{"list":"other","total":69,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"id":"1503.03832","title":"FaceNet: A Unified Embedding for Face Recognition and Clustering","created":"2015-03-12","cited_by_count":2849},{"id":"2209.14792","title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","created":"2022-09-29","cited_by_count":1742},{"id":"2102.05095","title":"Is Space-Time Attention All You Need for Video Understanding?","created":"2021-02-09","cited_by_count":1620},{"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":"2104.00650","title":"Frozen in Time: A Joint Video and Image Encoder for End-to-End Retrieval","created":"2021-04-01","cited_by_count":1177},{"id":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175},{"id":"2103.03206","title":"Perceiver: General Perception with Iterative Attention","created":"2021-03-04","cited_by_count":1104},{"id":"2304.07327","title":"OpenAssistant Conversations -- Democratizing Large Language Model Alignment","created":"2023-04-14","cited_by_count":721},{"id":"1908.09203","title":"Release Strategies and the Social Impacts of Language Models","created":"2019-08-24","cited_by_count":513},{"id":"2007.10639","title":"Multi-modal Transformer for Video Retrieval","created":"2020-07-21","cited_by_count":395},{"id":"2212.09058","title":"BEATs: Audio Pre-Training with Acoustic Tokenizers","created":"2022-12-18","cited_by_count":388},{"id":"2107.00135","title":"Attention Bottlenecks for Multimodal Fusion","created":"2021-06-30","cited_by_count":361},{"id":"2106.13043","title":"AudioCLIP: Extending CLIP to Image, Text and Audio","created":"2021-06-24","cited_by_count":339},{"id":"1804.03641","title":"Audio-Visual Scene Analysis with Self-Supervised Multisensory Features","created":"2018-04-10","cited_by_count":335},{"id":"2303.00747","title":"WhisperX: Time-Accurate Speech Transcription of Long-Form Audio","created":"2023-03-01","cited_by_count":326},{"id":"2005.03545","title":"MISA: Modality-Invariant and -Specific Representations for Multimodal Sentiment Analysis","created":"2020-05-07","cited_by_count":265},{"id":"2302.14115","title":"Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning","created":"2023-02-27","cited_by_count":263},{"id":"2106.11097","title":"CLIP2Video: Mastering Video-Text Retrieval via Image CLIP","created":"2021-06-21","cited_by_count":225},{"id":"2110.11499","title":"Wav2CLIP: Learning Robust Audio Representations From CLIP","created":"2021-10-21","cited_by_count":213},{"id":"2004.12943","title":"Audio-Visual Instance Discrimination with Cross-Modal Agreement","created":"2020-04-27","cited_by_count":195},{"id":"1803.03849","title":"Learning to Localize Sound Source in Visual Scenes","created":"2018-03-10","cited_by_count":189},{"id":"2208.03550","title":"Frozen CLIP Models are Efficient Video Learners","created":"2022-08-06","cited_by_count":182},{"id":"1906.01815","title":"Towards Multimodal Sarcasm Detection (An _Obviously_ Perfect Paper)","created":"2019-06-05","cited_by_count":174},{"id":"2010.10915","title":"Contrastive Learning of General-Purpose Audio Representations","created":"2020-10-21","cited_by_count":169},{"id":"1802.00927","title":"Memory Fusion Network for Multi-view Sequential Learning","created":"2018-02-03","cited_by_count":168},{"id":"2111.13196","title":"SwinBERT: End-to-End Transformers with Sparse Attention for Video Captioning","created":"2021-11-25","cited_by_count":162},{"id":"2210.07839","title":"Contrastive Audio-Visual Masked Autoencoder","created":"2022-10-02","cited_by_count":146},{"id":"2211.08553","title":"Hybrid Transformers for Music Source Separation","created":"2022-11-15","cited_by_count":134},{"id":"1904.06618","title":"UR-FUNNY: A Multimodal Language Dataset for Understanding Humor","created":"2019-04-14","cited_by_count":132},{"id":"1806.03198","title":"Spreading vectors for similarity search","created":"2018-06-08","cited_by_count":118},{"id":"1611.00471","title":"Dual Attention Networks for Multimodal Reasoning and Matching","created":"2016-11-02","cited_by_count":114},{"id":"2003.07758","title":"Multi-modal Dense Video Captioning","created":"2020-03-17","cited_by_count":113},{"id":"2006.09199","title":"AVLnet: Learning Audio-Visual Language Representations from Instructional Videos","created":"2020-06-16","cited_by_count":111},{"id":"1804.04121","title":"The Conversation: Deep Audio-Visual Speech Enhancement","created":"2018-04-11","cited_by_count":109},{"id":"2103.06695","title":"BYOL for Audio: Self-Supervised Learning for General-Purpose Audio Representation","created":"2021-03-11","cited_by_count":106},{"id":"1911.13254","title":"Music Source Separation in the Waveform Domain","created":"2019-11-27","cited_by_count":99},{"id":"2107.00650","title":"CLIP-It! Language-Guided Video Summarization","created":"2021-07-01","cited_by_count":99},{"id":"2112.09418","title":"Audio Retrieval with Natural Language Queries: A Benchmark Study","created":"2021-12-17","cited_by_count":61},{"id":"1809.08001","title":"Perfect match: Improved cross-modal embeddings for audio-visual synchronisation","created":"2018-09-21","cited_by_count":60},{"id":"1810.04635","title":"Multimodal Speech Emotion Recognition Using Audio and Text","created":"2018-10-10","cited_by_count":55},{"id":"2007.09902","title":"Sep-Stereo: Visually Guided Stereophonic Audio Generation by Associating Source Separation","created":"2020-07-20","cited_by_count":55},{"id":"2310.06838","title":"AutoAD II: The Sequel -- Who, When, and What in Movie Audio Description","created":"2023-10-10","cited_by_count":49},{"id":"2204.07402","title":"BYOL for Audio: Exploring Pre-trained General-purpose Audio Representations","created":"2022-04-15","cited_by_count":36},{"id":"2104.12807","title":"Multimodal Self-Supervised Learning of General Audio Representations","created":"2021-04-26","cited_by_count":32},{"id":"2204.08121","title":"End-to-end Dense Video Captioning as Sequence Generation","created":"2022-04-18","cited_by_count":27},{"id":"2303.17489","title":"Prefix tuning for automated audio captioning","created":"2023-03-30","cited_by_count":27},{"id":"2007.00222","title":"A Transformer-based Audio Captioning Model with Keyword Estimation","created":"2020-07-01","cited_by_count":24},{"id":"2105.09939","title":"Face, Body, Voice: Video Person-Clustering with Multiple Modalities","created":"2021-05-20","cited_by_count":24},{"id":"2308.12558","title":"Hyperbolic Audio-visual Zero-shot Learning","created":"2023-08-24","cited_by_count":19},{"id":"2110.10596","title":"Look at What I'm Doing: Self-Supervised Spatial Grounding of Narrations in Instructional Videos","created":"2021-10-20","cited_by_count":18},{"id":"2303.15616","title":"Fine-grained Audible Video Description","created":"2023-03-27","cited_by_count":18},{"id":"2210.16428","title":"Visually-Aware Audio Captioning With Adaptive Audio-Visual Attention","created":"2022-10-28","cited_by_count":13},{"id":"2303.05681","title":"Improving Text-Audio Retrieval by Text-aware Attention Pooling and Prior Matrix Revised Loss","created":"2023-03-10","cited_by_count":12},{"id":"2009.10991","title":"Attention Driven Fusion for Multi-Modal Emotion Recognition","created":"2020-09-23","cited_by_count":11},{"id":"2203.13645","title":"Audio-text Retrieval in Context","created":"2022-03-25","cited_by_count":10},{"id":"2210.04883","title":"SCAM! Transferring humans between images with Semantic Cross Attention Modulation","created":"2022-10-10","cited_by_count":10},{"id":"1501.01186","title":"Analysing domain shift factors between videos and images for object detection","created":"2015-01-06","cited_by_count":9},{"id":"2307.11636","title":"OxfordTVG-HIC: Can Machine Make Humorous Captions from Images?","created":"2023-07-21","cited_by_count":9},{"id":"1805.00625","title":"Multimodal Utterance-level Affect Analysis using Visual, Audio and Text Features","created":"2018-05-02","cited_by_count":1}],"next_cursor":null}