{"list":"other","total":54,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"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":"1703.05175","title":"Prototypical Networks for Few-shot Learning","created":"2017-03-15","cited_by_count":3015},{"id":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"id":"1409.7495","title":"Unsupervised Domain Adaptation by Backpropagation","created":"2014-09-26","cited_by_count":1917},{"id":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175},{"id":"2203.01941","title":"Autoregressive Image Generation using Residual Quantization","created":"2022-03-03","cited_by_count":722},{"id":"2210.13438","title":"High Fidelity Neural Audio Compression","created":"2022-10-24","cited_by_count":687},{"id":"1801.04062","title":"MINE: Mutual Information Neural Estimation","created":"2018-01-12","cited_by_count":683},{"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":"1801.07593","title":"Mitigating Unwanted Biases with Adversarial Learning","created":"2018-01-22","cited_by_count":663},{"id":"1809.01696","title":"TVQA: Localized, Compositional Video Question Answering","created":"2018-09-05","cited_by_count":467},{"id":"2206.08916","title":"Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks","created":"2022-06-17","cited_by_count":421},{"id":"2406.07550","title":"An Image is Worth 32 Tokens for Reconstruction and Generation","created":"2024-06-11","cited_by_count":302},{"id":"2201.02184","title":"Learning Audio-Visual Speech Representation by Masked Multimodal Cluster Prediction","created":"2022-01-05","cited_by_count":287},{"id":"1610.09001","title":"SoundNet: Learning Sound Representations from Unlabeled Video","created":"2016-10-27","cited_by_count":247},{"id":"2004.11138","title":"The Creation and Detection of Deepfakes: A Survey","created":"2020-04-23","cited_by_count":247},{"id":"2006.12013","title":"CLUB: A Contrastive Log-ratio Upper Bound of Mutual Information","created":"2020-06-22","cited_by_count":235},{"id":"2403.03100","title":"NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models","created":"2024-03-05","cited_by_count":226},{"id":"2203.14072","title":"Learning to Answer Questions in Dynamic Audio-Visual Scenarios","created":"2022-03-26","cited_by_count":191},{"id":"2203.09043","title":"Latent Image Animator: Learning to Animate Images via Latent Space Navigation","created":"2022-03-17","cited_by_count":175},{"id":"2007.10558","title":"Unified Multisensory Perception: Weakly-Supervised Audio-Visual Video Parsing","created":"2020-07-21","cited_by_count":146},{"id":"2006.08558","title":"Learning Diverse and Discriminative Representations via the Principle of Maximal Coding Rate Reduction","created":"2020-06-15","cited_by_count":142},{"id":"2309.04669","title":"Unified Language-Vision Pretraining in LLM with Dynamic Discrete Visual Tokenization","created":"2023-09-09","cited_by_count":87},{"id":"2104.00239","title":"Positive Sample Propagation along the Audio-Visual Event Line","created":"2021-04-01","cited_by_count":69},{"id":"1810.00108","title":"Audio-Visual Speech Recognition With A Hybrid CTC/Attention Architecture","created":"2018-09-28","cited_by_count":64},{"id":"2202.12555","title":"6D Rotation Representation For Unconstrained Head Pose Estimation","created":"2022-02-25","cited_by_count":64},{"id":"2203.00048","title":"Multi-modal Alignment using Representation Codebook","created":"2022-02-28","cited_by_count":63},{"id":"2508.18621","title":"Wan-S2V: Audio-Driven Cinematic Video Generation","created":"2025-08-26","cited_by_count":61},{"id":"2204.04588","title":"Robust Cross-Modal Representation Learning with Progressive Self-Distillation","created":"2022-04-10","cited_by_count":55},{"id":"2211.09980","title":"Contrastive Positive Sample Propagation along the Audio-Visual Event Line","created":"2022-11-18","cited_by_count":50},{"id":"2206.08919","title":"VLMixer: Unpaired Vision-Language Pre-training via Cross-Modal CutMix","created":"2022-06-17","cited_by_count":45},{"id":"2412.01064","title":"FLOAT: Generative Motion Latent Flow Matching for Audio-driven Talking Portrait","created":"2024-12-02","cited_by_count":40},{"id":"2305.14381","title":"Connecting Multi-modal Contrastive Representations","created":"2023-05-22","cited_by_count":36},{"id":"2106.05438","title":"Cross-Modal Discrete Representation Learning","created":"2021-06-10","cited_by_count":35},{"id":"2207.12661","title":"Learning Visual Representation from Modality-Shared Contrastive Language-Image Pre-training","created":"2022-07-26","cited_by_count":32},{"id":"2211.13929","title":"XKD: Cross-modal Knowledge Distillation with Domain Alignment for Video Representation Learning","created":"2022-11-25","cited_by_count":31},{"id":"2503.06764","title":"SemHiTok: A Unified Image Tokenizer via Semantic-Guided Hierarchical Codebook for Multimodal Understanding and Generation","created":"2025-03-09","cited_by_count":21},{"id":"2508.13618","title":"TalkVid: A Large-Scale Diversified Dataset for Audio-Driven Talking Head Synthesis","created":"2025-08-19","cited_by_count":18},{"id":"2405.00878","title":"SonicDiffusion: Audio-Driven Image Generation and Editing with Pretrained Diffusion Models","created":"2024-05-01","cited_by_count":15},{"id":"2104.02687","title":"Strumming to the Beat: Audio-Conditioned Contrastive Video Textures","created":"2021-04-06","cited_by_count":14},{"id":"2403.05168","title":"Enhancing Multimodal Unified Representations for Cross Modal Generalization","created":"2024-03-08","cited_by_count":12},{"id":"2503.22201","title":"Multi-modal Knowledge Distillation-based Human Trajectory Forecasting","created":"2025-03-28","cited_by_count":10},{"id":"2212.13937","title":"Towards Disentangling Relevance and Bias in Unbiased Learning to Rank","created":"2022-12-28","cited_by_count":9},{"id":"2410.13726","title":"DAWN: Dynamic Frame Avatar with Non-autoregressive Diffusion Framework for Talking Head Video Generation","created":"2024-10-17","cited_by_count":8},{"id":"2508.08237","title":"VGGSounder: Audio-Visual Evaluations for Foundation Models","created":"2025-08-11","cited_by_count":8},{"id":"2412.10208","title":"Efficient Generative Modeling with Residual Vector Quantization-Based Tokens","created":"2024-12-13","cited_by_count":7},{"id":"2509.23147","title":"BFA: Real-time Multilingual Text-to-speech Forced Alignment","created":"2025-09-27","cited_by_count":5},{"id":"2404.03179","title":"UniAV: Unified Audio-Visual Perception for Multi-Task Video Event Localization","created":"2024-04-04","cited_by_count":4},{"id":"2509.17006","title":"MBCodec:Thorough disentangle for high-fidelity audio compression","created":"2025-09-21","cited_by_count":2},{"id":"2509.19186","title":"Improving Test-Time Performance of RVQ-based Neural Codecs","created":"2025-09-23","cited_by_count":1}],"next_cursor":null}