Exposing Human Motion Generation to CLIP Space","created":"2022-03-15","cited_by_count":408},{"id":"2207.01696","title":"TM2T: Stochastic and Tokenized Modeling for the Reciprocal Generation of 3D Human Motions and Texts","created":"2022-07-04","cited_by_count":359},{"id":"1712.00080","title":"Super SloMo: High Quality Estimation of Multiple Intermediate Frames for Video Interpolation","created":"2017-11-30","cited_by_count":326},{"id":"1808.07371","title":"Everybody Dance Now","created":"2018-08-22","cited_by_count":315},{"id":"2205.09853","title":"MCVD: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation","created":"2022-05-19","cited_by_count":309},{"id":"2003.05534","title":"Softmax Splatting for Video Frame Interpolation","created":"2020-03-11","cited_by_count":279},{"id":"2011.06294","title":"Real-Time Intermediate Flow Estimation for Video Frame Interpolation","created":"2020-11-12","cited_by_count":213},{"id":"1702.02463","title":"Video Frame Synthesis using Deep Voxel Flow","created":"2017-02-08","cited_by_count":209},{"id":"2009.02119","title":"Speech Gesture Generation from the Trimodal Context of Text, Audio, and Speaker Identity","created":"2020-09-04","cited_by_count":202},{"id":"1906.04160","title":"Learning Individual Styles of Conversational Gesture","created":"2019-06-10","cited_by_count":191},{"id":"2212.04420","title":"Generating Holistic 3D Human Motion from Speech","created":"2022-12-08","cited_by_count":180},{"id":"2304.09790","title":"AMT: All-Pairs Multi-Field Transforms for Efficient Frame Interpolation","created":"2023-04-19","cited_by_count":180},{"id":"2203.05297","title":"BEAT: A Large-Scale Semantic and Emotional Multi-Modal Dataset for Conversational Gestures Synthesis","created":"2022-03-10","cited_by_count":178},{"id":"2303.14613","title":"GestureDiffuCLIP: Gesture Diffusion Model with CLIP Latents","created":"2023-03-26","cited_by_count":158},{"id":"1803.10967","title":"Context-aware Synthesis for Video Frame Interpolation","created":"2018-03-29","cited_by_count":153},{"id":"2202.04901","title":"FILM: Frame Interpolation for Large Motion","created":"2022-02-10","cited_by_count":153},{"id":"2303.09119","title":"Taming Diffusion Models for Audio-Driven Co-Speech Gesture Generation","created":"2023-03-16","cited_by_count":129},{"id":"2103.16206","title":"XVFI: eXtreme Video Frame Interpolation","created":"2021-03-30","cited_by_count":126},{"id":"2111.13817","title":"Video Frame Interpolation Transformer","created":"2021-11-27","cited_by_count":123},{"id":"2007.12622","title":"BMBC:Bilateral Motion Estimation with Bilateral Cost Volume for Video Interpolation","created":"2020-07-17","cited_by_count":118},{"id":"2205.14620","title":"IFRNet: Intermediate Feature Refine Network for Efficient Frame Interpolation","created":"2022-05-29","cited_by_count":109},{"id":"2203.13161","title":"Learning Hierarchical Cross-Modal Association for Co-Speech Gesture Generation","created":"2022-03-24","cited_by_count":107},{"id":"2108.06815","title":"Asymmetric Bilateral Motion Estimation for Video Frame Interpolation","created":"2021-08-15","cited_by_count":101},{"id":"2303.09508","title":"LDMVFI: Video Frame Interpolation with Latent Diffusion Models","created":"2023-03-16","cited_by_count":89},{"id":"2305.04919","title":"DiffuseStyleGesture: Stylized Audio-Driven Co-Speech Gesture Generation with Diffusion Models","created":"2023-05-08","cited_by_count":85},{"id":"2206.03287","title":"NeMF: Neural Motion Fields for Kinematic Animation","created":"2022-06-04","cited_by_count":68},{"id":"2404.01203","title":"Video Interpolation with Diffusion Models","created":"2024-04-01","cited_by_count":68},{"id":"2301.05339","title":"A Comprehensive Review of Data-Driven Co-Speech Gesture Generation","created":"2023-01-13","cited_by_count":66},{"id":"2108.08020","title":"Speech Drives Templates: Co-Speech Gesture Synthesis with Learned Templates","created":"2021-08-18","cited_by_count":58},{"id":"2212.02350","title":"Audio-Driven Co-Speech Gesture Video Generation","created":"2022-12-05","cited_by_count":55},{"id":"2403.17936","title":"ConvoFusion: Multi-Modal Conversational Diffusion for Co-Speech Gesture Synthesis","created":"2024-03-26","cited_by_count":41},{"id":"2305.11094","title":"QPGesture: Quantization-Based and Phase-Guided Motion Matching for Natural Speech-Driven Gesture Generation","created":"2023-05-18","cited_by_count":40},{"id":"2111.15483","title":"ST-MFNet: A Spatio-Temporal Multi-Flow Network for Frame Interpolation","created":"2021-11-30","cited_by_count":35},{"id":"2404.01862","title":"Co-Speech Gesture Video Generation via Motion-Decoupled Diffusion Model","created":"2024-04-02","cited_by_count":35},{"id":"2206.13454","title":"Optimizing Video Prediction via Video Frame Interpolation","created":"2022-06-27","cited_by_count":28},{"id":"2304.02225","title":"BiFormer: Learning Bilateral Motion Estimation via Bilateral Transformer for 4K Video Frame Interpolation","created":"2023-04-05","cited_by_count":23},{"id":"2310.06851","title":"BodyFormer: Semantics-guided 3D Body Gesture Synthesis with Transformer","created":"2023-09-07","cited_by_count":21},{"id":"2207.11524","title":"Audio-driven Neural Gesture Reenactment with Video Motion Graphs","created":"2022-07-23","cited_by_count":18},{"id":"2311.17532","title":"Weakly-Supervised Emotion Transition Learning for Diverse 3D Co-speech Gesture Generation","created":"2023-11-29","cited_by_count":17}],"next_cursor":null}