{"list":"other","total":72,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"1703.05175","title":"Prototypical Networks for Few-shot Learning","created":"2017-03-15","cited_by_count":3015},{"id":"1412.3555","title":"Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling","created":"2014-12-11","cited_by_count":2367},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"1606.04080","title":"Matching Networks for One Shot Learning","created":"2016-06-13","cited_by_count":2255},{"id":"1901.02860","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","created":"2019-01-09","cited_by_count":1850},{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620},{"id":"2107.07651","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","created":"2021-07-16","cited_by_count":1619},{"id":"2203.05557","title":"Conditional Prompt Learning for Vision-Language Models","created":"2022-03-10","cited_by_count":1433},{"id":"2203.03605","title":"DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection","created":"2022-03-07","cited_by_count":1319},{"id":"2004.06165","title":"Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks","created":"2020-04-13","cited_by_count":1214},{"id":"1711.06025","title":"Learning to Compare: Relation Network for Few-Shot Learning","created":"2017-11-16","cited_by_count":1143},{"id":"1706.04261","title":"The \"something something\" video database for learning and evaluating visual common sense","created":"2017-06-13","cited_by_count":1103},{"id":"2110.04544","title":"CLIP-Adapter: Better Vision-Language Models with Feature Adapters","created":"2021-10-09","cited_by_count":1026},{"id":"2104.13921","title":"Open-vocabulary Object Detection via Vision and Language Knowledge Distillation","created":"2021-04-28","cited_by_count":906},{"id":"1608.00859","title":"Temporal Segment Networks: Towards Good Practices for Deep Action Recognition","created":"2016-08-02","cited_by_count":902},{"id":"1811.08383","title":"TSM: Temporal Shift Module for Efficient Video Understanding","created":"2018-11-20","cited_by_count":856},{"id":"2201.03546","title":"Language-driven Semantic Segmentation","created":"2022-01-10","cited_by_count":717},{"id":"1303.5778","title":"Speech Recognition with Deep Recurrent Neural Networks","created":"2013-03-22","cited_by_count":669},{"id":"2112.09106","title":"RegionCLIP: Region-based Language-Image Pretraining","created":"2021-12-16","cited_by_count":616},{"id":"2111.07991","title":"LiT: Zero-Shot Transfer with Locked-image text Tuning","created":"2021-11-15","cited_by_count":577},{"id":"2112.01518","title":"DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting","created":"2021-12-02","cited_by_count":532},{"id":"1909.04630","title":"Meta-Learning with Implicit Gradients","created":"2019-09-10","cited_by_count":525},{"id":"1807.05960","title":"Meta-Learning with Latent Embedding Optimization","created":"2018-07-16","cited_by_count":476},{"id":"2111.03930","title":"Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modeling","created":"2021-11-06","cited_by_count":431},{"id":"1707.09835","title":"Meta-SGD: Learning to Learn Quickly for Few-Shot Learning","created":"2017-07-31","cited_by_count":379},{"id":"2111.15174","title":"CRIS: CLIP-Driven Referring Image Segmentation","created":"2021-11-30","cited_by_count":353},{"id":"1711.08496","title":"Temporal Relational Reasoning in Videos","created":"2017-11-22","cited_by_count":324},{"id":"2208.02816","title":"Expanding Language-Image Pretrained Models for General Video Recognition","created":"2022-08-04","cited_by_count":321},{"id":"2109.08472","title":"ActionCLIP: A New Paradigm for Video Action Recognition","created":"2021-09-17","cited_by_count":320},{"id":"2112.04478","title":"Prompting Visual-Language Models for Efficient Video Understanding","created":"2021-12-08","cited_by_count":310},{"id":"1812.03664","title":"Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions","created":"2018-12-10","cited_by_count":294},{"id":"2012.15409","title":"UNIMO: Towards Unified-Modal Understanding and Generation via Cross-Modal Contrastive Learning","created":"2020-12-31","cited_by_count":239},{"id":"2204.03610","title":"Unified Contrastive Learning in Image-Text-Label Space","created":"2022-04-07","cited_by_count":194},{"id":"2208.03550","title":"Frozen CLIP Models are Efficient Video Learners","created":"2022-08-06","cited_by_count":182},{"id":"2212.03640","title":"Fine-tuned CLIP Models are Efficient Video Learners","created":"2022-12-06","cited_by_count":179},{"id":"1805.07722","title":"Task-Agnostic Meta-Learning for Few-shot Learning","created":"2018-05-20","cited_by_count":151},{"id":"1906.11415","title":"Few-Shot Video Classification via Temporal Alignment","created":"2019-06-27","cited_by_count":125},{"id":"2003.13193","title":"Adversarial Feature Hallucination Networks for Few-Shot Learning","created":"2020-03-30","cited_by_count":110},{"id":"2207.07852","title":"TS2-Net: Token Shift and Selection Transformer for Text-Video Retrieval","created":"2022-07-16","cited_by_count":104},{"id":"1905.11116","title":"Finding Task-Relevant Features for Few-Shot Learning by Category Traversal","created":"2019-05-27","cited_by_count":101},{"id":"1902.07104","title":"Adaptive Cross-Modal Few-Shot Learning","created":"2019-02-19","cited_by_count":95},{"id":"1905.06549","title":"TapNet: Neural Network Augmented with Task-Adaptive Projection for Few-Shot Learning","created":"2019-05-16","cited_by_count":91},{"id":"2101.06184","title":"Temporal-Relational CrossTransformers for Few-Shot Action Recognition","created":"2021-01-15","cited_by_count":84},{"id":"2106.11149","title":"OadTR: Online Action Detection with Transformers","created":"2021-06-21","cited_by_count":83},{"id":"1907.09021","title":"TARN: Temporal Attentive Relation Network for Few-Shot and Zero-Shot Action Recognition","created":"2019-07-21","cited_by_count":71},{"id":"2207.01297","title":"Revisiting Classifier: Transferring Vision-Language Models for Video Recognition","created":"2022-07-04","cited_by_count":71},{"id":"2112.05132","title":"Spatio-temporal Relation Modeling for Few-shot Action Recognition","created":"2021-12-09","cited_by_count":53},{"id":"2204.13423","title":"Hybrid Relation Guided Set Matching for Few-shot Action Recognition","created":"2022-04-28","cited_by_count":50},{"id":"2011.08899","title":"Multimodal Prototypical Networks for Few-shot Learning","created":"2020-11-17","cited_by_count":48},{"id":"2010.11757","title":"Deep Analysis of CNN-based Spatio-temporal Representations for Action Recognition","created":"2020-10-22","cited_by_count":45},{"id":"2206.08919","title":"VLMixer: Unpaired Vision-Language Pre-training via Cross-Modal CutMix","created":"2022-06-17","cited_by_count":45},{"id":"2201.06696","title":"ProposalCLIP: Unsupervised Open-Category Object Proposal Generation via Exploiting CLIP Cues","created":"2022-01-18","cited_by_count":42},{"id":"2104.03214","title":"Self-Supervised Learning for Semi-Supervised Temporal Action Proposal","created":"2021-04-07","cited_by_count":39},{"id":"2107.04782","title":"TA2N: Two-Stage Action Alignment Network for Few-shot Action Recognition","created":"2021-07-10","cited_by_count":35},{"id":"2207.05515","title":"Compound Prototype Matching for Few-shot Action Recognition","created":"2022-07-12","cited_by_count":35},{"id":"1906.02944","title":"Learning Adaptive Classifiers Synthesis for Generalized Few-Shot Learning","created":"2019-06-07","cited_by_count":29},{"id":"2101.08085","title":"Few-shot Action Recognition with Prototype-centered Attentive Learning","created":"2021-01-20","cited_by_count":28},{"id":"2105.04823","title":"Learning Implicit Temporal Alignment for Few-shot Video Classification","created":"2021-05-11","cited_by_count":27},{"id":"2207.10785","title":"Inductive and Transductive Few-Shot Video Classification via Appearance and Temporal Alignments","created":"2022-07-21","cited_by_count":23},{"id":"2204.01208","title":"Attribute Prototype Network for Any-Shot Learning","created":"2022-04-04","cited_by_count":19},{"id":"2112.07515","title":"CoCo-BERT: Improving Video-Language Pre-training with Contrastive Cross-modal Matching and Denoising","created":"2021-12-14","cited_by_count":18},{"id":"2301.03330","title":"HyRSM++: Hybrid Relation Guided Temporal Set Matching for Few-shot Action Recognition","created":"2023-01-09","cited_by_count":12},{"id":"1811.09192","title":"Self Paced Adversarial Training for Multimodal Few-shot Learning","created":"2018-11-22","cited_by_count":8}],"next_cursor":null}