{"list":"other","total":119,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"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":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"2303.12712","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","created":"2023-03-22","cited_by_count":2592},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"2303.17580","title":"HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face","created":"2023-03-30","cited_by_count":1190},{"id":"2305.05665","title":"ImageBind: One Embedding Space To Bind Them All","created":"2023-05-09","cited_by_count":1175},{"id":"2212.10156","title":"Planning-oriented Autonomous Driving","created":"2022-12-20","cited_by_count":1087},{"id":"1705.09406","title":"Multimodal Machine Learning: A Survey and Taxonomy","created":"2017-05-26","cited_by_count":1013},{"id":"1506.04757","title":"Image-based Recommendations on Styles and Substitutes","created":"2015-06-15","cited_by_count":706},{"id":"1604.02808","title":"NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis","created":"2016-04-11","cited_by_count":686},{"id":"2303.04671","title":"Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models","created":"2023-03-08","cited_by_count":668},{"id":"1810.02508","title":"MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversations","created":"2018-10-05","cited_by_count":643},{"id":"2309.05519","title":"NExT-GPT: Any-to-Any Multimodal LLM","created":"2023-09-11","cited_by_count":615},{"id":"2303.08128","title":"ViperGPT: Visual Inference via Python Execution for Reasoning","created":"2023-03-14","cited_by_count":603},{"id":"2001.04193","title":"Deep Learning for Person Re-identification: A Survey and Outlook","created":"2020-01-13","cited_by_count":549},{"id":"2006.13256","title":"Rescaling Egocentric Vision","created":"2020-06-23","cited_by_count":540},{"id":"1602.01585","title":"Ups and Downs: Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filtering","created":"2016-02-04","cited_by_count":520},{"id":"2303.11381","title":"MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Action","created":"2023-03-20","cited_by_count":517},{"id":"1905.08094","title":"Be Your Own Teacher: Improve the Performance of Convolutional Neural Networks via Self Distillation","created":"2019-05-17","cited_by_count":497},{"id":"2310.01852","title":"LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment","created":"2023-10-03","cited_by_count":370},{"id":"2107.00135","title":"Attention Bottlenecks for Multimodal Fusion","created":"2021-06-30","cited_by_count":361},{"id":"1510.04389","title":"Sketch-based Manga Retrieval using Manga109 Dataset","created":"2015-10-15","cited_by_count":329},{"id":"1810.11654","title":"3D MRI brain tumor segmentation using autoencoder regularization","created":"2018-10-27","cited_by_count":328},{"id":"2103.05677","title":"SMIL: Multimodal Learning with Severely Missing Modality","created":"2021-03-09","cited_by_count":245},{"id":"2402.12226","title":"AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling","created":"2024-02-19","cited_by_count":217},{"id":"2305.11846","title":"Any-to-Any Generation via Composable Diffusion","created":"2023-05-19","cited_by_count":204},{"id":"1606.06259","title":"MOSI: Multimodal Corpus of Sentiment Intensity and Subjectivity Analysis in Online Opinion Videos","created":"2016-06-20","cited_by_count":194},{"id":"2311.05437","title":"LLaVA-Plus: Learning to Use Tools for Creating Multimodal Agents","created":"2023-11-09","cited_by_count":193},{"id":"2204.05454","title":"Are Multimodal Transformers Robust to Missing Modality?","created":"2022-04-12","cited_by_count":186},{"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":"1806.06176","title":"Learning Factorized Multimodal Representations","created":"2018-06-16","cited_by_count":171},{"id":"2307.14126","title":"Multi-modal Learning with Missing Modality via Shared-Specific Feature Modelling","created":"2023-07-26","cited_by_count":163},{"id":"2107.07502","title":"MultiBench: Multiscale Benchmarks for Multimodal Representation Learning","created":"2021-07-15","cited_by_count":146},{"id":"1405.2941","title":"Cross-view Action Modeling, Learning and Recognition","created":"2014-05-12","cited_by_count":134},{"id":"2308.02097","title":"Multi-interactive Feature Learning and a Full-time Multi-modality Benchmark for Image Fusion and Segmentation","created":"2023-08-04","cited_by_count":129},{"id":"2303.03369","title":"Multimodal Prompting with Missing Modalities for Visual Recognition","created":"2023-03-06","cited_by_count":121},{"id":"2303.01480","title":"Delivering Arbitrary-Modal Semantic Segmentation","created":"2023-03-02","cited_by_count":117},{"id":"1903.05485","title":"MMKG: Multi-Modal Knowledge Graphs","created":"2019-03-13","cited_by_count":105},{"id":"1804.02516","title":"Learning a Text-Video Embedding from Incomplete and Heterogeneous Data","created":"2018-04-07","cited_by_count":103},{"id":"1802.00923","title":"Multi-attention Recurrent Network for Human Communication Comprehension","created":"2018-02-03","cited_by_count":89},{"id":"2203.02177","title":"GCNet: Graph Completion Network for Incomplete Multimodal Learning in Conversation","created":"2022-03-04","cited_by_count":87},{"id":"1808.07275","title":"CentralNet: a Multilayer Approach for Multimodal Fusion","created":"2018-08-22","cited_by_count":86},{"id":"2210.17292","title":"M$^3$Care: Learning with Missing Modalities in Multimodal Healthcare Data","created":"2022-10-28","cited_by_count":72},{"id":"2311.04219","title":"OtterHD: A High-Resolution Multi-modality Model","created":"2023-11-07","cited_by_count":72},{"id":"2402.19469","title":"Humanoid Locomotion as Next Token Prediction","created":"2024-02-29","cited_by_count":69},{"id":"2002.09708","title":"Robust Multimodal Brain Tumor Segmentation via Feature Disentanglement and Gated Fusion","created":"2020-02-22","cited_by_count":68},{"id":"2104.02904","title":"Multimodal Object Detection via Probabilistic Ensembling","created":"2021-04-07","cited_by_count":68},{"id":"2106.09564","title":"Knowledge distillation from multi-modal to mono-modal segmentation networks","created":"2021-06-17","cited_by_count":68},{"id":"2003.05136","title":"CASIA-SURF CeFA: A Benchmark for Multi-modal Cross-ethnicity Face Anti-spoofing","created":"2020-03-11","cited_by_count":66},{"id":"1908.10654","title":"CASIA-SURF: A Large-scale Multi-modal Benchmark for Face Anti-spoofing","created":"2019-08-28","cited_by_count":61},{"id":"2303.05302","title":"M3AE: Multimodal Representation Learning for Brain Tumor Segmentation with Missing Modalities","created":"2023-03-09","cited_by_count":56},{"id":"2204.00102","title":"Dynamic Multimodal Fusion","created":"2022-03-31","cited_by_count":55},{"id":"2211.13916","title":"Towards Good Practices for Missing Modality Robust Action Recognition","created":"2022-11-25","cited_by_count":54},{"id":"2403.06197","title":"DrFuse: Learning Disentangled Representation for Clinical Multi-Modal Fusion with Missing Modality and Modal Inconsistency","created":"2024-03-10","cited_by_count":53},{"id":"2004.06500","title":"SpaceNet 6: Multi-Sensor All Weather Mapping Dataset","created":"2020-04-14","cited_by_count":47},{"id":"2302.00646","title":"Epic-Sounds: A Large-scale Dataset of Actions That Sound","created":"2023-02-01","cited_by_count":47},{"id":"2005.14511","title":"NuClick: A Deep Learning Framework for Interactive Segmentation of Microscopy Images","created":"2020-05-29","cited_by_count":46},{"id":"2310.01035","title":"Learnable Cross-modal Knowledge Distillation for Multi-modal Learning with Missing Modality","created":"2023-10-02","cited_by_count":45},{"id":"2105.10196","title":"Multimodal Remote Sensing Benchmark Datasets for Land Cover Classification with A Shared and Specific Feature Learning Model","created":"2021-05-21","cited_by_count":43},{"id":"2106.14591","title":"ACN: Adversarial Co-training Network for Brain Tumor Segmentation with Missing Modalities","created":"2021-06-28","cited_by_count":43},{"id":"2112.02222","title":"Predicting Axillary Lymph Node Metastasis in Early Breast Cancer Using Deep Learning on Primary Tumor Biopsy Slides","created":"2021-12-04","cited_by_count":43},{"id":"1904.07290","title":"Brain Tumor Segmentation on MRI with Missing Modalities","created":"2019-04-15","cited_by_count":42},{"id":"2104.06231","title":"Latent Correlation Representation Learning for Brain Tumor Segmentation with Missing MRI Modalities","created":"2021-04-13","cited_by_count":42},{"id":"2304.05340","title":"Unified Multi-Modal Image Synthesis for Missing Modality Imputation","created":"2023-04-11","cited_by_count":40},{"id":"2010.00734","title":"Training Strategies to Handle Missing Modalities for Audio-Visual Expression Recognition","created":"2020-10-02","cited_by_count":36},{"id":"2102.07978","title":"A Benchmark of Ocular Disease Intelligent Recognition: One Shot for Multi-disease Detection","created":"2021-02-16","cited_by_count":34},{"id":"1712.06246","title":"A Survey on Multi-View Clustering","created":"2017-12-18","cited_by_count":32},{"id":"2404.16456","title":"Correlation-Decoupled Knowledge Distillation for Multimodal Sentiment Analysis with Incomplete Modalities","created":"2024-04-25","cited_by_count":32},{"id":"2407.11351","title":"Learning Modality-agnostic Representation for Semantic Segmentation from Any Modalities","created":"2024-07-16","cited_by_count":31},{"id":"1907.01011","title":"Learning Representations from Imperfect Time Series Data via Tensor Rank Regularization","created":"2019-07-01","cited_by_count":30},{"id":"2310.03986","title":"Robust Multimodal Learning with Missing Modalities via Parameter-Efficient Adaptation","created":"2023-10-06","cited_by_count":29},{"id":"1409.6813","title":"Histogram of Oriented Principal Components for Cross-View Action Recognition","created":"2014-09-24","cited_by_count":27},{"id":"2104.07123","title":"The MuSe 2021 Multimodal Sentiment Analysis Challenge: Sentiment, Emotion, Physiological-Emotion, and Stress","created":"2021-04-14","cited_by_count":27},{"id":"2305.07214","title":"MMG-Ego4D: Multi-Modal Generalization in Egocentric Action Recognition","created":"2023-05-12","cited_by_count":26},{"id":"2407.05374","title":"Multimodal Prompt Learning with Missing Modalities for Sentiment Analysis and Emotion Recognition","created":"2024-07-07","cited_by_count":26},{"id":"2203.04419","title":"Survival Prediction of Brain Cancer with Incomplete Radiology, Pathology, Genomics, and Demographic Data","created":"2022-03-08","cited_by_count":25},{"id":"2305.02504","title":"Learning Missing Modal Electronic Health Records with Unified Multi-modal Data Embedding and Modality-Aware Attention","created":"2023-05-04","cited_by_count":25},{"id":"2303.09830","title":"Prototype Knowledge Distillation for Medical Segmentation with Missing Modality","created":"2023-03-17","cited_by_count":24},{"id":"2307.16210","title":"Rethinking Uncertainly Missing and Ambiguous Visual Modality in Multi-Modal Entity Alignment","created":"2023-07-30","cited_by_count":21},{"id":"2102.13284","title":"A Large Collection of Real-world Pediatric Sleep Studies","created":"2021-02-26","cited_by_count":20},{"id":"2203.06217","title":"Medical Image Segmentation on MRI Images with Missing Modalities: A Review","created":"2022-03-11","cited_by_count":18},{"id":"2012.00201","title":"Detect, Reject, Correct: Crossmodal Compensation of Corrupted Sensors","created":"2020-12-01","cited_by_count":17},{"id":"2402.15858","title":"FedMM: Federated Multi-Modal Learning with Modality Heterogeneity in Computational Pathology","created":"2024-02-24","cited_by_count":17},{"id":"2407.14796","title":"PASSION: Towards Effective Incomplete Multi-Modal Medical Image Segmentation with Imbalanced Missing Rates","created":"2024-07-20","cited_by_count":17},{"id":"2107.03442","title":"Modality Completion via Gaussian Process Prior Variational Autoencoders for Multi-Modal Glioma Segmentation","created":"2021-07-07","cited_by_count":16},{"id":"2312.15890","title":"Towards Robust Multimodal Prompting With Missing Modalities","created":"2023-12-26","cited_by_count":16},{"id":"2402.19298","title":"Suppress and Rebalance: Towards Generalized Multi-Modal Face Anti-Spoofing","created":"2024-02-29","cited_by_count":16},{"id":"2303.09117","title":"Cross-Modal Causal Intervention for Medical Report Generation","created":"2023-03-16","cited_by_count":15},{"id":"2312.10386","title":"RedCore: Relative Advantage Aware Cross-modal Representation Learning for Missing Modalities with Imbalanced Missing Rates","created":"2023-12-16","cited_by_count":15},{"id":"1709.07383","title":"Urban Land Cover Classification with Missing Data Modalities Using Deep Convolutional Neural Networks","created":"2017-09-21","cited_by_count":14},{"id":"2407.11734","title":"Multi-Modal and Multi-Attribute Generation of Single Cells with CFGen","created":"2024-07-16","cited_by_count":12},{"id":"2401.16923","title":"Fourier Prompt Tuning for Modality-Incomplete Scene Segmentation","created":"2024-01-30","cited_by_count":11},{"id":"2108.10513","title":"Maximum Likelihood Estimation for Multimodal Learning with Missing Modality","created":"2021-08-24","cited_by_count":10},{"id":"2303.07016","title":"HOOV: Hand Out-Of-View Tracking for Proprioceptive Interaction using Inertial Sensing","created":"2023-03-13","cited_by_count":8},{"id":"2401.17859","title":"Towards Semantic Consistency: Dirichlet Energy Driven Robust Multi-Modal Entity Alignment","created":"2024-01-31","cited_by_count":8}],"next_cursor":"100"}