{"list":"other","total":51,"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":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"2507.06261","title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","created":"2025-07-07","cited_by_count":3796},{"id":"1812.01717","title":"Towards Accurate Generative Models of Video: A New Metric & Challenges","created":"2018-12-03","cited_by_count":1234},{"id":"2503.20215","title":"Qwen2.5-Omni Technical Report","created":"2025-03-26","cited_by_count":736},{"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":"1810.02508","title":"MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversations","created":"2018-10-05","cited_by_count":643},{"id":"2212.04048","title":"Executing your Commands via Motion Diffusion in Latent Space","created":"2022-12-08","cited_by_count":575},{"id":"2004.12992","title":"MakeItTalk: Speaker-Aware Talking-Head Animation","created":"2020-04-27","cited_by_count":312},{"id":"2104.11116","title":"Pose-Controllable Talking Face Generation by Implicitly Modularized Audio-Visual Representation","created":"2021-04-22","cited_by_count":288},{"id":"1905.08233","title":"Few-Shot Adversarial Learning of Realistic Neural Talking Head Models","created":"2019-05-20","cited_by_count":284},{"id":"1905.03820","title":"Hierarchical Cross-Modal Talking Face Generationwith Dynamic Pixel-Wise Loss","created":"2019-05-09","cited_by_count":252},{"id":"1912.05566","title":"Neural Voice Puppetry: Audio-driven Facial Reenactment","created":"2019-12-11","cited_by_count":250},{"id":"2402.17485","title":"EMO: Emote Portrait Alive -- Generating Expressive Portrait Videos with Audio2Video Diffusion Model under Weak Conditions","created":"2024-02-27","cited_by_count":235},{"id":"1807.07860","title":"Talking Face Generation by Adversarially Disentangled Audio-Visual Representation","created":"2018-07-20","cited_by_count":212},{"id":"2312.15185","title":"emotion2vec: Self-Supervised Pre-Training for Speech Emotion Representation","created":"2023-12-23","cited_by_count":205},{"id":"2407.08136","title":"EchoMimic: Lifelike Audio-Driven Portrait Animations through Editable Landmark Conditions","created":"2024-07-11","cited_by_count":196},{"id":"2404.10667","title":"VASA-1: Lifelike Audio-Driven Talking Faces Generated in Real Time","created":"2024-04-16","cited_by_count":187},{"id":"2203.04036","title":"StyleHEAT: One-Shot High-Resolution Editable Talking Face Generation via Pre-trained StyleGAN","created":"2022-03-08","cited_by_count":169},{"id":"2404.19759","title":"MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Model","created":"2024-04-30","cited_by_count":168},{"id":"1803.10404","title":"Lip Movements Generation at a Glance","created":"2018-03-28","cited_by_count":155},{"id":"2205.15278","title":"EAMM: One-Shot Emotional Talking Face via Audio-Based Emotion-Aware Motion Model","created":"2022-05-30","cited_by_count":151},{"id":"2107.09293","title":"Audio2Head: Audio-driven One-shot Talking-head Generation with Natural Head Motion","created":"2021-07-20","cited_by_count":149},{"id":"2303.11089","title":"EmoTalk: Speech-Driven Emotional Disentanglement for 3D Face Animation","created":"2023-03-20","cited_by_count":142},{"id":"2301.03786","title":"DiffTalk: Crafting Diffusion Models for Generalized Audio-Driven Portraits Animation","created":"2023-01-10","cited_by_count":136},{"id":"2201.07786","title":"Semantic-Aware Implicit Neural Audio-Driven Video Portrait Generation","created":"2022-01-19","cited_by_count":119},{"id":"2007.08547","title":"Talking-head Generation with Rhythmic Head Motion","created":"2020-07-16","cited_by_count":112},{"id":"2305.08293","title":"Identity-Preserving Talking Face Generation with Landmark and Appearance Priors","created":"2023-05-15","cited_by_count":98},{"id":"2207.11770","title":"Learning Dynamic Facial Radiance Fields for Few-Shot Talking Head Synthesis","created":"2022-07-24","cited_by_count":97},{"id":"2211.14506","title":"Progressive Disentangled Representation Learning for Fine-Grained Controllable Talking Head Synthesis","created":"2022-11-26","cited_by_count":93},{"id":"2301.01081","title":"StyleTalk: One-shot Talking Head Generation with Controllable Speaking Styles","created":"2023-01-03","cited_by_count":92},{"id":"2112.02749","title":"One-shot Talking Face Generation from Single-speaker Audio-Visual Correlation Learning","created":"2021-12-06","cited_by_count":87},{"id":"2309.04946","title":"Efficient Emotional Adaptation for Audio-Driven Talking-Head Generation","created":"2023-09-10","cited_by_count":81},{"id":"2404.01647","title":"EDTalk: Efficient Disentanglement for Emotional Talking Head Synthesis","created":"2024-04-02","cited_by_count":80},{"id":"1907.00193","title":"Frame attention networks for facial expression recognition in videos","created":"2019-06-29","cited_by_count":56},{"id":"2212.04248","title":"Talking Head Generation with Probabilistic Audio-to-Visual Diffusion Priors","created":"2022-12-07","cited_by_count":55},{"id":"2211.09809","title":"SPACE: Speech-driven Portrait Animation with Controllable Expression","created":"2022-11-17","cited_by_count":49},{"id":"2412.01064","title":"FLOAT: Generative Motion Latent Flow Matching for Audio-driven Talking Portrait","created":"2024-12-02","cited_by_count":40},{"id":"2403.06365","title":"Style2Talker: High-Resolution Talking Head Generation with Emotion Style and Art Style","created":"2024-03-11","cited_by_count":33},{"id":"2411.16726","title":"EmotiveTalk: Expressive Talking Head Generation through Audio Information Decoupling and Emotional Video Diffusion","created":"2024-11-23","cited_by_count":16},{"id":"2303.11548","title":"Emotionally Enhanced Talking Face Generation","created":"2023-03-21","cited_by_count":14},{"id":"2503.19383","title":"MVPortrait: Text-Guided Motion and Emotion Control for Multi-view Vivid Portrait Animation","created":"2025-03-25","cited_by_count":14},{"id":"2209.08289","title":"Continuously Controllable Facial Expression Editing in Talking Face Videos","created":"2022-09-17","cited_by_count":13},{"id":"2410.00316","title":"EmoKnob: Enhance Voice Cloning with Fine-Grained Emotion Control","created":"2024-10-01","cited_by_count":13},{"id":"2501.01808","title":"MoEE: Mixture of Emotion Experts for Audio-Driven Portrait Animation","created":"2025-01-03","cited_by_count":12},{"id":"2406.04930","title":"MA-AVT: Modality Alignment for Parameter-Efficient Audio-Visual Transformers","created":"2024-06-07","cited_by_count":11},{"id":"2308.04830","title":"VAST: Vivify Your Talking Avatar via Zero-Shot Expressive Facial Style Transfer","created":"2023-08-09","cited_by_count":7},{"id":"2310.12459","title":"Affective Conversational Agents: Understanding Expectations and Personal Influences","created":"2023-10-19","cited_by_count":6},{"id":"2501.08393","title":"Empathetic Conversational Agents: Utilizing Neural and Physiological Signals for Enhanced Empathetic Interactions","created":"2025-01-14","cited_by_count":3},{"id":"2503.19416","title":"EmoHead: Emotional Talking Head via Manipulating Semantic Expression Parameters","created":"2025-03-25","cited_by_count":3}],"next_cursor":null}