{"list":"other","total":51,"rows":[{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"2211.05100","title":"BLOOM: A 176B-Parameter Open-Access Multilingual Language Model","created":"2022-11-09","cited_by_count":1984},{"id":"2310.02255","title":"MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts","created":"2023-10-03","cited_by_count":1614},{"id":"2305.06355","title":"VideoChat: Chat-Centric Video Understanding","created":"2023-05-10","cited_by_count":857},{"id":"2306.01116","title":"The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data, and Web Data Only","created":"2023-06-01","cited_by_count":763},{"id":"2309.17421","title":"The Dawn of LMMs: Preliminary Explorations with GPT-4V(ision)","created":"2023-09-29","cited_by_count":681},{"id":"1906.00295","title":"Multimodal Transformer for Unaligned Multimodal Language Sequences","created":"2019-06-01","cited_by_count":645},{"id":"2305.11000","title":"SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities","created":"2023-05-18","cited_by_count":529},{"id":"1708.03985","title":"AffectNet: A Database for Facial Expression, Valence, and Arousal Computing in the Wild","created":"2017-08-14","cited_by_count":492},{"id":"1707.07250","title":"Tensor Fusion Network for Multimodal Sentiment Analysis","created":"2017-07-23","cited_by_count":433},{"id":"2305.16355","title":"PandaGPT: One Model To Instruction-Follow Them All","created":"2023-05-25","cited_by_count":334},{"id":"1307.0414","title":"Challenges in Representation Learning: A report on three machine learning contests","created":"2013-07-01","cited_by_count":302},{"id":"1804.08348","title":"Deep Facial Expression Recognition: A Survey","created":"2018-04-23","cited_by_count":270},{"id":"2005.03545","title":"MISA: Modality-Invariant and -Specific Representations for Multimodal Sentiment Analysis","created":"2020-05-07","cited_by_count":265},{"id":"1806.06176","title":"Learning Factorized Multimodal Representations","created":"2018-06-16","cited_by_count":171},{"id":"1802.00927","title":"Memory Fusion Network for Multi-view Sequential Learning","created":"2018-02-03","cited_by_count":168},{"id":"1608.01041","title":"Training Deep Networks for Facial Expression Recognition with Crowd-Sourced Label Distribution","created":"2016-08-03","cited_by_count":158},{"id":"2002.10392","title":"Suppressing Uncertainties for Large-Scale Facial Expression Recognition","created":"2020-02-24","cited_by_count":157},{"id":"2109.00412","title":"Improving Multimodal Fusion with Hierarchical Mutual Information Maximization for Multimodal Sentiment Analysis","created":"2021-09-01","cited_by_count":131},{"id":"2008.05924","title":"DFEW: A Large-Scale Database for Recognizing Dynamic Facial Expressions in the Wild","created":"2020-08-13","cited_by_count":128},{"id":"1905.04075","title":"Region Attention Networks for Pose and Occlusion Robust Facial Expression Recognition","created":"2019-05-10","cited_by_count":127},{"id":"2108.11116","title":"TransFER: Learning Relation-aware Facial Expression Representations with Transformers","created":"2021-08-25","cited_by_count":85},{"id":"2310.19773","title":"MM-VID: Advancing Video Understanding with GPT-4V(ision)","created":"2023-10-30","cited_by_count":83},{"id":"2307.07961","title":"EmoSet: A Large-scale Visual Emotion Dataset with Rich Attributes","created":"2023-07-16","cited_by_count":82},{"id":"2310.09909","title":"Can GPT-4V(ision) Serve Medical Applications? Case Studies on GPT-4V for Multimodal Medical Diagnosis","created":"2023-10-15","cited_by_count":77},{"id":"1605.02677","title":"Building a Large Scale Dataset for Image Emotion Recognition: The Fine Print and The Benchmark","created":"2016-05-09","cited_by_count":71},{"id":"2203.09463","title":"FERV39k: A Large-Scale Multi-Scene Dataset for Facial Expression Recognition in Videos","created":"2022-03-17","cited_by_count":69},{"id":"2207.10299","title":"Learn From All: Erasing Attention Consistency for Noisy Label Facial Expression Recognition","created":"2022-07-21","cited_by_count":67},{"id":"1907.00193","title":"Frame attention networks for facial expression recognition in videos","created":"2019-06-29","cited_by_count":56},{"id":"2109.07270","title":"Distract Your Attention: Multi-head Cross Attention Network for Facial Expression Recognition","created":"2021-09-15","cited_by_count":55},{"id":"2204.04083","title":"POSTER: A Pyramid Cross-Fusion Transformer Network for Facial Expression Recognition","created":"2022-04-08","cited_by_count":49},{"id":"1509.06041","title":"Robust Image Sentiment Analysis Using Progressively Trained and Domain Transferred Deep Networks","created":"2015-09-20","cited_by_count":46},{"id":"2107.02823","title":"Deep Learning for Micro-expression Recognition: A Survey","created":"2021-07-06","cited_by_count":43},{"id":"2307.02227","title":"MAE-DFER: Efficient Masked Autoencoder for Self-supervised Dynamic Facial Expression Recognition","created":"2023-07-05","cited_by_count":43},{"id":"2208.10335","title":"Intensity-Aware Loss for Dynamic Facial Expression Recognition in the Wild","created":"2022-08-19","cited_by_count":41},{"id":"2311.15732","title":"GPT4Vis: What Can GPT-4 Do for Zero-shot Visual Recognition?","created":"2023-11-27","cited_by_count":35},{"id":"2304.08981","title":"MER 2023: Multi-label Learning, Modality Robustness, and Semi-Supervised Learning","created":"2023-04-18","cited_by_count":33},{"id":"2205.04749","title":"Spatio-Temporal Transformer for Dynamic Facial Expression Recognition in the Wild","created":"2022-05-10","cited_by_count":29},{"id":"1901.04656","title":"Spatiotemporal Recurrent Convolutional Networks for Recognizing Spontaneous Micro-expressions","created":"2019-01-15","cited_by_count":25},{"id":"2301.12149","title":"POSTER++: A simpler and stronger facial expression recognition network","created":"2023-01-28","cited_by_count":25},{"id":"1410.8586","title":"DeepSentiBank: Visual Sentiment Concept Classification with Deep Convolutional Neural Networks","created":"2014-10-30","cited_by_count":24},{"id":"2012.07175","title":"MSAF: Multimodal Split Attention Fusion","created":"2020-12-13","cited_by_count":23},{"id":"2103.10189","title":"Learning to Amend Facial Expression Representation via De-albino and Affinity","created":"2021-03-18","cited_by_count":19},{"id":"2306.15401","title":"Explainable Multimodal Emotion Recognition","created":"2023-06-27","cited_by_count":19},{"id":"2311.04199","title":"Exploring Recommendation Capabilities of GPT-4V(ision): A Preliminary Case Study","created":"2023-11-07","cited_by_count":12},{"id":"2111.02172","title":"A cross-modal fusion network based on self-attention and residual structure for multimodal emotion recognition","created":"2021-11-03","cited_by_count":11},{"id":"2208.08106","title":"Disentangling Identity and Pose for Facial Expression Recognition","created":"2022-08-17","cited_by_count":11},{"id":"2004.11639","title":"Survey on Visual Sentiment Analysis","created":"2020-04-24","cited_by_count":5}],"next_cursor":null}