{"list":"other","total":53,"rows":[{"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":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"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":"2203.11171","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","created":"2022-03-21","cited_by_count":5708},{"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":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"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":"2304.14178","title":"mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality","created":"2023-04-27","cited_by_count":1040},{"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":"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":"2305.15408","title":"Towards Revealing the Mystery behind Chain of Thought: A Theoretical Perspective","created":"2023-05-24","cited_by_count":294},{"id":"2301.13379","title":"Faithful Chain-of-Thought Reasoning","created":"2023-01-31","cited_by_count":288},{"id":"2305.15021","title":"EmbodiedGPT: Vision-Language Pre-Training via Embodied Chain of Thought","created":"2023-05-24","cited_by_count":279},{"id":"1804.08348","title":"Deep Facial Expression Recognition: A Survey","created":"2018-04-23","cited_by_count":270},{"id":"2112.03109","title":"General Facial Representation Learning in a Visual-Linguistic Manner","created":"2021-12-06","cited_by_count":195},{"id":"2002.10392","title":"Suppressing Uncertainties for Large-Scale Facial Expression Recognition","created":"2020-02-24","cited_by_count":157},{"id":"2401.06805","title":"Exploring the Reasoning Abilities of Multimodal Large Language Models (MLLMs): A Comprehensive Survey on Emerging Trends in Multimodal Reasoning","created":"2024-01-10","cited_by_count":136},{"id":"2309.16058","title":"AnyMAL: An Efficient and Scalable Any-Modality Augmented Language Model","created":"2023-09-27","cited_by_count":93},{"id":"2104.00232","title":"Dive into Ambiguity: Latent Distribution Mining and Pairwise Uncertainty Estimation for Facial Expression Recognition","created":"2021-04-01","cited_by_count":89},{"id":"2105.04714","title":"Sample and Computation Redistribution for Efficient Face Detection","created":"2021-05-10","cited_by_count":89},{"id":"2205.01782","title":"Learning Multi-dimensional Edge Feature-based AU Relation Graph for Facial Action Unit Recognition","created":"2022-05-02","cited_by_count":82},{"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":"2109.07270","title":"Distract Your Attention: Multi-head Cross Attention Network for Facial Expression Recognition","created":"2021-09-15","cited_by_count":55},{"id":"2212.02291","title":"I2MVFormer: Large Language Model Generated Multi-View Document Supervision for Zero-Shot Image Classification","created":"2022-12-05","cited_by_count":54},{"id":"1904.09939","title":"Semantic Relationships Guided Representation Learning for Facial Action Unit Recognition","created":"2019-04-22","cited_by_count":53},{"id":"2103.16854","title":"Facial Expression Recognition with Visual Transformers and Attentional Selective Fusion","created":"2021-03-31","cited_by_count":49},{"id":"2310.00582","title":"Pink: Unveiling the Power of Referential Comprehension for Multi-modal LLMs","created":"2023-10-01","cited_by_count":47},{"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":"2310.16640","title":"EmoCLIP: A Vision-Language Method for Zero-Shot Video Facial Expression Recognition","created":"2023-10-25","cited_by_count":31},{"id":"2303.00193","title":"CLIPER: A Unified Vision-Language Framework for In-the-Wild Facial Expression Recognition","created":"2023-03-01","cited_by_count":28},{"id":"2408.11424","title":"EMO-LLaMA: Enhancing Facial Emotion Understanding with Instruction Tuning","created":"2024-08-21","cited_by_count":28},{"id":"1702.02925","title":"EAC-Net: A Region-based Deep Enhancing and Cropping Approach for Facial Action Unit Detection","created":"2017-02-09","cited_by_count":26},{"id":"2404.05052","title":"Facial Affective Behavior Analysis with Instruction Tuning","created":"2024-04-07","cited_by_count":26},{"id":"1509.03936","title":"Learning Social Relation Traits from Face Images","created":"2015-09-14","cited_by_count":25},{"id":"2405.19100","title":"Enhancing Zero-Shot Facial Expression Recognition by LLM Knowledge Transfer","created":"2024-05-29","cited_by_count":18},{"id":"2211.13490","title":"Pose-disentangled Contrastive Learning for Self-supervised Facial Representation","created":"2022-11-24","cited_by_count":17},{"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":"2403.02138","title":"Self-Supervised Facial Representation Learning with Facial Region Awareness","created":"2024-03-04","cited_by_count":17},{"id":"2406.04659","title":"LocLLM: Exploiting Generalizable Human Keypoint Localization via Large Language Model","created":"2024-06-07","cited_by_count":17},{"id":"2304.00058","title":"Weakly-Supervised Text-driven Contrastive Learning for Facial Behavior Understanding","created":"2023-03-31","cited_by_count":16},{"id":"2307.11404","title":"Latent-OFER: Detect, Mask, and Reconstruct with Latent Vectors for Occluded Facial Expression Recognition","created":"2023-07-21","cited_by_count":13},{"id":"2308.12380","title":"FG-Net: Facial Action Unit Detection with Generalizable Pyramidal Features","created":"2023-08-23","cited_by_count":12},{"id":"2209.12244","title":"Multimodal Channel-Mixing: Channel and Spatial Masked AutoEncoder on Facial Action Unit Detection","created":"2022-09-25","cited_by_count":11},{"id":"2010.07614","title":"THIN: THrowable Information Networks and Application for Facial Expression Recognition In The Wild","created":"2020-10-15","cited_by_count":9},{"id":"1904.01509","title":"FEAFA: A Well-Annotated Dataset for Facial Expression Analysis and 3D Facial Animation","created":"2019-04-02","cited_by_count":7},{"id":"2111.02751","title":"FEAFA+: An Extended Well-Annotated Dataset for Facial Expression Analysis and 3D Facial Animation","created":"2021-11-04","cited_by_count":7},{"id":"2211.06143","title":"FAN-Trans: Online Knowledge Distillation for Facial Action Unit Detection","created":"2022-11-11","cited_by_count":5}],"next_cursor":null}