{"list":"other","total":52,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"1801.04381","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks","created":"2018-01-13","cited_by_count":4795},{"id":"1902.00751","title":"Parameter-Efficient Transfer Learning for NLP","created":"2019-02-02","cited_by_count":4236},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"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":"1711.11248","title":"A Closer Look at Spatiotemporal Convolutions for Action Recognition","created":"2017-11-30","cited_by_count":1143},{"id":"2110.04366","title":"Towards a Unified View of Parameter-Efficient Transfer Learning","created":"2021-10-08","cited_by_count":872},{"id":"2205.13535","title":"AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition","created":"2022-05-26","cited_by_count":719},{"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":"2209.00647","title":"Visual Prompting via Image Inpainting","created":"2022-09-01","cited_by_count":250},{"id":"2206.13559","title":"ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learning","created":"2022-06-27","cited_by_count":193},{"id":"1804.07573","title":"MobileFaceNets: Efficient CNNs for Accurate Real-Time Face Verification on Mobile Devices","created":"2018-04-20","cited_by_count":182},{"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":"2302.03024","title":"AIM: Adapting Image Models for Efficient Video Action Recognition","created":"2023-02-06","cited_by_count":148},{"id":"2303.10826","title":"Visual Prompt Multi-Modal Tracking","created":"2023-03-20","cited_by_count":142},{"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":"2303.01498","title":"ABAW: Valence-Arousal Estimation, Expression Recognition, Action Unit Detection & Emotional Reaction Intensity Estimation Challenges","created":"2023-03-02","cited_by_count":110},{"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":"2108.11116","title":"TransFER: Learning Relation-aware Facial Expression Representations with Transformers","created":"2021-08-25","cited_by_count":85},{"id":"2210.00990","title":"Visual Prompt Tuning for Generative Transfer Learning","created":"2022-10-03","cited_by_count":75},{"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":"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":"2211.06627","title":"MARLIN: Masked Autoencoder for facial video Representation LearnINg","created":"2022-11-12","cited_by_count":57},{"id":"2108.08504","title":"Understanding and Mitigating Annotation Bias in Facial Expression Recognition","created":"2021-08-19","cited_by_count":50},{"id":"2103.16854","title":"Facial Expression Recognition with Visual Transformers and Attentional Selective Fusion","created":"2021-03-31","cited_by_count":49},{"id":"2204.04083","title":"POSTER: A Pyramid Cross-Fusion Transformer Network for Facial Expression Recognition","created":"2022-04-08","cited_by_count":49},{"id":"2308.13382","title":"Prompting Visual-Language Models for Dynamic Facial Expression Recognition","created":"2023-08-25","cited_by_count":44},{"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":"1906.06196","title":"Factorized Higher-Order CNNs with an Application to Spatio-Temporal Emotion Estimation","created":"2019-06-14","cited_by_count":40},{"id":"2212.05463","title":"Vision Transformer with Attentive Pooling for Robust Facial Expression Recognition","created":"2022-12-11","cited_by_count":35},{"id":"2109.08409","title":"Expression Snippet Transformer for Robust Video-based Facial Expression Recognition","created":"2021-09-17","cited_by_count":33},{"id":"2209.10448","title":"Uncertainty-aware Label Distribution Learning for Facial Expression Recognition","created":"2022-09-21","cited_by_count":30},{"id":"2205.04749","title":"Spatio-Temporal Transformer for Dynamic Facial Expression Recognition in the Wild","created":"2022-05-10","cited_by_count":29},{"id":"2207.11660","title":"MAR: Masked Autoencoders for Efficient Action Recognition","created":"2022-07-24","cited_by_count":29},{"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":"2106.04520","title":"MVT: Mask Vision Transformer for Facial Expression Recognition in the wild","created":"2021-06-08","cited_by_count":27},{"id":"2206.04975","title":"NR-DFERNet: Noise-Robust Network for Dynamic Facial Expression Recognition","created":"2022-06-10","cited_by_count":27},{"id":"1902.10859","title":"PFLD: A Practical Facial Landmark Detector","created":"2019-02-28","cited_by_count":26},{"id":"2308.08414","title":"Tem-adapter: Adapting Image-Text Pretraining for Video Question Answer","created":"2023-08-16","cited_by_count":22},{"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":"1905.10784","title":"Impact of facial landmark localization on facial expression recognition","created":"2019-05-26","cited_by_count":7},{"id":"2303.09164","title":"Multimodal Feature Extraction and Fusion for Emotional Reaction Intensity Estimation and Expression Classification in Videos with Transformers","created":"2023-03-16","cited_by_count":5}],"next_cursor":null}