{"list":"other","total":54,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"id":"1705.07750","title":"Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset","created":"2017-05-22","cited_by_count":3270},{"id":"2109.01134","title":"Learning to Prompt for Vision-Language Models","created":"2021-09-02","cited_by_count":2281},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"2006.16668","title":"GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding","created":"2020-06-30","cited_by_count":1631},{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620},{"id":"2203.05482","title":"Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","created":"2022-03-10","cited_by_count":1396},{"id":"1609.04836","title":"On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima","created":"2016-09-15","cited_by_count":1352},{"id":"2012.14913","title":"Transformer Feed-Forward Layers Are Key-Value Memories","created":"2020-12-29","cited_by_count":1336},{"id":"1711.11248","title":"A Closer Look at Spatiotemporal Convolutions for Action Recognition","created":"2017-11-30","cited_by_count":1143},{"id":"1712.09913","title":"Visualizing the Loss Landscape of Neural Nets","created":"2017-12-28","cited_by_count":1130},{"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":"2104.13921","title":"Open-vocabulary Object Detection via Vision and Language Knowledge Distillation","created":"2021-04-28","cited_by_count":906},{"id":"2104.11227","title":"Multiscale Vision Transformers","created":"2021-04-22","cited_by_count":897},{"id":"2111.11432","title":"Florence: A New Foundation Model for Computer Vision","created":"2021-11-22","cited_by_count":804},{"id":"2106.05974","title":"Scaling Vision with Sparse Mixture of Experts","created":"2021-06-10","cited_by_count":747},{"id":"2201.03546","title":"Language-driven Semantic Segmentation","created":"2022-01-10","cited_by_count":717},{"id":"1706.08947","title":"Exploring Generalization in Deep Learning","created":"2017-06-27","cited_by_count":600},{"id":"2104.08164","title":"Editing Factual Knowledge in Language Models","created":"2021-04-16","cited_by_count":553},{"id":"2202.11094","title":"GroupViT: Semantic Segmentation Emerges from Text Supervision","created":"2022-02-22","cited_by_count":531},{"id":"2111.03930","title":"Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modeling","created":"2021-11-06","cited_by_count":431},{"id":"2008.03800","title":"Spatiotemporal Contrastive Video Representation Learning","created":"2020-08-09","cited_by_count":372},{"id":"1808.01340","title":"A Short Note about Kinetics-600","created":"2018-08-03","cited_by_count":333},{"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":"2104.14558","title":"A Large-Scale Study on Unsupervised Spatiotemporal Representation Learning","created":"2021-04-29","cited_by_count":214},{"id":"2206.02770","title":"Multimodal Contrastive Learning with LIMoE: the Language-Image Mixture of Experts","created":"2022-06-06","cited_by_count":203},{"id":"2206.13559","title":"ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learning","created":"2022-06-27","cited_by_count":193},{"id":"2212.03640","title":"Fine-tuned CLIP Models are Efficient Video Learners","created":"2022-12-06","cited_by_count":179},{"id":"2302.03024","title":"AIM: Adapting Image Models for Efficient Video Action Recognition","created":"2023-02-06","cited_by_count":148},{"id":"2210.17451","title":"AdaMix: Mixture-of-Adaptations for Parameter-efficient Model Tuning","created":"2022-10-31","cited_by_count":137},{"id":"2303.13076","title":"CORA: Adapting CLIP for Open-Vocabulary Detection with Region Prompting and Anchor Pre-Matching","created":"2023-03-23","cited_by_count":133},{"id":"2110.04260","title":"Taming Sparsely Activated Transformer with Stochastic Experts","created":"2021-10-08","cited_by_count":113},{"id":"2304.03307","title":"Vita-CLIP: Video and text adaptive CLIP via Multimodal Prompting","created":"2023-04-06","cited_by_count":91},{"id":"1706.10239","title":"Towards Understanding Generalization of Deep Learning: Perspective of Loss Landscapes","created":"2017-06-30","cited_by_count":84},{"id":"2108.02833","title":"Elaborative Rehearsal for Zero-shot Action Recognition","created":"2021-08-05","cited_by_count":77},{"id":"2010.16402","title":"Why Do Better Loss Functions Lead to Less Transferable Features?","created":"2020-10-30","cited_by_count":73},{"id":"2207.01297","title":"Revisiting Classifier: Transferring Vision-Language Models for Video Recognition","created":"2022-07-04","cited_by_count":71},{"id":"2302.00624","title":"Open-VCLIP: Transforming CLIP to an Open-vocabulary Video Model via Interpolated Weight Optimization","created":"2023-02-01","cited_by_count":55},{"id":"2301.00182","title":"Bidirectional Cross-Modal Knowledge Exploration for Video Recognition with Pre-trained Vision-Language Models","created":"2022-12-31","cited_by_count":49},{"id":"2304.10465","title":"Implicit Temporal Modeling with Learnable Alignment for Video Recognition","created":"2023-04-20","cited_by_count":46},{"id":"2303.08914","title":"MAtch, eXpand and Improve: Unsupervised Finetuning for Zero-Shot Action Recognition with Language Knowledge","created":"2023-03-15","cited_by_count":43},{"id":"2402.03241","title":"FROSTER: Frozen CLIP Is A Strong Teacher for Open-Vocabulary Action Recognition","created":"2024-02-05","cited_by_count":36},{"id":"2311.01723","title":"Towards Calibrated Robust Fine-Tuning of Vision-Language Models","created":"2023-11-03","cited_by_count":35},{"id":"2309.07911","title":"Disentangling Spatial and Temporal Learning for Efficient Image-to-Video Transfer Learning","created":"2023-09-14","cited_by_count":32},{"id":"2203.01104","title":"Parameter-Efficient Mixture-of-Experts Architecture for Pre-trained Language Models","created":"2022-03-02","cited_by_count":31},{"id":"2206.15369","title":"No Reason for No Supervision: Improved Generalization in Supervised Models","created":"2022-06-30","cited_by_count":23},{"id":"2308.04828","title":"Seeing in Flowing: Adapting CLIP for Action Recognition with Motion Prompts Learning","created":"2023-08-09","cited_by_count":16},{"id":"2402.15726","title":"CLIPose: Category-Level Object Pose Estimation with Pre-trained Vision-Language Knowledge","created":"2024-02-24","cited_by_count":16},{"id":"2309.00297","title":"Fine-Grained Spatiotemporal Motion Alignment for Contrastive Video Representation Learning","created":"2023-09-01","cited_by_count":7},{"id":"2308.06897","title":"Orthogonal Temporal Interpolation for Zero-Shot Video Recognition","created":"2023-08-14","cited_by_count":6}],"next_cursor":null}