{"list":"other","total":62,"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"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":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"2305.06500","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","created":"2023-05-11","cited_by_count":2876},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"2306.02858","title":"Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding","created":"2023-06-05","cited_by_count":1471},{"id":"2311.10122","title":"Video-LLaVA: Learning United Visual Representation by Alignment Before Projection","created":"2023-11-16","cited_by_count":1402},{"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":"2306.05424","title":"Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models","created":"2023-06-08","cited_by_count":1062},{"id":"2404.16821","title":"How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites","created":"2024-04-25","cited_by_count":1050},{"id":"1604.02878","title":"Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks","created":"2016-04-11","cited_by_count":903},{"id":"2303.15389","title":"EVA-CLIP: Improved Training Techniques for CLIP at Scale","created":"2023-03-27","cited_by_count":798},{"id":"1810.02508","title":"MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversations","created":"2018-10-05","cited_by_count":643},{"id":"2311.17043","title":"LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models","created":"2023-11-28","cited_by_count":546},{"id":"2307.16449","title":"MovieChat: From Dense Token to Sparse Memory for Long Video Understanding","created":"2023-07-31","cited_by_count":542},{"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":"2404.18930","title":"Hallucination of Multimodal Large Language Models: A Survey","created":"2024-04-29","cited_by_count":388},{"id":"2311.08046","title":"Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding","created":"2023-11-14","cited_by_count":371},{"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":"2404.05726","title":"MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understanding","created":"2024-04-08","cited_by_count":229},{"id":"2312.03700","title":"OneLLM: One Framework to Align All Modalities with Language","created":"2023-12-06","cited_by_count":187},{"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":"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":"2406.11161","title":"Emotion-LLaMA: Multimodal Emotion Recognition and Reasoning with Instruction Tuning","created":"2024-06-17","cited_by_count":121},{"id":"2404.03413","title":"MiniGPT4-Video: Advancing Multimodal LLMs for Video Understanding with Interleaved Visual-Textual Tokens","created":"2024-04-04","cited_by_count":118},{"id":"2305.18279","title":"Contextual Object Detection with Multimodal Large Language Models","created":"2023-05-29","cited_by_count":100},{"id":"2311.11860","title":"LION : Empowering Multimodal Large Language Model with Dual-Level Visual Knowledge","created":"2023-11-20","cited_by_count":81},{"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":"2208.00847","title":"MAFW: A Large-scale, Multi-modal, Compound Affective Database for Dynamic Facial Expression Recognition in the Wild","created":"2022-08-01","cited_by_count":65},{"id":"2107.00285","title":"iMiGUE: An Identity-free Video Dataset for Micro-Gesture Understanding and Emotion Analysis","created":"2021-07-01","cited_by_count":63},{"id":"2003.08834","title":"J$\\hat{\\text{A}}$A-Net: Joint Facial Action Unit Detection and Face Alignment via Adaptive Attention","created":"2020-03-18","cited_by_count":62},{"id":"2401.08508","title":"EmoLLMs: A Series of Emotional Large Language Models and Annotation Tools for Comprehensive Affective Analysis","created":"2024-01-16","cited_by_count":62},{"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":"2008.00923","title":"Cross-Domain Facial Expression Recognition: A Unified Evaluation Benchmark and Adversarial Graph Learning","created":"2020-08-03","cited_by_count":46},{"id":"2308.13382","title":"Prompting Visual-Language Models for Dynamic Facial Expression Recognition","created":"2023-08-25","cited_by_count":44},{"id":"2208.10335","title":"Intensity-Aware Loss for Dynamic Facial Expression Recognition in the Wild","created":"2022-08-19","cited_by_count":41},{"id":"2312.05447","title":"From Static to Dynamic: Adapting Landmark-Aware Image Models for Facial Expression Recognition in Videos","created":"2023-12-09","cited_by_count":39},{"id":"2312.04293","title":"GPT-4V with Emotion: A Zero-shot Benchmark for Generalized Emotion Recognition","created":"2023-12-07","cited_by_count":38},{"id":"2403.12960","title":"FaceXFormer: A Unified Transformer for Facial Analysis","created":"2024-03-19","cited_by_count":34},{"id":"2310.16640","title":"EmoCLIP: A Vision-Language Method for Zero-Shot Video Facial Expression Recognition","created":"2023-10-25","cited_by_count":31},{"id":"2401.05698","title":"HiCMAE: Hierarchical Contrastive Masked Autoencoder for Self-Supervised Audio-Visual Emotion Recognition","created":"2024-01-11","cited_by_count":30},{"id":"2403.04697","title":"AUFormer: Vision Transformers are Parameter-Efficient Facial Action Unit Detectors","created":"2024-03-07","cited_by_count":29},{"id":"2106.04520","title":"MVT: Mask Vision Transformer for Facial Expression Recognition in the wild","created":"2021-06-08","cited_by_count":27},{"id":"2404.05052","title":"Facial Affective Behavior Analysis with Instruction Tuning","created":"2024-04-07","cited_by_count":26},{"id":"2401.00416","title":"SVFAP: Self-supervised Video Facial Affect Perceiver","created":"2023-12-31","cited_by_count":18},{"id":"2307.09023","title":"LA-Net: Landmark-Aware Learning for Reliable Facial Expression Recognition under Label Noise","created":"2023-07-18","cited_by_count":17},{"id":"2310.19636","title":"Leave No Stone Unturned: Mine Extra Knowledge for Imbalanced Facial Expression Recognition","created":"2023-10-30","cited_by_count":17},{"id":"2308.07770","title":"Multi-scale Promoted Self-adjusting Correlation Learning for Facial Action Unit Detection","created":"2023-08-15","cited_by_count":14},{"id":"2207.11081","title":"Emotion Separation and Recognition from a Facial Expression by Generating the Poker Face with Vision Transformers","created":"2022-07-22","cited_by_count":9},{"id":"1805.00326","title":"I Know How You Feel: Emotion Recognition with Facial Landmarks","created":"2018-04-22","cited_by_count":7},{"id":"2106.15453","title":"Critically examining the Domain Generalizability of Facial Expression Recognition models","created":"2021-06-29","cited_by_count":4}],"next_cursor":null}